Current Medical Imaging - Volume 20, Issue 1, 2024

To verify the multiphase ratio of Computer Tomography-value between the renal cortex and renal medulla, which can be used to concisely evaluate renal function in kidney recipients.

Fifty-eight kidney recipients were retrospectively enrolled and divided into the Normal group (eGFR≥90 mL/min/1.73m²) and Abnormal group (eGFR<90 mL/min/1.73m²) according to Chronicle Kidney Disease Epidemiology Collaboration (eGFR(CKD-EPI)) and the Modular of Diet in Renal Disease (eGFR(MDRD)) formulas respectively. The multiphasic ratios between the renal cortex and medulla in the arterial phase and venous phase were noted as A(RatioC/M) and V(RatioC/M), and the difference between those two was recorded as D(RatioC/M). Correlation/regression analysis, student t-test, and ROC curves analysis were used to test the ability of multiphasic ratios to assess renal function.

Both A(RatioC/M) and V(RatioC/M) were moderately correlated with eGFR(CKD-EPI) (Y =20.41*X + 28.20, r=0.40 (95%Cl, 0.13-0.58), P<0.01; Y =-16.57*X + 109.8, r=-0.29 (95%Cl, -0.51--0.04), P=0.03) and eGFR(MDRD) (Y =23.72*X + 23.52, r=0.38 (95%Cl, 0.13-0.58), P<0.01; Y =-19.88*X + 119.5, r=-0.30 (95%Cl, -0.52--0.05), P=0.02). However, D(RatioC/M) was strongly positive correlated with eGFR(CKD-EPI) (Y = 30.95*X + 60.71, r=0.61 (95%Cl,0.42-0.75), P<0.001) and eGFR(MDRD) (Y = 36.47*X + 61.01, r=0.62 (95%Cl, 0.44-0.76), P<0.001), respectively, and both regression lines were not significant different (slope: P=0.496, intercept: P=0.378). The differences in D(RatioC/M) between the two groups were significant (all P<0.05). The ROC curve analysis provided the cutoff values of D(RatioC/M) for assessing eGFR (AUC:0.863 and AUC:0.822, all P<0.001).

The D(RatioC/M) can be used to assess renal function for kidney recipients.

The aim of this study was to investigate the feasibility of muscle CT radiomics in identifying gout.

A total of 30 gout patients and 20 non-gout cases with CT examinations of ankles were analyzed by using the methods of CT radiomics. CT radiomics features of the soleus muscle were extracted using the software of a 3D slicer, and then gout cases and non-gout cases were compared. The radiomics features that were significantly different between the two groups were then processed with machine learning methods. Receiver operating characteristic curve analysis was used to evaluate the diagnostic performance.

Five CT radiomics features were significantly different between gout cases and non-gout cases (P < 0.05). In the logic regression, the AUC, sensitivity, specificity, and accuracy were 0.738, 77% (46/60), 70% (28/40), and 74% (74/100), respectively. In the Random forest, Xgboost, and support vector machine analysis, the accuracy was 0.901, 0.833, and 0.875, respectively.

From this study, it can be concluded that muscle CT radiomics is feasible in identifying gout.

Magnetic Resonance Imaging (MRI) data acquisition includes several sequences that might be optimized to reduce the scan time.

This study aimed to investigate the impact of gadolinium chelate administration timing on scan duration and image quality in Diffusion-weighted Imaging (DWI) and T2-weighted Imaging (T2WI) during abdominal MRI examinations.

A prospective study was conducted from October 2018 to May 2020. Study participants were assigned into a conventional group, undergoing MRI with DWI and T2WI sequences pre and post-gadolinium injection, or an optimized group, receiving MRI with DWI and T2WI sequences after gadolinium injection. Quantitative image quality, measured by the Signal-to-noise Ratio (SNR), Contrast-to-noise Ratio (CNR), and Apparent Diffusion Coefficient (ADC), was analyzed. Kappa statistics were employed for the inter-observer agreement on liver lesion detection.

