Current Medical Imaging - Volume 20, Issue 1, 2024

Abdominal multi-slice helical computed tomography (CT) and contrast-enhanced scanning have been widely recognized clinically.

The impact of the deep learning image reconstruction (DLIR) on the quality of dynamic contrast-enhanced CT imaging of primary liver cancer lesions was evaluated through comparison with the filtered back projection (FBP) and the new generation of adaptive statistical iterative reconstruction-V (ASIR-V).

We evaluated the image noise of the lesion, fine structures inside the lesion, and diagnostic confidence in 48 liver cancer subjects. The CT values of the solid part of the lesion and the adjacent normal liver tissue and the systolic and diastolic blood pressure (SD) values of the right paravertebral muscle were measured. The muscle SD value was considered as the background noise of the image, and the signal noise ratio (SNR) and contrast signal-to-noise ratio (CNR) of the lesion and normal liver parenchyma were calculated.

High consistency in the evaluation of image noise (Kappa = 0.717). The Kappa values for margin/pseudocapsule, fine structure within the lesion, and diagnostic confidence were 0.463, 0.527, and 0.625, respectively. Besides, the differences in SD, SNR and CNR data of reconstructed lesion images among the six groups were statistically significant.

The contrast-enhanced CT image noise of DLIR-H in the portal venous phase is much lower than that of ASIR-V and FBP in primary liver cancer patients. In terms of the lesion structure display, the new reconstruction algorithm DLIR is superior.

To investigate CT, MRI, and PET/CT features with histopathological findings of primary thymic neuroendocrine tumor.

All 9 cases with pathologically proven primary thymic neuroendocrine tumors were reviewed retrospectively. Among them, 7 underwent enhanced CT, 1 with MRI (enhanced) and another with PET/CT scan. Multiple characters were examined, including tumor location, contour, CT attenuation, enhancement pattern, involvement of surrounding structure and lymphadenopathy.

Among 9 patients studied, 7 (77%) masses were located in the anterior superior mediastinum, 1 in the anterior superior-middle mediastinum, and 1 in the anterior and middle mediastinum. The maximum diameter (longitudinal) ranged from 4.2 to 23 cm (mean ± standard deviation, 9.5 cm ± 2.8). Four masses had irregular, 3 had lobulated, and 2 had smooth contours, while 8 masses had clear margins and 1 had an ill-defined margin. Six masses showed heterogeneous attenuation with necrotic/cystic component (n=5), calcification (n=2) and hemorrhage(n=1), and 3 showed homogeneous attenuation on the non-enhanced image. After contrast administration, 8 masses showed heterogeneous attenuation, and 1 showed homogeneous attenuation with tumor vessels visible in 4 masses. Among all, 8 masses showed strong enhancement, and 1 showed moderate enhancement in comparison to muscles in the anterior thoracic wall on enhanced images. Involvement of adjacent mediastinal structures was observed in 5 cases. Immunohistochemical analysis showed that the tumor cells were positive for CgA, Syn, CK, CD56 and EMA.

Primary NETs are large masses located anterior superior mediastinum, irregular in contour, showing heterogeneous attenuation with necrotic/cystic component and strong heterogeneous enhancement with tumor vessels, compressing local mediastinal structures. In addition, immunohis-tochemical examination is required in such a diagnosis.

With the rapid development in computed tomography (CT), the establishment of artificial intelligence (AI) technology and improved awareness of health in folks in the decades, it becomes easier to detect and predict pulmonary nodules with high accuracy. The accurate identification of benign and malignant pulmonary nodules has been challenging for radiologists and clinicians. Therefore, this study applied the unenhanced CT images-based radiomics to identify the benign or malignant pulmonary nodules.

One hundred and four cases of pulmonary nodules confirmed by clinicopathology were analyzed retrospectively, including 79 cases of malignant nodules and 25 cases of benign nodules. They were randomly divided into a training group (n = 74 cases) and test group (n = 30 cases) according to the ratio of 7:3. Using ITK-SNAP software to manually mark the region of interest (ROI), and using AK software (Analysis kit, Version 3.0.0.R, GE Healthcare, America) to extract image radiomics features, a total of 1316 radiomics features were extracted. Then, the minimum–redundancy–maximum–relevance (mRMR) algorithms were used to preliminarily reduce the dimension, and retain the 30 most meaningful features, and then the least absolute shrinkage and selection operator (LASSO) algorithm was used to select the optimal subset of features, so as to establish the final model. The performance of the model was evaluated by using the receiver operating characteristic (ROC) curve, area under the ROC curve (AUC), accuracy, sensitivity and specificity. Calibration refers to the agreement between observed endpoints and predictions, and the clinical benefit of the model to patients was evaluated by decision curve analysis (DCA).

The accuracy, sensitivity, and specificity of the training and testing groups were 81.0%, 77.7%, 82.1% and 76.6%, 85.7%, 73.9%, respectively, and the corresponding AUCs were of 0.83 in both groups.

CT image-based radiomics could differentiate benign from malignant pulmonary nodules, which might provide a new method for clinicians to detect benign and malignant pulmonary nodules.

This study aims to assess the accuracy of computed tomography (CT) in detecting recurrent laryngeal tumors after failed chemoradiation therapy (CRT).

Local recurrence of laryngeal tumors following CRT has been reported in approximately 25%, yet it is often difficult to detect.

Ten patients with laryngeal cancer who failed CRT and subsequently underwent salvage total laryngectomy were included. The laryngeal subsites involved in the tumor were identified based on postoperative pathology. The corresponding preoperative CT scans were selected for review by seven experts (head-and-neck surgeons or radiologists) who scored the extent of tumor spread on each scan on a 5-point scale, from no tumor detected to clearly visible tumor.

The rates of high tumor detectability (scores 4-5) varied according to laryngeal subsite, from 75% in the glottic region, to 45% in the subglottic region, and to 19% in the supraglottic region (P=0.01). The detectability rates were higher on scans performed 2 years or more after CRT.

The CT evaluation of laryngeal cancer after CRT has limited value, particularly in the epiglottis and subglottis.

Immunoglobulin G4-related disease (IgG4-RD) is a relatively rare immune-mediated chronic inflammatory disease with fibrosis newly defined in recent years. It can involve multiple systems and organs with complex clinical manifestations. Due to mass-like lesions, it is easily misdiagnosed as tumors.

Herein, we report a 57-year-old woman treated for submandibular mass and anosmia. The serum IgG4 level was increased. The biopsy of the submandibular gland indicated salivary gland tissue and hyperplasia of fibrous tissue and lymphoid tissue. Immunohistochemical examination showed a large number of IgG4-positive plasma cells. M protein was found in the patient's serum by immunofixation electrophoresis, and plasma cell diseases were excluded by bone marrow puncture. PET/CT examination showed that besides the submandibular glands, the parotid gland, common bile duct, the transitional part of the left renal pelvis and ureter, retroperitoneum in the lower abdomen, and multiple lymph nodes were also involved. The patient was diagnosed with IgG4-RD, and after treatment with glucocorticoid, the enlargement of submandibular glands and decreased olfactory function improved. After 14 weeks of treatment, the serological examinations, PET/CT, and ultrasound re-examination results showed significant improvement. So far, the patient has been followed up for 27 months and is in continuous remission.

This case report aims to raise awareness of IgG4-RD and explore the value of PET/CT in the diagnosis and efficacy monitoring of the disease.

The accurate diagnosis of superficial lymphadenopathy is challenging. We aim to explore a non-invasive and accurate machine-learning method for distinguishing benign lymph nodes, lymphoma, and metastatic lymph nodes.

The clinical data and ultrasound images of 160 patients with superficial lymphadenopathy (58 benign lymph nodes, 62 lymphoma, 40 metastatic lymph nodes) admitted to our hospital from January 2020 to November 2022 were retrospectively studied. Patients were randomly divided into a training set and test set according to the ratio of 6:4. Firstly, the radiomics features of each lymph node were extracted, and then a series of statistical methods were used to avoid over-fitting. Then, the gradient boosting machine(GBM) was used to build the model. The area under receiver(AUC) operating characteristic curve, precision, recall rate and F1 value were calculated to evaluate the effectiveness of the model.

Ten robust features were selected to build the model. The AUC values of benign lymph nodes, lymphoma and metastatic lymph nodes in the training set were 1.00, 0.98 and 0.99, and the AUC values of the test set were 0.96, 0.84 and 0.90, respectively.

It was a reliable and non-invasive method for the differential diagnosis of lymphadenopathy based on the model constructed by machine learning.

