Current Medical Imaging - Volume 20, Issue 1, 2024

Magnetic resonance enteroclysis (MRE) has been widely applied to diagnose Crohn’s disease (CD). Magnetic resonance (MR) at 3.0 T improves signal-to-noise ratio (SNR), shortens image acquisition time, and shows more advantages.

This study aimed to retrospectively analyze the diagnostic value of 3.0 T MR imaging for active CD.

48 CD patients hospitalized in our hospital from January 2021 to December 2022 were selected as the study subjects. These 48 CD patients underwent both double-balloon enteroscopy and 3.0 T MRE. All patients' arterial phase signal, venous phase signal, bowel wall, and bowel lumen of MRE were observed to identify whether they suffered from active CD. Based on the results of enteroscopy, the number of true positives, true negatives, false negatives, and false positives diagnosed by MRE were screened; next, the diagnostic accuracy, sensitivity, and specificity of MRE in assessing active CD were calculated.

Of the 48 patients, 39 were diagnosed with small bowel CD by MRE, which was not significantly different from the results of enteroscopy (P>0.05). According to MRE diagnostic results, the arterial phase predominantly presented high signal intensity, and the venous phase mainly presented low signal intensity or isointensity. Small bowel CD lesions were primarily characterized by bowel wall thickening, rare pneumatosis enhancement of the bowel wall, bowel lumen pneumatosis or dilatation, and rare strictures. Besides, MRE presented an accuracy of 93.75%, sensitivity of 97.37%, and specificity of 80.00% in diagnosing CD.

3.0 T MR imaging has diagnostic value for active CD and shows certain clinical application value.

Hydatidosis, a distinctive parasitic ailment, exhibits a broad range of imaging characteristics influenced by the growth stage, resultant complications, and tissue involvement. Its occurrence throughout the human anatomy underscores its ubiquitous propensity. Despite its relatively infrequent manifestation as diffuse hydatosis, the disease assumes particular significance in rural regions. Given its detrimental complications and resemblance to other cystic conditions, vigilance towards the potential presence of this ailment becomes imperative.

In 2022, a 12-year-old female patient residing in a village sought medical assistance for left flank pain. During the evaluation, an incidental discovery of a pancreatic cyst through sonography prompted further investigation. Subsequent abdominopelvic computed tomography (CT) scans identified multiple lesions consistent with hydatid cysts in various anatomical locations, including the pancreas, right atrium, ventricle of the heart, pericardium, and lung. Confirmation of the hydatid cysts was obtained through pathology examination and consideration of the patient's medical history, which included a previously diagnosed brain hydatid cyst. Treatment with albendazole was initiated, and the patient underwent cardiac surgical intervention. Unfortunately, the condition of the patient deteriorated, leading to septic shock and subsequent mortality.

In areas with a high prevalence of hydatid cysts, the presence of diverse lesions on radiologic assessments, despite negative serologic tests, should raise suspicion for this condition. Furthermore, understanding the importance of timely detection and intervention is crucial, as it greatly impacts patient prognosis,. In the advanced stages of the disease, particularly when cardiac involvement occurs, surgical excision of the cysts remains the sole therapeutic approach, albeit accompanied by certain complications. Through the utilization of various imaging modalities and early recognition and treatment, the need for more complex interventions can be minimized.

The pathogenesis of breast cancer is characterized by dysregulated cell proliferation, leading to the formation of a neoplastic mass. Conventional methodologies for analyzing carcinomatous distal areas within whole-slide images (WSIs) tissue regions may lack comprehensive insights.

This study aims to introduce an innovative methodology based on convolutional neural networks (CNN), specifically employing a CNN Modified ResNet architecture for breast cancer detection. The research seeks to address the limitations of existing approaches and provide a robust solution for the comprehensive analysis of tissue regions.

The dataset utilized in this study comprises approximately 275,000 RGB image patches, each standardized at 50x50 pixels. The CNN Modified ResNet architecture is implemented, and a comparative evaluation against diverse architectures is conducted. Rigorous validation tests employing established performance metrics are carried out to assess the proposed methodology.

The proposed architecture achieves a notable 89% accuracy in breast cancer detection, surpassing alternative methods by 2%. The results signify the efficacy and superiority of the CNN Modified ResNet model in analyzing carcinomatous distal areas within WSIs tissue regions.

In conclusion, this study demonstrates the potential of the CNN Modified ResNet architecture as an effective tool for breast cancer detection. The enhanced accuracy and comprehensive analysis capabilities make it a promising approach for advancing the understanding of neoplastic masses in WSIs tissue regions. Further research and validation could solidify its role in clinical applications and diagnostic procedures.