Our study has included 341 patients, with 168 and 173 in the conventional and optimized groups, respectively. Mean scan durations were 1,304 (±143) and 1,015 (±129) s for the conventional and optimized groups, respectively (p<0.05). For the liver, spleen, and pancreas, SNR and ADC remained statistically unchanged in post-enhanced DWI and T2WI (p>0.05). Significant decreases in the SNR and ADC of the kidney were observed in post-contrast DWI and T2WI (p<0.05). Hepatic lesion detectability did not show significant differences between pre and post-contrast DWI and T2WI images (p>0.05).

DWI and T2WI sequences assessed post-gadolinium administration exhibited shortened scan time without compromising the image quality for liver, spleen, and pancreas evaluations. However, these sequences should be examined before gadolinium administration when assessing the kidneys.

Accurately modeling respiratory motion in medical images is crucial for various applications, including radiation therapy planning. However, existing registration methods often struggle to extract local features effectively, limiting their performance.

In this paper, we aimed to propose a new framework called CvTMorph, which utilizes a Convolutional vision Transformer (CvT) and Convolutional Neural Networks (CNN) to improve local feature extraction.

CvTMorph integrates CvT and CNN to construct a hybrid model that combines the strengths of both approaches. Additionally, scaling and square layers are added to enhance the registration performance. We have evaluated the performance of CvTMorph on the 4D-Lung and DIR-Lab datasets and compared it with state-of-the-art methods to demonstrate its effectiveness.

The experimental results have demonstrated CvTMorph to outperform the existing methods in terms of accuracy and robustness for respiratory motion modeling in 4D images. The incorporation of the convolutional vision transformer has significantly improved the registration performance and enhanced the representation of local structures.

CvTMorph offers a promising solution for accurately modeling respiratory motion in 4D medical images. The hybrid model, leveraging convolutional vision transformer and convolutional neural networks, has proven effective in extracting local features and improving registration performance. The results have highlighted the potential of CvTMorph for various applications, such as radiation therapy planning, and provided a basis for further research in this field.

Patients with malignant tumors often develop bone metastases. SPECT bone scintigraphy is an effective tool for surveying bone metastases due to its high sensitivity, low-cost equipment, and radiopharmaceutical. However, the low spatial resolution of SPECT scans significantly hinders manual analysis by nuclear medicine physicians. Deep learning, a promising technique for automated image analysis, can extract hierarchal patterns from images without human intervention.

To enhance the performance of deep learning-based segmentation models, we integrate textual data from diagnostic reports with SPECT bone scans, aiming to develop an automated analysis method that outperforms purely unimodal data-driven segmentation models.

We propose a dual-path segmentation framework to extract features from bone scan images and diagnostic reports separately. In the first path, an encoder-decoder network is employed to learn hierarchical representations of features from SPECT bone scan images. In the second path, the Chinese version of the MacBERT model is utilized to develop a text encoder for extracting features from diagnostic reports. The extracted textual features are then fused with image features during the decoding stage in the first path, enhancing the overall segmentation performance.

Experimental evaluation conducted on real-world clinical data demonstrated the superior performance of the proposed segmentation model. Our model achieved a 0.0209 increase in the DSC (Dice Similarity Coefficient) score compared to the well-known U-Net model.

The proposed multimodal data-driven method effectively identifies and isolates metastasis lesions in SPECT bone scans, outperforming existing classical deep learning models. This study demonstrates the value of incorporating textual data in the deep learning-based segmentation of low-resolution SPECT bone scans.

Eosinophilic gastroenteritis (EGE) is a rare immune-mediated chronic inflammatory disorder, which is classified into 3 types according to the affected gastric wall layer. The serosal-type EGE is the least common type. Gastric oral contrast-enhanced ultrasonography (OCEUS) may show some specific changes in the serosal-type EGE. Herein, we reported OCEUS findings in a serosal-type EGE case.