Medical image registration plays an important role in several applications. Existing approaches using unsupervised learning encounter issues due to the data imbalance problem, as their target is usually a continuous variable.

In this study, we introduce a novel approach known as Unsupervised Imbalanced Registration, to address the challenge of data imbalance and prevent overconfidence while increasing the accuracy and stability of 4D image registration.

Our approach involves performing unsupervised image mixtures to smooth the input space, followed by unsupervised image registration to learn the continual target. We evaluated our method on 4D-Lung using two widely used unsupervised methods, namely VoxelMorph and ViT-V-Net.

Our findings demonstrate that our proposed method significantly enhances the mean accuracy of registration by 3%-10% on a small dataset while also reducing the accuracy variance by 10%.

Unsupervised Imbalanced Registration is a promising approach that is compatible with current unsupervised image registration methods applied to 4D images.

Glaucoma is a significant cause of irreversible blindness worldwide, with symptoms often going undetected until the patient's visual field starts shrinking.

To develop an AI-based glaucoma detection method to reduce glaucoma-related blindness and offer more precise diagnosis.

Discusses various methods and technologies, including Heidelberg Retinal Tomography (HRT), Optical Coherence Tomography (OCT), and Fundus Photography, for obtaining relevant information about the presence of glaucoma in a patient. Additionally, it mentions the use of Support Vector Machines (SVMs) and Convolutional Neural Networks (CNNs) for glaucoma detection. There are many limitations for existing methods as; Asymptomatic Progression, reliance on subjective feedback, multiple tests required, late detection, limited availability of preventive tests, influence of external factors.

Findings reveal promising outcomes in terms of glaucoma detection accuracy, particularly in the analysis of the RIM-ONE-r3 dataset. By scrutinizing 20 images from the Healthy, Glaucoma, and Suspects categories through fundus image recognition, our developed AI model consistently achieved high diagnostic accuracy rates.

Our study suggests that further enhancements in glaucoma detection accuracy are attainable by augmenting the dataset with additional labeled images. We emphasize the significance of considering various application parameters when discussing the integration of computer-aided decision/management systems into healthcare frameworks.

Artificial intelligence (AI) is rapidly evolving in healthcare, with transformative potential. AI revolutionizes medical imaging by enabling online self-diagnosis for patients and improving diagnostic accuracy for healthcare professionals. While valuable datasets aid machine learning in disease detection, challenges persist in diagnosing similar lung conditions from chest X-rays. Integrating AI into healthcare holds promise for enhanced outcomes and efficiency.

In this article, we aim to present a new AI model that solves this challenge by allowing the differentiation, diagnosis and classification of three distinct diseases, whose symptoms are very similar. The fundamental contribution is to reduce the number of parameters used while maintaining the same level of precision for use in embedded systems.

Our proposed model combines the power of the neural network using the SqueezeNet architecture with a set of machine learning algorithms as classifiers, including logistic regression, support vector machine (SVM), k-nearest neighbors (KNN), decision tree, and naive Bayes. The chest X-ray dataset used in the proposed model consists of CXR images that are classified into four categories: pneumonia, tuberculosis, COVID-19, and normal cases.

Our proposed model demonstrated remarkable accuracy (97,32%), precision (97,33), F1 score (97,31%), recall (97,30%), and AUC (99,40), which is close to the best model. Whereas, the number of parameters used by our model (4,6 M) is very small compared to the best model in the literature (47M).

The model demonstrated good classification accuracy. In addition, the proposed model has the ability to use fewer parameters, which means it requires less internal memory and computing resources.

Colon cancer with liver metastasis is a common occurrence in clinical practice. The presence of liver metastasis has a significant impact on the treatment strategy of patients, so the first step is to diagnose whether it is liver metastasis. Imaging is one of the auxiliary methods for diagnosing liver metastases, but due to the presence of different diseases with the same shadow, we need to be cautious when using imaging methods for the diagnosis of liver metastases.

We report a 53-year-old female patient with sigmoid colon cancer and perforation who underwent a surgical operation. Three years after the operation, reexamination of the liver through computed tomography and magnetic resonance imagery scanning revealed multiple progressive liver lesions. However, the liver biopsy did not show malignant changes. Repeated analysis of the patient's liver magnetic resonance imaging revealed that multiple liver nodules were significantly enhanced in the arterial phase and that the portal vein density/signal ratio was higher than that of the liver parenchyma. The coincidence of doughnut-shaped nodules and high signal in the hepatobiliary phase, combined with the results of pathological liver puncture examination, led to nodular regenerative hyperplasia being considered as a possible diagnosis.

A review of the relevant literature showed that following oxaliplatin chemotherapy for colorectal cancer, it is not uncommon for doughnut-shaped nodules with obvious enhancement in the middle hepatic artery phase and high signal intensity in the hepatobiliary phase to develop. Such changes should be paid sufficient attention by radiologists.

Extrahepatic cholangiocarcinoma (EHCC), an exceedingly malignant neoplasm, often eludes early detection, culminating in a dire prognosis. Accurate cancer staging systems and pathological differentiation are designed to guide adjuvant interventions and predict postoperative prognoses.

This study sought to investigate the predictive capacity of DW-MRI in discerning T stages, lymph node metastasis, and pathological differentiation grades in patients with EHCC.

Eighty-five patients were pathologically diagnosed with EHCC and underwent abdominal MRI within two weeks before surgery at our hospital from Aug 2011 to Aug 2021. Tumor axial maximum area (AMA) and apparent diffusion coefficient (ADC) values for diverse T stages, N stages, and differentiation grades were retrospectively analyzed.

The Mann-Whitney U test displayed significantly higher lesion AMA values (P =0.006) and lower tumor ADC values (P = 0.001) in the node-positive group (median ADC and AMA value: 1.220×10^-3 mm²/s, 82.231 mm²) than in the node-negative group (median ADC and AMA value: 1.316×10^-3 mm²/s, 51.174 mm²). A tumor ADC value<1.249×10^-3 mm²/s from the receiver operating characteristic curve (AUC=0.725, P=0.001) exhibited the capability to predict node-positive EHCC with a sensitivity of 64.29%, and specificity of 73.68%. Furthermore, a progressive decrease in the degree of EHCC differentiation was associated with a reduction in the tumor ADC value (P=0.000).

The N stage and differentiation of EHCC can be evaluated non-invasively using diffusion-weighted MRI.

Artificial intelligence (AI) in medical imaging rapidly expands regarding image processing and interpretation. Therefore, the aim was to explore radiographers’ and radiologists’ perceptions and attitudes towards AI use in medical imaging technologies in Saudi Arabia.

The survey was distributed online, and responses were collected from 173 participants nationwide. Data analysis was performed using SPSS Statistics (version 27).

The participants scored an average of 1.7, 1.6, and 1.8 on a scale of 1–3 for attitudinal perspectives on clinical application and the positive and negative impact of integrating AI technology in diagnostic radiology. Lack of knowledge (43.9%) and perceived cyber threats (37.7%) were the most cited factors hindering AI implementation in Saudi Arabia.

The radiographers and radiologists in this study had a favorable attitude toward AI integration in diagnostic radiology; nonetheless, concerns were raised about data protection, cyber security, AI-related errors, and decision-making challenges.

The classification of Congenital Uterine Malformations (CONUTA) relies on coronal imaging of the uterus using 3D TVUS and MRI. In everyday practice, radiologists and gynaecologists often struggle to confidently categorize CONUTA due to varying classification systems and the lack of worldwide consensus.

The aim of this study was to evaluate the diagnostic concordance and discrepancies between two imaging techniques within the context of the ASRM, ESHRE/ESGE, and CUME systems.

Ninety-four patients suspected of having CONUTA underwent evaluation: 67 underwent 3D TVUS, 53 had MRI scans, and 34 were examined using both imaging techniques.

An initial cross-listing table of ASRM, ESHRE/ESGE, and CUME was created, and a flowchart schema was used to define the type of congenital uterine anomaly for each system

The prevalence of anomalies in each system was calculated, and Fleiss’ Kappa was used to assess and determine the level of agreement.

Class VI arcuate uterus was the most common form in ASRM 2016 and 2021, while the partially septate uterus predominated in the CUME 2018 and ESHRE/ESGE 2016 classification systems.

There is no discordance between classification systems for all fusion defects and complete septate type of absorption defects. In the ESHRE/ESGE system, nearly half of the abnormal uteruses were categorized as partially septate. However, the CUME system proved less effective in distinguishing between normal and arcuate uteruses.