A 60-year-old man with unexplained abdominal pain accompanied by diarrhea, which lasted for half a month, consulted the hospital. Laboratory findings revealed peripheral eosinophilia and elevated carbohydrate antigen 125(CA125). OCEUS showed a thickened gastric antrum wall and ascites, with distinct layers (thickening of the muscularis propria layer was most obvious), which is rare and specific. Endoscopy showed normal mucosa of the esophagus and stomach and scattered hyperemia spots in the mucoua of the duodenal bulb and small intestine. Microscopy evaluation revealed few eosinophils infiltration in the lamina propria. A large number of eosinophils were seen in peritoneal lavage fluid and the greater omentum. Eventually, the patient was diagnosed with serosal type EGE.

Significant thickening of the digestive tract walls and ascites at ultrasonography (US)-examination, with distinct layers and predominant thickening of the muscularis propria layer at OCEUS, can indicate EGE.

The automatic computer-assisted mammogram classification system is important for women patients to detect and diagnose the cancer regions. In this work, the mammogram images are classified into three cases: healthy, benign and cancer, using the proposed Resource Efficient Convolutional Neural Network (RECNN architecture).

The proposed mammogram image classification system consists of Data Augmentation (DA) module and Spatial transformation module and CNN architecture with a segmentation module. The DA methods are used to increase the mammogram image count and Spatial Gabor Transform is used as the spatial transformation module for transforming the spatial pixels into spatial-frequency pixels. Then, the proposed RECNN architecture is used to perform the classification of mammogram images into healthy, benign and cancer cases. Further, the cancer mammogram images are diagnosed as either ‘Early’ or ‘Severe’ using the proposed RECNN architecture in this work.

The proposed MCDS obtains 98.65% SeDR, 98.93% SpDR and 98.84% ADR for benign case mammogram images on DDSM dataset and also obtains 98.84% SeDR, 98.7% SpDR and 98.92% ADR for cancer case mammogram images on DDSM dataset. The proposed MCDS obtains 98.94% SeDR, 98.86% SpDR and 98.96% ADR for benign case mammogram images on MIAS dataset and also obtains 98.89% SeDR, 98.88% SpDR and 99.03% ADR for cancer case mammogram images on MIAS dataset.

This proposed method is tested on the mammogram images from DDSM and MIAS datasets and the experimental results are compared with other similar mammogram classification works in this paper. Based on several performance evaluation measures, the experimental results show that MCDS outperforms the state-of-the-art methods currently used for the diagnosis and detection of mammography cancer.

Capitellar injury (CI) includes capitellar cartilage injury (CCI) and capitellar fracture (CF). A comprehensive classification of CI concurrent with radial head fracture (RHF) that can guide surgical strategy is lacking in the literature. Therefore, this study aimed to introduce a comprehensive classification of CI concurrent with RHF and investigate its value.

A total of 35 patients with CI concurrent with RHF confirmed by surgical exploration were retrospectively analyzed, including males in 19 cases and females in 16 cases. RHF was classified according to the Mason classification, and CI was classified into six types, including 3 types of CCI and CF, each based on the site and degrees of injuries (comprehensive classification method proposed in this study). The classification results were analyzed. Two radiologists were selected to independently classify the CI, and the inter- and intra-observer agreements were analyzed with kappa statistics.

Mason Type I, II, III, and IV RHF accounted for 14.3%, 48.6%, 37.1%, and 0% of cases, respectively. Type I, II, III, IV, V, and VI CIs accounted for 22.9%, 34.3%, 25.7%, 11.4%, 2.9%, and 2.9% of cases, respectively. There was no obvious relationship between the CI and RHF types (p > 0.05). All Type I CIs underwent removal, 9 Type II CIs underwent microfracture repair, and 3 Type II CIs underwent removal. All Type III CIs underwent fixation, one Type IV CI underwent removal, and 3 Type IV CIs underwent fixation, one Type V CI underwent fixation, and one Type VI CI underwent arthroplasty. The inter- and intra-observer kappa coefficients were 0.830 ~ 0.905 and 0.805 ~ 0.892, respectively. At 12 months postoperatively, the elbow function evaluated by MEPS was 91, with an excellent and good rate of 97%.