Type 2 diabetes mellitus (T2DM) and hypertension (HT) are the two most common underlying diseases worldwide, and they often coexist. The long-term existence of both may lead to left ventricular dysfunction. Therefore, evaluating the cardiac function of T2DM patients with HT is vital to guide treatment and improve prognosis. Left ventricular pressure strain loops (LVPSL) combine left ventricular strain and afterload, which can quantify left ventricular energy expenditure and detect left ventricular subclinical systolic dysfunction. Many studies have focused on myocardial work (MW) in uncomplicated T2DM patients or simple HT patients, but a few have focused on T2DM patients with HT.

The study aimed to evaluate the MW changes in T2DM patients with HT using LVPSL and to find independent related factors of MW parameters.

40 T2DM patients, 35 HT patients, 40 T2DM patients with HT (T2DM+HT group), and 35 controls were enrolled. The differences between clinical data, conventional ultrasound parameters, and MW parameters were analyzed among the four groups.

The global longitudinal strain (GLS) of the T2DM group, HT group, and T2DM+HT group was lower than the control group (P<0.05). The global work index (GWI) and global constructive work (GCW) in the T2DM group were lower than other groups (P<0.05). The GWI of the HT group was higher than other groups (P<0.05), while GCW was only higher than the T2DM group and T2DM+HT group (P<0.05). The GWI and GCW of the T2DM+HT group were higher than the T2DM group and were lower than the HT group(P<0.05), while there was no significant difference with the control group. HT group and T2DM+HT group had higher global work waste (GWW) (P<0.05). The global work efficiency (GWE) of the T2DM+HT group was lower than other groups (P<0.05). Systolic blood pressure (SBP) and glycosylated hemoglobin (HbA1c) were independent factors of each MW parameter.

LVPSL can recognize left ventricular subclinical systolic dysfunction early in patients with T2DM and HT. Compared to simple T2DM or HT, the combination of T2DM and HT had greater damage to left ventricular systolic function. SBP and HbA1c are two factors that have a considerable impact on MW parameters. The impact of afterload on MW parameters should be paid more attention to.

The most difficult aspect of diagnosing lung cancer is early diagnosis. According to the American Cancer Society, each year, there are around 11 million newly diagnosed instances of cancer worldwide. Radiologists often turn to Computed Tomography (CT) scans to diagnose respiratory conditions, which can reveal if lung tissue remains normal or abnormal. However, there is an increased chance of inaccuracy and delay; therefore, radiologists are concerned with the physical segmentation of nodules.

The objective of the research is to implement an advanced modified threshold segmentation and classification model for early and accurate detection of lung cancer from CT images.

Using the Support Vector Machines (SVM) classifier as well as the Artificial Neural Network (ANN) classifier, the authors propose using Modified adaptive threshold segmentation as a segmentation approach for cancer detection. Here, Lung Image Database Consortium (LIDC) datasets, a collection of CT scans, are used as the video frames in an investigation to authorize the recitation of the suggested technique.

Both quantitative as well as qualitative analyses are used to analyze the segmentation function of the anticipated algorithm. Both the ANN and SVM classifiers used in the suggested technique for lung cancer diagnosis achieve world-record levels of accuracy, with the former achieving a 96.3% detection rate and the latter a 97% rate of accuracy.

This innovation may have a major impact on the worldwide rate of lung cancer rate due to its ability to detect lung tumors in their earliest stages when they are most amenable to being avoided and treated. This method is useful because it provides more information and facilitates quick, precise decision-making for doctors diagnosing lung cancer in their patients.

Lymphaticovenous anastomosis (LVA) surgery is an effective treatment for lymphedema. Accurate evaluation and localization of the superficial lymphatic vessels before the operation is crucial for the success of the operation. Contrast-enhanced ultrasound (CEUS) is a new ultrasound technology, and its clinical application value in LVA surgery has not been established.

This study aimed to assess the efficacy of CEUS in LVA surgery and provide a novel approach for the clinical assessment and localization of superficial lymphatic vessels.

Retrospective analysis of imaging and surgical data was performed on 20 LVA patients. Among them, 10 cases underwent evaluation and localization using indocyanine green (ICG) lymphatic imaging (Group A), while 10 cases were evaluated and localized using CEUS (Group B). The differences in surgical data between the two groups were compared and analyzed.

All 20 patients were female (mean age, 57.7 years ± 6.3 [SD]). CEUS demonstrated superior visualization and localization of superficial lymphatic vessels. The average diameter of lymphatic vessels identified in the CEUS group was significantly greater than that in the ICG group (0.78±0.06 vs. 0.52±0.05mm; P<0.001). The duration of operation in group B was significantly shorter than that in group A (4.47±0.37 vs. 6.70±0.45mm; P<0.001). The number of anastomosed lymphatic vessels in group B was less than that in group A [5.0(4.0, 6.0) vs. 9.5 (9.0, 11.3); P<0.001].

CEUS can serve as a viable alternative to ICG lymphatic imaging, facilitating improved lymphatic venous anastomosis surgery.

Recurrence of uterine cervical cancer is common and often shows a dismal prognosis. Local recurrence usually manifests as solid soft tissue lesions and has rarely been reported to have cystic lesions.

Herein, we report a case of recurrent uterine cervical cancer with initial manifestation as a hemorrhagic cyst, assessed using strain sonoelastography, CT, and MRI.

Although cystic recurrence is uncommon, newly detected simple or complex cystic lesions should be closely monitored.

To explore the development of a mind map-based predictive nursing protocol and assess its impact on the quality of images in patients undergoing high-concentration contrast three-dimensional computed tomography (CT) imaging of liver blood vessels.

A total of 600 patients who were admitted to Beijing You an Hospital were chosen for this prospective study and underwent high-concentration contrast three-dimensional CT imaging of liver blood vessels between April 2021 and December 2021. The patients were divided into two groups using the digital table method, with 300 cases. The control group received conventional nursing intervention, while the research group was provided with a mind map-based predictive nursing protocol. We recorded the image quality of three-dimensional CT imaging of liver blood vessels, satisfaction scores regarding nurse examination guidance, and the Self-Rating Anxiety Scale (SAS) and Self-Rating Depression Scale (SDS) in both groups.

The research group achieved a perfect rate of 100.00% for the high-quality three-dimensional CT imaging of liver blood vessels, which was noticeably higher compared to the rate of the control group of 98.67%. Patients in the research group expressed higher satisfaction levels regarding the guidance provided by nurses, including their attitude, timeliness, accuracy, and overall satisfaction, compared to the control group. Initially, the two groups had no notable differences in the SAS and SDS scores. However, after the intervention, both groups experienced a significant decrease in SAS and SDS scores, with the research group showing an even more substantial decline.

Through the creation of a mind map-based predictive nursing protocol and its implementation on patients undergoing high-concentration contrast three-dimensional CT imaging of liver blood vessels, it is possible to significantly enhance the quality of CT scans, alleviate feelings of anxiety and depression, increase patient satisfaction with examination guidance by nurses, and effectively decrease the occurrences of contrast agent leakage and allergic reactions to iodine.

Chest wall tuberculosis may develop if tuberculous (TB) lesions spread through the chest wall and invade the thoracic cavity. The presence of a mass on the patient's chest wall may be the first indication of TB, and a chest CT scan can help diagnose external penetrating chest wall TB, the incursion of tuberculosis from the lungs into the chest wall.

This study examines the safety and efficacy of thoracoscopic-assisted surgery for the treatment of penetrating chest wall tuberculosis as a means of exploring novel concepts of minimally invasive surgery.

Our hospital conducted a retrospective study of 25 patients with penetrating chest wall TB who underwent thoracoscopic surgery between January 2020 and June 2021. General demographics, CT scan data linked to surgery, and postoperative patient outcomes were compared between the two groups. The data was also evaluated to determine the range of operation time and the volume of bleeding from different foci in the thoracic cavity.

All procedures went well after patients took conventional antituberculosis medication for at least two weeks prior to surgery. CT scans showed that thoracoscopic surgery needed a smaller incision than traditional chest wall TB surgery, with no discernible increase in surgical time. Postoperative tube use, length of hospital stay, and blood loss were all significantly lower than they would have been with conventional surgery. In addition, thoracoscopy was associated with a significantly reduced rate of subsequent treatment. Fibrous plate development and calcification caused the longest operation times in the thoracoscopic surgery group, whereas multiple pleural tuberculomas generated the most hemorrhage. Thoracoscopic surgery usually reveals tuberculous foci hiding in the thoracic cavity.

Thethoracic surgery can eliminate the TB focus in the chest wall and intrathoracic while treating penetrating chest wall tuberculosis. The CT scan is a crucial part of the diagnostic process for these patients. Minor surgical trauma, low complication and recurrence rates, and good results. There is a greater distinction between the two surgical approaches for patients with penetrating chest wall TB as opposed to those with basic chest wall tuberculosis.

This study aims to investigate the value of gemstone spectral imaging (GSI) combined with an 80 mm wide-body detector in head-neck CTA.

Ninety patients with head-neck CTA were prospectively selected and randomly divided into a control group and a test group, with 45 patients in each group. The control group was scanned conventionally. With a tube voltage of 100 kVp and detector width of 40 mm, a 70 ml contrast agent was injected at a flow rate of 5.0 ml/s. The test group used GSI. With a tube current fixed of 445 mAs and a detector width of 80 mm, the contrast agent was injected at a flow rate of 3.5 ml/s and 0.6 ml/kg body weight, and the 55 keV virtual monoenergetic images (VMIs) were automatically reconstructed. Finally, the target vessel CT values, background noise (BN), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), subjective scores, contrast agent dose, CT dose index volume (CTDIvol), and dose length product (DLP) were recorded. The DLP was converted to the effective dose (ED).

The target vessel CT values, BN, SNR, CNR, and subjective scores of the two groups were not statistically significant (all P > 0.05), and the image quality of both groups was the same and met the diagnostic requirements. The contrast agent dose and effective dose (ED) in the test group were approximately 44% and 26% lower than that of the control group, respectively (all P < 0.05).

In head-neck CTA examination, the Revolution CT GSI combined with an 80 mm wide-body detector can reduce the contrast agent dose and radiation dose while ensuring image quality.

Hip dysplasia is one of the most prevalent disorders in children and one of the three primary congenital orthopedic deformities. Although there are numerous existing methods (e.g., CT, MRI and arthrography) for early identification of hip dysplasia, their diagnostic criteria differ widely. It is critical to establish a safe, accurate, and reliable way for early diagnosis and treatment of hip dysplasia.

This study aimed to analyze the diagnostic efficacy of high-frequency ultrasound (HFU) for congenital developmental hip dysplasia and hip dislocation and to provide a reference for the early diagnosis of congenital hip dysplasia in the future.

A total of 104 infants and children suspected of having congenital hip dislocation or developmental hip dysplasia admitted to our hospital from April 2019 to August 2022 were enrolled as study subjects. All the infants and children were subjected to HFU and X-ray examination in our hospital. The diagnostic efficacy of HFU for congenital hip dysplasia was observed using X-ray as the gold standard.

HFU confirmed 79 cases of congenital hip dysplasia, while X-ray confirmed 71 cases. The sensitivity and specificity of HFU were 77.42% and 83.33%, respectively, in the diagnosis of congenital developmental hip dysplasia, 76.47% and 96.55% in the diagnosis of congenital hip dislocation, and 77.22% and 60% in the diagnosis of congenital hip abnormality, which is very close to the gold standard. According to statistics on infants and children, the majority of patients were girls, and the left joint was more likely to be affected.

HFU has excellent diagnostic efficiency for congenital developmental hip dysplasia and hip dislocation, which can be considered an early assessment method for congenital hip dysplasia in the future.

Non-invasive imaging methods are still lacking for the evaluation of muscle changes in diabetes.

To investigate the feasibility of muscle CT radiomics in evaluating muscle changes in diabetes.

60 diabetics and 60 health controls (HC) were assessed with the method of muscle CT radiomics. 93 CT images of radiomics features of the pectoralis major muscle (PMM) were obtained by using the software 3D Slicer and were then compared between diabetics and HC cases. The least absolute shrinkage and selection operator (LASSO) regression method was used to establish a prediction model. The receiver operating characteristic (ROC) curve was used to determine the performance of the model.

Diabetics and HC cases differed in 19 radiomics features (P<0.05). By using the LASSO method, 6 features were finally selected. The AUC of the model in the discrimination of diabetics and HC were 0.92 and 0.90, respectively, for the training cohort and validation cohort.

Muscle CT radiomics is feasible in evaluating muscle changes in diabetes.

The degree of cervical foraminal stenosis on MRI scans may be measured and categorised using the Kim or modified Kim methods. These grading scales have not previously been validated in a cohort of patients awaiting surgery.

To establish the normal foraminal and root diameters as well as the consistency of inter and intra-rater grading using the Kim and modified Kim grading systems in pre-operative surgical patients.

Asymptomatic cervical nerve roots and foramina demonstrated on the pre-operative MRI scans of adult surgical patients with cervical radiculopathy were measured and categorised by six raters using the Kim and modified Kim grading methods. Repeat “second pass” measurements were made by the same assessors on the same images a minimum of one month later.

Foraminal diameters (mm) in asymptomatic foramina were C2/C3 (mean ± SD): 4.18 ± 1.44, C3/C4 2.96 ± 1.23, C4/C5 3.02 ± 1.19, C5/C6 3.15 ± 1.33, C6/C7 3.53 ± 1.36, C7/T1 3.93 ± 1.34. Nerve root diameters were C3 3.11 ± 0.87, C4 2.95 ± 0.77, C5 2.56 ± 0.73, C6 2.26 ± 0.76, C7 2.56 ± 0.82, C8 3.83 ± 0.86.

Inter-rater consistency was kappa [95% CI]: Kim 0.01 [0.00, 0.03], modified Kim 0.08 [0.05, 0.10]. Intra-rater consistency was kappa [95% CI]: Kim 0.81 [0.77, 0.86], modified Kim 0.69 [0.62, 0.76].

There was poor inter-rater consistency but good intra-rater consistency when assessing the severity of foraminal stenosis on axial T2 MRI scans. Foraminal diameter was narrowest at C3/C4 and C4/C5, whereas the smallest root diameter was C5/C6. Volumetric or oblique MR may improve consistency.

Generalized cystic lymphangiomatosis (GCL) is a rare disease characterized by the widespread proliferation of lymphatic vessels, often seen in the pediatric patient group. Imaging techniques are instrumental in revealing the extent and morphological features of the disease.

The objective of this study is to interpret the radiological findings of GCL and address the differential diagnosis between GCL and other lymphatic malformations in light of the relevant literature data.

The sample of this retrospective study consisted of six pediatric patients, four males and two females, diagnosed with GCL based on clinical, radiological, and histopathological findings between 2015 and 2022. The age of the patients at the time of diagnosis and their symptoms at admission were obtained from the hospital database. Radiological imaging findings were evaluated in detail based on the involved systems (thorax, abdomen, and musculoskeletal).

The median age of the sample, 4/6 were male, was 9 years at admission (min. 3, max. 12). The most common symptom at admission was dyspnea, often accompanied by pleural effusion. Bone involvement was the most common extrathoracic finding. Abdominal involvement was primarily asymptomatic, and the spleen was the most frequently involved organ in the abdomen.

The diagnosis of GCL is challenging because of its rarity and overlapping diseases. Whole-body magnetic resonance imaging is a valuable tool as it reveals the typical radiological features of GCL and how far it has spread throughout the body.

Real-time shear wave elastography (SWE) has emerged as a useful imaging modality for detecting the lesion location of various diseases, including cervical diseases.

In this paper, the SWE was used to quantitatively determine the tissue hardness of the internal and external orifice of the cervix (IOC & EOC) and to relatively objectively analyze the impact of different production methods on the hardness of the cervical tissue.

A total of 48 patients were selected, and they were divided into three groups according to different production methods: control group (16 cases), cesarean section group (16 cases), and spontaneous delivery group (16 cases). Artificial intelligence has also been incorporated into this work. A deep flexible neural tree model and a new set of FNT models were proposed to assist in classifying cervical physical data in different states. The physical data was extracted as the features, and the different states were considered as category labels.

There was no statistically significant difference in the elasticity of the IOC and the EOC between the groups. However, the difference in the elasticity of the IOC and the EOC within each group was statistically significant. The classification results corresponded with the results of the statistical analysis. The hardness of the EOC is generally lower than that of the IOC, and there was no significant difference in hardness between the IOC and the EOC in the three groups.

There is no significant difference in the cervical elasticity hardness between different delivery modes.

Cesarean scar pregnancy (CSP) refers to the phenomenon in which a fertilized egg implants and develops in the scar of the uterus in a woman with a history of cesarean section.

The study aimed to explore the differential diagnostic value of two-dimensional ultrasound (2D US) combined with three-dimensional ultrasound (3D US) for CSP.