Different types of CI differ not only in pathology but also in treatment methods. The CI comprehensive classification put forth in this paper for the first time reflects different types of pathology well, with high consistency and repeatability, and can guide the selection of surgical methods, leading to satisfactory postoperative results.

Mediastinal venous malformation (MVM) and fusiform superior vena cava aneurysm (F-SVCA) are both rare congenital vascular anomalies.

A 46-year-old male presented with acute ischemic stroke of unknown etiology. Computed tomography (CT) angiography revealed the coexistence of MVM and F-SVCA. Diagnostic venography demonstrated a significant reduction in blood flow velocity within the F-SVCA, but failed to identify a direct connection to the left heart system or pulmonary vein. The patient expired due to extensive brain damage caused by a stroke.

This case may increase the necessity of meticulous radiological evaluation and preventive management for these anomalies, as mediastinal vascular anomalies can result in thromboembolic complications.

Intrahepatic primary osteosarcoma is a rare disease with a very low incidence but a very poor prognosis. A total of 12 cases have been previously reported, and in most of these cases, intra-focal calcification was observed. This paper aims to report a case of non-calcified intrahepatic primary osteosarcoma.

We hereby report a female patient with hepatitis B for 20 years, identified during a routine examination due to a mass in the right lobe of the liver. The patient experienced no significant discomfort, and the serological tumor markers were not elevated. Surgical resection was performed after comprehensive examinations, and postoperative pathology showed primary osteosarcoma of the liver. The patient experienced recurrence and metastasis seven months postoperatively and died eight and a half months postoperatively.

Intrahepatic primary osteosarcoma is an extremely rare disease, and it currently requires a combination of clinical, radiological, and pathological findings to make a diagnosis of exclusion. Further, patients may benefit from early diagnosis, aggressive surgery, and post-operative chemotherapy.

“Pelvic rib”, “pelvic digit (finger)”, or “eleventh digit (finger)” is a rare congenital anomaly, in which a finger-like bony structure is present in the soft tissue in the pelvic or abdomen (less common) area.

This case report presents a symptomatic “pelvic digit” discovered in a patient referred to the radiology department after prolonged unilateral hip pain, especially during long walks. To our knowledge, this is the first case report of unilateral pelvic digit occurrence in our region. It is an extremely rare condition that is often discovered incidentally due to the lack of clinical symptoms.

To the best of the authors’ knowledge, this is the tenth reported case of symptomatic pelvic digit in the literature and four of them have required surgical intervention.

Chest X-ray image classification for multiple diseases is an important research direction in the field of computer vision and medical image processing. It aims to utilize advanced image processing techniques and deep learning algorithms to automatically analyze and identify X-ray images, determining whether specific pathologies or structural abnormalities exist in the images.

We present the MMPDenseNet network designed specifically for chest multi-label disease classification.

Initially, the network employs the adaptive activation function Meta-ACON to enhance feature representation. Subsequently, the network incorporates a multi-head self-attention mechanism, merging the conventional convolutional neural network with the Transformer, thereby bolstering the ability to extract both local and global features. Ultimately, the network integrates a pyramid squeeze attention module to capture spatial information and enrich the feature space.

The concluding experiment yielded an average AUC of 0.898, marking an average accuracy improvement of 0.6% over the baseline model. When compared with the original network, the experimental results highlight that MMPDenseNet considerably elevates the classification accuracy of various chest diseases.

It can be concluded that the network, thus, holds substantial value for clinical applications.

The neural mechanisms underlying Congenital Sensorineural Hearing Loss (CSNHL) remain elusive.

This study evaluated the function of the glymphatic system in children with CSNHL compared to normal-hearing children using the DTI-ALPS approach, which utilizes diffusion tensor imaging along the perivascular space.

Twenty-six children with CSNHL and 30 age- and sex-matched Healthy Controls (HCs) with normal hearing thresholds were recruited. The DTI-ALPS index was calculated for each group. We analyzed the discrepancies in the DTI-ALPS index between patients with CSNHL and healthy controls. Additionally, Spearman's correlation analysis was performed to investigate the relationship between the DTI-ALPS index and age in children with CSNHL.