Clinical data of 89 patients with CSP admitted to our hospital from January 2022 to January 2023 were retrospectively analyzed. Of them, 65 patients met the inclusion criteria. Patients underwent 2D US, 3D US, and combined 2D and 3D US imaging. Using the clinical pathological diagnosis as the “gold standard”, the differential diagnostic value of 2D US, 3D US, and 2D US combined with 3D US for CSP was compared.

The detection rate of CSP using a combined 2D US and 3D US was 98.46%, which was higher than 84.62% and 89.23% achieved with 2D US and 3D US alone, respectively (P<0.05). The pathological results showed that among 65 patients, CSP type I accounted for 24.62%, type II accounted for 55.38%, and type III accounted for 20.00%. The coincidence rate of 2D US combined with 3D US was 98.46%, which was higher than that of 2D US (83.08%) and 3D US 89.23%) alone (P<0.05). The accuracy, specificity, and sensitivity of 2D US combined with 3D US in diagnosing CSP were higher compared to the two methods alone (P<0.05).

The combination of 2D US and 3D US can accurately detect and classify CSP, further improving diagnostic efficiency.

Fetal small bowel obstruction (SBO) is a serious condition with high morbidity and mortality rates. Prenatal ultrasound is an important tool for detecting SBO, but the optimal cutoff value for intestinal diameter remains undefined.

This study aimed to investigate the ultrasonic characteristics of fetal SBO and determine the optimal cutoff value for intestinal diameter to enhance prenatal ultrasound diagnosis.

We retrospectively analyzed the ultrasonic characteristics and postpartum data of 76 cases diagnosed with SBO. Receiver operating characteristic (ROC) curve analysis was performed to identify the optimal cutoff value for dilated intestinal diameter.

Among the 76 cases, 31 displayed the “double bubble sign” on ultrasound, with 20 cases identified as annular pancreas, 6 as duodenal atresia, and 5 as duodenal membranous stenosis. In 45 cases, the lesions were located in the jejunal or ileal segment and exhibited intestinal dilatation above the lesion site, including 27 cases of small bowel atresia, 7 cases of membranous jejunal stenosis, and 11 cases of small bowel volvulus. Out of the 76 cases, 9 showed no abnormalities after birth. ROC curve analysis determined optimal cutoff values of 17.5mm and 10.5mm for predicting “double bubble sign” lesions in the gastric and duodenal widths. For predicting small intestinal dilatation, the optimal cutoff values for dilated width and length of the intestinal tube were 11.5mm and 21.5mm, respectively, with high sensitivity and specificity.

Ultrasonic imaging and changes in intestinal diameter provide valuable information for prenatal diagnosis and management of SBO. Establishing these cutoff values can improve the accuracy of prenatal ultrasound diagnosis for SBO.

Preoperative T-staging is essential for planning optimal treatment and care for colorectal cancer (CRC).

To evaluate the accuracy of Dual-energy CT (DECT) in preoperative T-staging of CRC.

The clinical data and DECT images of 37 patients with 39 CRC lesions were retrospectively analyzed. The performance of the DECT quantitative parameters in CRC T-staging was evaluated. Postoperative pathologic results were used as a gold standard. Receiver operating characteristic curves were used to assess the diagnostic efficacy of DECT parameters. P < 0.05 was deemed significant.

The overall accuracy of T-staging by DECT was 76.9%. The DECT parameters were significantly different between the T3 pericolic fat stranding, T4a pericolic fat stranding, and normal pericolic fat stranding. Arterial phase λHU had the best diagnostic performance with a cut-off value of ≥0.967, resulting in a 70.6% sensitivity and a 100% specificity in differentiating between T3 and T4a stages of CRC.

DECT has high accuracy in the T-staging of CRC. Arterial phase λHU has the best diagnostic performance in differentiating between T3 and T4a stages of CRC.

Molybdenum cofactor deficiency (MoCD-A) is an extremely rare autosomal recessive disease that presents with intractable seizures. The diagnosis poses challenges due to the limited number of cases reported worldwide. Magnetic resonance imaging (MRI) is a useful diagnostic tool that can detect brain injury associated with the disorder. The prognosis of MoCD-A is poor partly because most cases are initially misdiagnosed as HIE (hypoxic ischemic encephalopathy), emphasizing the need for an early and accurate diagnosis to improve quality of life and provide adequate genetic counseling to avoid new cases in the future.

This report presents a case of molybdenum cofactor deficiency type A (MoCD-A) caused by MOCS1 gene mutations. A male newborn was admitted on the 10th day of birth due to uncontrolled seizures and feeding difficulties. Brain MRI showed severe cerebral damage with multiple foci that did not enhance upon contrast administration. The diagnosis was confirmed by genetic analysis and the patient received rehabilitation. His parents also received genetic counseling. To the best of our knowledge, this is the first reported MoCD-A case that had enhanced MR imaging with Gd-DTPA (0.1 mmol/kg). In addition, we reviewed the clinical and neuroimaging features of 25 newborns diagnosed with MoCD-A, as documented in the existing literature.

MRI is crucial in the diagnosis of MoCD-A. A correct diagnosis can provide the family with timely genetic counseling to prevent future cases.

Dissection of the lymph nodes posterior to the right recurrent laryngeal nerve (LN-prRLNs) in papillary thyroid cancer (PTC) remains controversial.

This study aimed to determine the capability of ultrasonography (US)-based radiomics for presurgical prediction of metastasis in LN-prRLNs in PTC.

Patients were retrospectively enrolled and pathologically confirmed as LN-prRLN metastasis with PTC after surgery. Radiomic analysis based on preoperative US images with manual segmentation of targets was used to develop a radiomics model. US features described in ACR TI-RADS were collected to construct a clinical model. The Radiomics model, a combined model integrating radiomics and clinical model, were also developed for the presurgical prediction of metastasis in LN-prRLNs.

A total of 570 patients, including 488 patients with non-LN-prRLN metastasis and 82 with LN-prRLN metastasis, were assessed. The 15 top-performing features finally remained significant for constructing the radiomics model. The combined model showed that US measured tumor size (OR: 1.036, P = 0.044), US suspected lateral lymph node metastasis (OR: 2.247, P = 0.009), multifocality (OR: 1.920, P = 0.021), Delphian lymph node metastasis (DLNM) (OR: 2.300, P = 0.039), VIa compartment metastasis (OR: 5.357, P = 0.000), the radiomics score (OR: 1.003, P = 0.001) were significant risk factors for predicting LN-prRLN metastasis. The combined model achieved a higher AUC of 0.849 than that of the clinical model (AUC: 0.826) and radiomics model (AUC: 0.759).

The US-based radiomics combined model can more effectively predict LN-prRLN metastasis in PTCs patients preoperatively. This approach had the potential to assist surgeons in decision-making regarding LN-prRLN dissection.

Only a small number of the investigations that were carried out in the Middle East attempted to characterize patients with NCFB. In order to characterize patients with NCFB, as well as their etiologies, microbiological profiles, and outcomes, we therefore carried out this investigation.

This retrospective cohort study was carried out at the Jordan University Hospital (JUH), a tertiary facility located in Amman, Jordan. Non-cystic Fibrosis Bronchiectasis (NCFB) was defined as an HRCT scan typical for bronchiectasis along with a negative sweat chloride test to rule out cystic fibrosis. Patients’ data were collected by the use of Electronic Medical Records (EMR) at our institution. Frequent exacerbation was defined as more than 2 exacerbations in 1 year of the onset of the diagnosis.

A total of 79 patients were included, and 54.4% of them were female. The mean and standard deviation of the patient's age was 48.61 ± 19.62. The etiologies of bronchiectasis were evident in 79.7% of the sample. Asthma, Chronic Obstructive Pulmonary Diseases (COPD), and Kartagener syndrome were the most prevalent etiologies, accounting for related illnesses in 21.8%, 21.5%, and 13.9% of the patients, respectively. The most frequent bacteria cultured in our cohort were Pseudomonas and Candida Species. Moreover, 43 patients of the study cohort were frequent exacerbators, and 5 patients died.

Our study supports the need to identify several bronchiectasis phenotypes linked to various causes. These findings provide information to clinicians for the early detection and treatment of bronchiectasis in Jordan.

Acquired immune deficiency syndrome (AIDS) associated with eosinophilic gastroenteritis is rare. We report a case of duodenal “stone” inducing acute pancreatitis with eosinophilic gastroduodenitis in an AIDS patient.

A 73-year-old female AIDS patient came to the hospital with recurrent abdominal pain for 20 days. Computed tomography (CT) showed pancreatitis with exudation and a high-density shadow under the gastric antrum. Gastroscopy showed that the descending part of the duodenum was blocked by a “stone”. The mucosa of the duodenum was rough, and a red polyp was found on the gastric body. The pathology result was chronic inflammation with eosinophilic granulocytes in the duodenal mucosa and gastric body polyp.

When AIDS patients suffer acute pancreatitis, the possibility of eosinophilic gastroenteritis needs to be considered to enable the patient to accept timely treatment.

Artificial intelligence-based aided diagnostic systems for pulmonary nodules can be divided into subtasks such as nodule detection, segmentation, and benign and malignant differentiation. Most current studies are limited to single-target tasks. However, aided diagnosis aims to distinguish benign from malignant pulmonary nodules, which requires the fusion of multiple-scale features and comprehensive discrimination based on the results of multiple learning tasks.

This study focuses on the aspects of model design, network structure, and constraints and proposes a novel model that integrates the learning tasks of pulmonary nodule detection, segmentation, and classification under weakly supervised conditions.

The main innovations include the following three aspects: (1) a two-dimensional sequence detection model based on a ConvLSTM (Convolutional Long Short-Term Memory) network and U-shaped structure network is proposed to obtain the context space features of image slices fully; (2) a differential diagnosis of benign and malignant pulmonary nodules based on multitask learning is proposed, which uses the annotated data of different types of tasks to mine the potential common features among tasks; and (3) an optimization strategy incorporating prior knowledge of computed tomography images and dynamic weight adjustment of multiple tasks is proposed to ensure that each task can efficiently complete training and learning.

Experiments on the LIDC-IDRI and LUNA16 datasets showed that our proposed method achieved a final competition performance metric score of 87.80% for nodule detection and a Dice similarity coefficient score of 83.95% for pulmonary nodule segmentation.

The cross-validation results of the LIDC-IDRI and LUNA16 datasets show that our model achieved 87.80% of the final competition performance metric score for nodule detection and 83.95% of the DSC score for pulmonary nodule segmentation, representing the optimal result for that dataset.

This study aimed to determine the utility of a radiomic nomogram combined with clinical imaging and radiomic features based on MRI for the diagnosis of triple-negative breast cancer.

Multi-parametric MRI images of 136 breast cancer patients were retrospectively analyzed, 95 cases were stratified into the training cohort, and 41 cases were selected for the test group. According to the pathological molecular typing, the patients were divided into 23 cases of triple-negative breast cancer and 113 cases of non-triple-negative breast cancer. ITK software was used to manually delineate the lesion volume region of interest (VOI), and the Pyradiomics package was used to extract radiomic features for screening and model building. The platform was then used to analyze the clinical and imaging risk factors of breast cancer to build a characteristic model separately. Finally, a radiomic nomogram was constructed by integrating the radiomic and independent clinical image features. The diagnostic performance of the model was assessed using ROC curves.

Univariate and multivariate analyses showed that the menstrual cycle, glandular density, and skin thickening were risk factors for clinical imaging characteristics of triple-negative breast cancer. The Area Under the Curve (AUC) was 0.839 and 0.826 for univariate and multivariate analysis, respectively. After screening, 11 radiomic features participated in the calculation of the radiomic score, and its AUC in the test set was 0.803. Combining it further with clinical models, the AUC improved to 0.899.

The radiomic nomogram developed in this study has great value in the diagnosis of triple-negative breast cancer.

Osteonecrosis of the femoral head (ONFH) is an incapacitating disease that frequently results in the collapse of the femoral head and secondary osteoarthritis. The diagnosis and staging of this pathology, which usually rely on imaging studies, are challenging. Currently, conventional radiography is the basis of the initial diagnostic assessment. In recent decades, however, radiographs have been considered insensitive to early changes in ONFH and thus, a suboptimal diagnostic tool. Paradoxically, the imaging features of radiographs are often profuse, substantial, and characteristic. This study aimed to elucidate the real limitations of this radiologic tool by assessing the diagnostic reliability of the key radiologic features and staging.

This was a retrospective study in which radiographs from 28 idiopathic ONFH confirmed cases who underwent hip arthroplasty were analyzed by eight observers who were asked to identify the presence or absence of ONFH universally reported imaging features in AP hip radiographs.

Concordance analysis revealed a poor agreement between observers for most of the assessed imaging features. Only the identification of femoral head flattening and osteoarthritis signs exhibited moderate agreement with statistical significance. In contrast, the detection of radiological osteoporosis and the loss of trabeculation showed the lowest reliability, with negative kappa coefficients.

There is a lack of agreement between qualified observers, even for the identification of the most characteristic ONFH radiographic features. The reliability of plain radiography for the detection of basic radiological elements is even weaker in the early stages of the disease.

Vitrectomy combined with internal limiting membrane (ILM) peeling or ILM inverted flap greatly improves hole closure and vision prognosis for idiopathic macular holes (IMH). The application of indocyanine green (ICG) in MH surgery increases the visibility of ILM and the safety of surgery. However, the area of ILM peeling and the state of the flap and a closed hole has not been well observed.

Fundus autofluorescence at 7935nm can show the range of ILM peeling and the state of the hole site and ILM flap by monitoring residual ICG postoperatively. However, the characteristics of fundus autofluorescence especially the site of the closed hole, and its relationship with vision prognosis have not been explored. The aim of this project was to find the autofluorescence features of the closed hole and their relation with vision.

To investigate the characteristics of fundus autofluorescence imaging after ICG-assisted vitrectomy for IMH and to evaluate the correlations of fluorescence patterns at the MH site with visual acuity and macular anatomic outcomes.

We retrospectively evaluated 33 IMH patients (33 eyes) who underwent a 25G pars plana vitrectomy (follow-up, 6-14.5 months). ICG staining (2.5 mg/mL) was either used to remove the internal limiting membrane (ILM) or the inverted ILM flap was overlaid on the hole. After surgery, fluorescence imaging of the fundus was obtained using a scanning laser ophthalmoscope at 795 nm.

On fluorescence imaging, the area of ILM peeling in all eyes showed hypofluorescence with no changes over time. The inverted ILM flap (performed in 18 eyes) was positioned on the inferior retina and exhibited early mild hyperfluorescence with blurred edges. This was gradually enhanced up to 3-6 months postoperatively and was then attenuated. MHs showed two distinct patterns on optical coherence tomography: granular (21 eyes) and patchy hyperfluorescence (12 eyes). Best-corrected visual acuity improved postoperatively in all cases (p<0.001, Z=-4.744). VA was worse in the patchy (vs. granular) hyperfluorescence cases (p=0.011, Z=-2.548).

The status of the ILM peeling area, ILM flap, and closed MH can be clearly observed using autofluorescence imaging at 795 nm. Fluorescence may be due to ICG staining of the ILM and accumulation in retinal pigment epithelium cells during ICG-assisted surgery. Granular hyperfluorescence at the MH site may indicate good anatomic and visual prognoses.

A number of studies have evaluated the effect of colour Doppler ultrasound in patients with cervical cancer.

Objective: This study aims to evaluate the efficacy of colour Doppler ultrasound and two-dimensional ultrasound of monitoring patients with cervical cancer.

Colour Doppler ultrasound (Experimental group) and two-dimensional ultrasound (Control group) are used to monitor cervical cancer and assess the treatment effects. PFS, CI, HR, DCR, ORR, PR, SD, PD, ROD, sensitivity, and specificity, accuracy between the two groups were collected and analyzed.

A total of 50 patients are included in this study, and the results show that PFS (Experimental group (EG) 5.8±2.2 versus Control group (CG) 6.1±2.6), CI (EG 20% versus CG 16%), HR (EG0.31±0.18 versus CG 0.36±0.21), DCR (EG 80% versus CG 84%), ORR(EG 28% versus CG 36%), PR (EG 16% versus CG 20%), SD (EG 48% versus CG 56%), PD (EG 12% versus CG 16%) (EG 12% versus CG 16%), ROD(EG 44% versus CG 52%) between the two groups are >0.05, and the values of sensitivity (EG 75.6% versus CG 40.2%), specificity (EG 78.4% versus CG 43.3%), and accuracy(EG 80.5% versus CG 41.4%) between the two groups are<0.05.

Both Colour Doppler ultrasound and two-dimensional ultrasound are effective methods to evaluate the efficacy of concurrent chemo-radiotherapy in patients with cervical cancer.