Significant differences in the DTI-ALPS index were observed between the two groups. Compared with HCs, the DTI-ALPS index in CSNHL patients was significantly lower (1.49388±0.11441 vs. 1.61402±0.15430, p=0.002). In addition, diffusivity along the z-axis in the association fiber (Dzzassoc) index was significantly higher in the CSNHL group than in the HC group (0.00041±0.00006 vs. 0.00036±0.00004, p=0.003). Furthermore, we discovered a noteworthy downward correlation between the DTI-ALPS index and age in children with CSNHL (rho = -0.544, p=0.005).

In this present study, glymphatic system activity in CSNHL children was investigated for the first time using the DTI-ALPS index. A significant decrease in glymphatic system function was detected in CSNHL children, which correlated well with age. The DTI-ALPS index could serve as a valuable biomarker for tracking disease progression and treatment in CSNHL and unraveling the neural mechanisms of early hearing deprivation in children with CSNHL.

Transcatheter radiofrequency ablation is one of the main treatments for atrial fibrillation, but related complications of this surgery are uncommon.

Here, we report a 70-year-old elderly male patient with atrial fibrillation who experienced severe abdominal pain early after undergoing radiofrequency ablation; related imaging examinations suggested that the patient had intestinal edema and thickening, combined with hepatic portal vein gas accumulation. The reason was that the patient experienced intestinal necrosis due to superior mesenteric artery embolism related to radiofrequency surgery. The surgeon suggested laparotomy for exploration. However, after multidisciplinary consideration, we ultimately chose conservative treatment. After fasting, gastrointestinal decompression, spasmolysis, pain relief, somatostatin inhibition of intestinal edema, anti-infection, and anticoagulation, the patient's condition improved, and he was discharged. We followed the patient for 1 month after discharge, and there was no special discomfort.

Hepatoportal vein gas accumulation after radiofrequency ablation of atrial fibrillation is rare, and imaging findings have important guiding significance for the diagnosis and treatment of the disease.

The purpose of this study was to compare the image quality of different MRI sequences regarding the presentation of Dermatofibrosarcoma Protuberans (DFSP).

We retrospectively collected MRI images of 40 patients who had been pathologically diagnosed with DFSP, including 21 primary tumors and 19 recurrent tumors. The image quality of different MRI sequences was assessed subjectively by two radiologists, taking into account the display of the lesions, artifacts, and distortions, as well as the overall impact of the image quality.

Among the 40 cases, 22 cases involved the trunk, 14 cases involved the shoulders and limbs, 2 cases involved the head and neck, 1 case involved the breast, and 1 case involved the groin. In terms of image quality, fat suppression T2-weighted images were superior to T1-weighted images and T2-weighted images (P<0.05). The difference between fat suppression T2-weighted images and contrast-enhanced images was not significant (P>0.05). As far as lesion contrast is concerned, diffusion-weighted images, fat suppression T2-weighted images, and contrast-enhanced images did not differ significantly (P>0.05). On the DWI images, there were severe magnetic artifacts and deformations.

Fat suppression T2-weighted images and enhanced sequences produce the highest quality images, while diffusion-weighted images provide the best lesion contrast.

Osteoid osteoma (OO) is a painful benign bone tumor. Typically, it causes pain that is most noticeable during the night, which is improved by nonsteroidal anti-inflammatory drugs. In the treatment of symptomatic lesions, open surgery for nidus removal is the gold standard. However, surgical technical difficulties and morbidities vary by location. Percutaneous radiofrequency ablation (RFA) therapy guided by computed tomography (CT) is now a popular treatment option for OO. This study aims to assess our single-center experience with the technique, complications, and procedure effectiveness.

The study included fifteen patients who were treated between 2017 and 2021. A retrospective analysis was carried out on archive images and file records. The lesions' location, nidus width, and affected area (cortical, medullary) were all recorded. The procedure and technical success, as well as postoperative complications and the need for repeat ablation, were all documented.