Wire localisation techniques are used widely for precision surgery in many specialities. This convenient technique has not yet become mainstream in the field of head and neck surgery. With limited space and many vital structures coursing through the head and neck region, pathological nodes that are difficult to palpate can be a challenge for clinicians.

A patient with a history of papillary thyroid cancer treated with surgery and radioactive iodine had a single pathological node detected on ultrasound surveillance. An isolated recurrence of papillary thyroid carcinoma was confirmed. An excisional biopsy was performed using ultrasound wire guidance to successfully remove the diseased node with minimal morbidity.

Wire-guided lymph node excision biopsy is a safe and effective method that can be applied to multiple pathologies. As of yet, it is not routine practice to employ this technique. Larger studies would increase the generalisability and safety profile of this technique in the head and neck region.

The current article presents a clinical case of ultrasound controlled transthoracic tru-cut needle biopsy of a small metastatic lesion in the left lung, performed with contrast-enhanced ultrasonography (CEUS). The following case demonstrates a real-time interventional manipulation of a very small lesion, which was done under local anesthesia, with a minimal invasion to the patient.

A 72-year-old woman is presented, hospitalized for a left-sided pleural effusion with bilateral, multiple nodulеs of different sizes in the lungs. Thoracentesis revealed data for atypical cells in the pleural fluid. The CT scan suspected a probable neoplastic process, but the subsequently performed fiberbronchoscopy couldn’t prove the existence of the same. The final diagnosis was established after ultrasound controlled transthoracic tru-cut needle biopsy of a pulmonary lesion with the application of a contrast medium.

The CEUS allows precise detection of the metastatic area because of its unique perfusion characteristics and ability to remain hypocontrasted after the application of the contrast medium sulfur hexafluoride. The persistence of a concomitant left-sided pleural effusion is used as an ultrasound window during the performance of the manipulation, with the successful verification of the pathology as primary pulmonary adenocarcinoma. By the application of this minimally invasive manipulation, an accurate final histological result was obtained.

Chronic liver disease (CLD) will affect the enhancement of hepatic parenchyma and portal vein on abdominal-enhanced MRI.

To investigate the difference in liver parenchyma and portal vein enhancement in patients with CLD of different liver function grades between Gd-EOB-DTPA and Gd-DPTA in the portal venous phase (PVP).

This retrospective study included 218 patients with CLD who had undergone abdominal enhanced MRI from January 2019 to June 2020. Patients with various degrees of liver dysfunction were identified with Child-Turcotte-Pugh and albumin-bilirubin grade. Two readers measured the precontrast and PVP signal intensities of liver parenchyma, portal vein, spleen, and psoas muscle. Relative liver enhancement, liver-to-spleen contrast index, portal vein image contrast, and portal vein-to-liver contrast were calculated.

The relative enhancement of liver parenchyma was significantly lower for the Gd-EOB-DTPA group in any degree of liver function than the Gd-DTPA group in the PVP. The Gd-EOB-DTPA group showed significantly lower portal vein-to-liver contrast in the overall study population, CTP class B, and ALBI grade 2 patients compared to the group of Gd-DTPA at PVP. No significant difference was noted in the portal vein image contrast between the two contrast agents, regardless of CTP and ALBI grading.

In CLD patients, Gd-EOB-DTPA yielded lower liver parenchymal enhancement and similar portal vein image contrast compared to Gd-DTPA in the PVP. Portal vein-to-liver contrast in the Gd-EOB-DTPA group was lower in the CTP class B and ALBI grade 2 subgroups compared to the Gd-DTPA group.

Lung cancer is a pervasive and persistent issue worldwide, with the highest morbidity and mortality among all cancers for many years. In the medical field, computer tomography (CT) images of the lungs are currently recognized as the best way to help doctors detect lung nodules and thus diagnose lung cancer. U-Net is a deep learning network with an encoder-decoder structure, which is extensively employed for medical image segmentation and has derived many improved versions. However, these advancements do not utilize various feature information from all scales, and there is still room for future enhancement.

In this study, we proposed a new model called Blend U-Net, which incorporates nested structures, redesigned long and short skip connections, and deep supervisions. The nested structures and the long and short skip connections combined characteristic information of different levels from feature maps in all scales, while the deep supervision learning hierarchical representations from all-scale concatenated feature maps. Additionally, we employed a mixed loss function to obtain more accurate results.

We evaluated the performance of the Blend U-Net against other architectures on the publicly available Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset. Moreover, the accuracy of the segmentation was verified by using the dice coefficient. Blend U-Net with a boost of 0.83 points produced the best outcome in a number of baselines.

Based on the results, our method achieves superior performance in terms of dice coefficient compared to other methods and demonstrates greater proficiency in segmenting lung nodules of varying sizes.

Portal vein size and hemodynamics can be altered in patients with portal hypertension. Elastography for liver stiffness has been proposed as a potential predictor of portal hypertension. However, the relationship between liver stiffness measured using point shear wave elastography (pSWE) and portal vein diameter and Doppler parameters remains unclear. Therefore, this observational study aimed to investigate the correlation between liver ultrasound pSWE and portal vein hemodynamics in healthy participants.

Twenty-five healthy men with no underlying medical conditions and who were not on regular medications were enrolled in the study. Liver stiffness, portal vein diameter, and Doppler parameters were measured using ultrasound EPIQ Elite with a curved-array transducer (C5-1 MHz) equipped with pSWE and Doppler imaging. Real-time pSWE measurements were taken from the liver. Portal vein diameter and Doppler parameters were measured in a longitudinal view of the extra-hepatic segment. Spearman correlation was used to assess the association between liver pSWE and portal vein diameter as well as Doppler parameters, with a significance level set at < 0.05.

There was no significant correlation between liver stiffness and portal vein diameter (p = 0.67) or Doppler parameters, including peak systolic velocity (p = 0.89), end-diastolic velocity (p = 0.65), and resistive index (p = 0.86).

Our findings suggest no direct correlation between liver stiffness measured using pSWE and portal vein hemodynamics in healthy adults. Further studies are warranted to investigate the relationship between liver pSWE and the hemodynamics of portal veins in patients with liver diseases.

Generalized distal radius die-punch fractures (GDP) can involve three columns. However, there is no three-column classification for GDP. The aim of this study was to introduce a three-column classification for GDP, and to investigate the application effect of the classification.

613 patients with GDP accrued from January 2013 to December 2021 were classified by column and fracture type based on imaging findings. First, the GDP was categorized into single-, double-, or three-column fractures. Second, the intermediate column fractures were divided into volar, dorsal, split, collapse, or mixed types; the radial column fractures were divided into metaphyseal, articular or mixed types; and the ulnar column fractures were divided into apical or basal types of the styloid process. The intra- and inter-observer consistency between the two assessors was analyzed with kappa statistics. 227 patients with less fracture displacement were treated conservatively, whereas 386 patients with increased fracture displacement were treated surgically, and the selection of surgical approaches and fracture reduction-fixation methods was guided by the classification. The differences in incidence, gender, age, treatment methods, and functional recovery were compared among the three categories, and the characteristics of different types were observed. The wrist joint function was evaluated according to the Sarmiento-modified Gartland-Werley method.

The intra- and the inter-observer kappa coefficients were obtained as ≥ 0.810. There were significant differences in the incidence (12.7%, 68.5%, and 18.8%, respectively) and age (39.8, 46.6, and 47.1 years, respectively) for single-, double- and three-column fractures (P<0.05). However, there was no significant difference in terms of gender among the three (P>0.05). The mixed, collapse, split, dorsal, and volar types accounted for 28.7%, 27.7%, 21.9%, 15.5%, and 4.5%, respectively. The metaphyseal, articular surface, and mixed types accounted for 35.9%, 33.1%, and 31.0%, respectively. The apical and base types were 81.7% and 18.3%, respectively. Among the cases of volar and dorsal types, the missed diagnosis rate of X-ray alone was 28.5%, but it was confirmed by subsequent CT. In the last follow-up of 12.2 months (range, 6 to 24 months), the excellent plus good rate was 82.7% and 82.6%, respectively, in total and among patients undergoing surgical treatment; the excellent plus good rate of the single column fractures was 96.2%, significantly higher than that of double- and three-column fractures (80.0% and 83.5%, respectively) (P<0.05). All patients with fair or poor wrist function had collapse or mixed-type intermediate column fractures.

Different categories/types of GDP have significant differences in terms of incidence, age, efficacy, and prognosis. Imaging classification by column and type of GDP better reflects the features and injury mechanism of the fractures with good consistency. Therefore, it has important reference value for the surgical modality and prognosis evaluation.