A total of 20 patients, 18 men, and 2 women, were included in the study, and 12 of them were pediatric patients. The patients' mean age was 16.9±7.3 years old, and the mean nidus diameter was 7.1±8.7 mm. There were 13 cortical niduses, 2 intramedullary niduses, and 5 corticomedullary niduses. The lesions were in the femur (n=12), tibia (n=6), scapula (n=1), and vertebrae (n=1). Two recurrences (10%) were observed in our patients during the follow-up. Patient with a femoral OO, the pain started again 12 weeks after the procedure and we performed additional RFA. The patient with vertebral OO had fewer symptoms and full recovery was not achieved. Therefore, the vertebral OO was ablated again 4 months later, and clinical success was achieved. One patient had a minor burn at the entry site that went away on its own after a short period of time. Except for the patient who was scheduled for a repeat RFA, no recurrence has been observed so far. The primary and secondary success rates are, respectively, 90% (18/20) and 100% (20/20).

RFA has a high success rate in treating OO. The procedure failure and recurrence rates are low. There are possibilities for posttreatment pain relief, early discharge, and a quick return to daily life. For inappropriate lesion localization, the RFA process replaces surgical treatment. The procedure-related complication rate is low. On the other hand, the burn during the procedure can be a serious problem.

Prostate cancer, a significant contributor to male cancer mortality globally, demands improved diagnostic strategies. In Saudi Arabia, where the incidence is expected to double, this study assessed the compliance of multiparametric MRI (mpMRI) practices with Prostate Imaging-Reporting and Data System version 2 (PI-RADS v2) guidelines across diverse healthcare institutions.

A survey was distributed to the radiology departments of all tertiary referral hospitals in Saudi Arabia (n=60) to assess their compliance with the technical specifications outlined in PI-RADS v2. Statistical analysis included chi-square, Fisher exact, ANOVA, and Student t-tests to examine the collected data;

The study revealed an overall commendable compliance rate of 95.23%. However, significant variations were observed in technical parameters, particularly between 1.5 Tesla and 3 Tesla scanners and tertiary versus non-tertiary hospitals. Notable adherence in certain sequences contrasted with discrepancies in T2-weighted and diffusion-weighted imaging parameters;

These findings underscore the need for nuanced approaches to optimize prostate imaging protocols, considering field strength and institutional differences. The study contributes to the ongoing refinement of standardized mpMRI practices, aiming to enhance diagnostic accuracy and improve clinical outcomes in prostate cancer.

This study aimed to enhance the existing nursing model in imaging departments by implementing a characteristic seamless nursing care approach and assessing its impact on patient and medical staff satisfaction, nursing quality, examination efficiency, and patient awareness. We hypothesized that the implementation of a seamless nursing care model would be associated with higher patient satisfaction, improved nursing quality, increased examination efficiency, and better patient awareness compared to the traditional nursing model.

This prospective cohort study included 300 patients undergoing imaging examinations from January 2019 to January 2022. Subjects were divided into control and observation groups (n=150 each) based on different nursing methods. The control group received routine care, and the observation group received seamless care. The following outcome measures were assessed using validated questionnaires: patient satisfaction (measured using a 5-point Likert scale), medical staff satisfaction with patient examination cooperation (measured using a 5-point Likert scale), nursing quality compliance rate (percentage of nursing tasks performed according to established guidelines), dissatisfaction rate (percentage expressing dissatisfaction with examination cooperation), and effect evaluation [measured using a knowledge test validated in previous studies (Chung et al., 2020) with a total score range of 0-20].

Average imaging examination and nursing times were significantly lower in the observation group compared to the control group (P<0.05). The examination cooperation dissatisfaction rate was significantly lower in the observation group (P<0.05). There were significant differences in examination precautions, procedures, breathing training methods, and injection comparisons between the groups (all P<0.05).

The application of seamless nursing care may be associated with improved patient satisfaction, nursing service quality, imaging examination efficiency, and patient awareness of imaging examinations. However, further research is needed to establish causal relationships.