Currently, three-dimensional cephalometry measurements are mainly based on cone beam computed tomography (CBCT), which has limitations of ionizing radiation, lack of soft tissue information, and lack of standardization of median sagittal plane establishment.

This study investigated magnetic resonance imaging (MRI)-only based 3D cephalometry measurement based on the integrated and modular characteristics of the human head.

Double U-Net CycleGAN was used for CT image synthesis from MRI. This method enabled the synthesis of a CT-like image from MRI and measurements were made using 3D slicer registration and fusion.

A protocol for generating and optimizing MRI-based synthetic CT was described and found to meet the precision requirements of 3D head measurement using MRI midline positioning methods reported in neuroscience to establish the median sagittal plane. An MRI-only reference frame and coordinate system were established enabling an MRI-only cephalometric analysis protocol that combined the dual advantages of soft and hard tissue display. The protocol was devised using data from a single volunteer and validation data from a larger sample remains to be collected.

The reported method provided a new protocol for MRI-only cephalometric analysis of craniofacial growth and development, malformation occurrence, treatment planning, and outcomes.

Breast cancer, one of the most prevalent malignant tumors in females, usually occurs in the breast epithelial tissues.

The study aimed to explore the diagnostic value of contrast-enhanced ultrasound (CEUS) combined with shear wave elastography (SWE) in the diagnosis of benign and malignant breast masses in BI-RADS (Breast Imaging Reporting and Data System) 4.

Examination outcomes and clinical information of 83 patients with BI-RADS 4 breast masses were analyzed retrospectively. These included patients who received CEUS, SWE, and pathological examinations. The difference of CEUS in determining the classification of BI-RADS 4 breast masses was evaluated using histopathological outcomes of breast masses as a reference standard. The diagnostic value of CEUS, SWE, and CEUS combined with SWE in the diagnosis of benign and malignant breast masses in BI-RADS 4 was also explored.

Pathological biopsy results revealed 63 malignant masses and 20 benign masses among 83 BI-RADS 4 breast masses, with a 75.9% incidence of malignant masses. After the diagnosis of BI-RADS 4 breast masses with CEUS, SWE, and CEUS+SWE, the incidence of malignancy was 56.6%, 78.3%, and 73.5%, respectively. CEUS+SWE showed higher sensitivity (93.7% vs. 81% and 68.3%), specificity (90% vs. 30% and 80%), positive predictive value (96.7% vs. 78.5% and 91.5%), negative predictive value (81.8% vs. 33.3% and 44.4%), and diagnostic coincidence rate (92.8% vs. 68.7% and 71.1%) than SWE and CEUS alone in diagnosing pathological type of breast masses. Moreover, CEUS combined with SWE exhibited a larger area under the receiver operating characteristic (ROC) curve (0.918) than SWE (0.741, p = 0.028) and CEUS (0.555, p 0.001) alone in the diagnosis of BI-RADS 4 breast masses.

Overall, the diagnostic value of CEUS+SWE for the pathological type of BI-RADS is preferred over CEUS and SWE alone. CEUS+SWE showed higher values than CEUS and SWE alone in diagnosing BI-RADS 4 breast masses. Specifically, CEUS+SWE can correctly identify benign and malignant masses, reduce unnecessary trauma, and avoid misdiagnosis. In summary, CEUS combined with SWE can serve as an effective diagnostic method and avoid delaying the best treatment opportunity for some malignant lesions.

This paper presents a novel approach for detecting abnormality in coronary arteries using MRI data in RGB images. The study evaluates the test accuracy of the weak classifiers and the test accuracy and F1 score of the strong classifier.

The method involves separating the image into information planes, including R, G, and B color space, or bit-planes, and training a VGG-like convolutional neural network model on each plane separately, referred to as a “weak classifier.” The classification results of these planes are aggregated using a proposed soft voting method, forming a “strong classifier,” with the weights for the aggregation determined by the model's performance on the training set.

The results indicate that the strong classifier achieves a test accuracy and F1 score of around 68% to 74% on our private coronary artery dataset. Moreover, by aggregating the top three highest bit-plane levels in a grayscale image, the accuracy is slightly lower than that of the three color spaces but requires a significantly smaller CNN model of nearly 4M parameters.

The potential of bit-planes in reducing model storage costs is suggested. This approach holds promise for improving the detection of abnormalities in coronary arteries using MRI data.

To investigate the radiological characteristics of the PHNENs on CT and MRI and improve the understanding of the image manifestations and preoperative diagnosis of the disease.

Primary hepatic neuroendocrine neoplasms (PHNENs) are rare diseases, and most of the relevant studies are case reports. Characterized by no specific clinical symptoms, PHNENs not only have a low preoperative diagnosis rate with great difficulty in early diagnosis but are frequently misdiagnosed as primary hepatic cancer.

15 PHNEN patients were enrolled, with 10 cases in the G2 stage and 5 cases in the G3 stage.

The imaging and clinicopathological information of 15 patients pathologically diagnosed with PHNENs was retrospectively reviewed.

The average age of the patients enrolled was 46.14±18.24 years, and the average tumor size was 91.00±61.17 mm. 13 cases showed nodules or masses, 8 cases were located in the periphery of the liver, showing capsule depression and subcapsular effusion signs. CT enhanced scan showed heterogeneous and obvious enhancement in 9 arterial-phase cases, 2 cases in arterial and portal venous phases both saw mild enhancement; the enhancement degree of lesions in the G2 stage in the arterial phase was significantly higher than in the G3 stage. Gd-EOB-DTPA dynamic enhanced MRI was conducted on 3 cases, and scattered lesions with heterogeneous and slight hyperintensity were observed in the hepatobiliary-specific lesions. Image manifestations showed diffuse lesions in 2 cases, with heterogeneous enhancement in the arterial phase and decreased enhancement in the portal venous phase by the dynamic enhanced scan.

PHNENs were the imaging characteristics of PHNENs. The CT-enhanced scanning during the arterial phase may provide a certain reference for pathological grading (G2 and G3 grades). Gd-EOB-DTPA-enhanced MRI is helpful for PHNEN diagnosis.

This study aimed to characterize and assess the diagnostic value of prenatal magnetic resonance (MR) imaging in detecting fetal cerebellar hypoplasia/dysplasia and developmental malformations.

Reports of suspected intracranial abnormalities were retrospectively collected on ultrasound screening (US), and MR images of fetuses were reviewed at our institution over a 5-year period on picture archiving and communication system (PACS) servers. Two experienced radiologists recorded major abnormalities and coexisting abnormalities at the reading of the census. The results of the MRI were compared against the US in each case.

For prenatal MR imaging, we enlisted a total of 121 patients (mean gestational week, 24.5 ± 4.7 weeks). This included 28 cases with normal findings of MR imaging, 62 cases with findings of cerebellar hypoplasia or dysplasia, and the remaining 31 cases with other abnormities findings. Cerebral malformations cases included agenesis of the corpus callosum, cerebral hemorrhage, hydrocephalus, holoprosencephaly, ventriculomegaly, and brainstem/gyri malformation. Cerebellar abnormalities included vermis absence, cerebellar tonsil hernia, Dandy-Walker malformation, Blake’s pouch cysts, arachnoid cysts, and intracranial hemorrhage. Other systemic malformation cases included tethered cord syndromes (9 cases), cleft lip and palate (1 case), club foot (1 case), and cardiac malformation (1 case). In 12 cases (24.5%), compared to the US, MR imaging proved the value of confirming the diagnosis and/or even yielded more findings on abnormalities.

Prenatal MR imaging can better visualize systemic malformations coexisting with cerebellar abnormalities. MR imaging, a complementary means to the US, can aid in prenatal counseling and treatment selection for term delivery.

The aneurysmal bone cyst is a benign neoplasm that tends to form the appearance of a mass with a bony septum that forms cavities with blood inside. It is estimated to represent 1% of bone tumours and has an incidence of 0.14 per 100,000 people worldwide. Current publications have not shown a multidisciplinary approach that can benefit patients, mainly in the functionality and quality of the management approach.

Describe the multidisciplinary approach and the benefits of quality of life and functionality in this diagnosis.

A paediatric patient was diagnosed with an aneurysmal bone cyst located in the cervical spine, which initially manifested with muscle pain, enlargement of the posterior cervical region, and difficulty in performing arcs of movement. He was treated with multidisciplinary management with surgery, embolisation, radiation, and bisphosphonate support.

The purpose of approaching multidisciplinary management helped to improve the accompanying symptoms that prevented our patient from having an active and quality life. However, more successful cases have not been reported to establish the best therapeutic protocol.