This case report describes a case of Müllerian duct cyst that occurred in a male retroperitoneum. The cyst lesion is rare and complicated with diaphragmatic hernia. Müllerian duct-derived cyst is a rare developmental disorder that is more common in male pelvic tissues and rare in the retroperitoneum. We investigated the important role of computerized tomography (CT) and magnetic resonance imaging (MRI) in preoperative diagnosis and disease prediction of this condition.

A 25-year-old male was found to have an abnormal occupying lesion in the left diaphragm in imaging examinations, usually healthy with no obvious clinical symptoms. X-ray examination showed a circular, high-density shadow near the left diaphragm. CT scan showed a soft tissue density shadow resembling a tumor in the left adrenal area, irregularly protruding into the chest cavity, with uneven density. MRI examination showed an irregular elongated T1 and T2 signal shadow in the left adrenal area. T2 fat suppression showed high signal intensity with unrestricted diffusion. Robotic-assisted laparoscopic surgery showed left retroperitoneal tumor resection. The patient recovered well postoperatively and had no recurrence after discharge follow-up.

The preclinical symptoms of retroperitoneal Müllerian cysts complicated by diaphragmatic hernia in young men are difficult to distinguish, and it is difficult to diagnose other similar cysts with imaging. The method of combined CT and MRI diagnosis guides the endoscopic robot-assisted minimally invasive surgery for excision of cysts to achieve accurate diagnosis and treatment of such diseases.

Although the amygdala has structural and functional abnormalities in Chronic Migraine (CM), less is known about the altered perfusion of the amygdala in CM.

The current study aimed to assess amygdala perfusion in CM using a contrast agent-free and quantitative approach.

15 Normal Controls (NC) and 13 patients with CM during the migraine interval were assessed for brain structure and subjected to 3D Pseudo-Continuous Arterial Spin Labeling (3D-PCASL) MR imaging. The Cerebral Blood Flow (CBF) value of the amygdala was automatically extracted based on the individual amygdala mask for all participants. The independent sample t-test, Receiver Operating Characteristic (ROC) curve, and correlation analysis were used to evaluate the perfusion changes in CM.

Bilateral amygdala cerebral perfusion was lower in CM (left amygdala, 42.21±4.49 ml/100mg/min; right amygdala, 42.38±4.41 ml/100mg/min) than in NC (left amygdala, 48.31±6.92 ml/100mg/min; right amygdala, 47.88±6.53 ml/100mg/min) (left, p = 0.01; right, p = 0.02). There was no significant correlation between the perfusion of bilateral amygdalas and the clinical variables. Also, there was no significant difference in the volume of bilateral amygdalas between the two groups. The Area Under the Curve (AUC) of the CBF values of the left and right amygdala was 0.78 (95%CI: 0.58-0.91) and 0.75 (95%CI: 0.55-0.89), respectively. The cut-off value was 44.24 ml/100mg/min (left amygdala, with sensitivity 76.90% and specificity 78.70%) and 46.75 ml/100mg/min (right amygdala, with sensitivity 92.3% and specificity 58.80%), respectively.

CM presented bilateral hypoperfusion in the amygdala, offering potential diagnostic value in distinguishing CM from NC. The 3D-PCASL could be regarded as a simple and efficient neuroimaging tool to assess the perfusion status in CM patients.

Positron Emission Tomography (PET) scan stands as a valuable diagnostic tool in nuclear medicine, enabling the observation of metabolic and physiological changes at a molecular level. However, PET scans have a number of drawbacks, such as poor spatial resolution, noisy images, scattered radiation, artifacts, and radiation exposure. These challenges demonstrate the need for optimization in image processing techniques.

Our objective is to identify the evolving trends and impacts of publication in this field, as well as the most productive and influential countries, institutions, authors, themes, and articles.

A bibliometric study was conducted using a comprehensive query string such as “positron emission tomography” AND “image processing” AND optimization to retrieve 1,783 publications from 1981 to 2022 found in the Scopus database related to this field of study.

The findings revealed that the most influential country, institution, and authors are from the USA, and the most prevalent theme is TOF PET image reconstruction.

The increasing trend in publication in the field of optimization of image processing in PET scans would address the challenges in PET scan by reducing radiation exposure, faster scanning speed, as well as enhancing lesion identification.

This study aimed to compare the parametric value of T2 with and without fat suppression (FS) on T2 mapping for the evaluation of extraocular muscles (EOMs) in mild thyroid-associated ophthalmopathy (TAO).

We prospectively recruited 44 consecutive patients with mild TAO seen between May 2020 and October 2022 and 26 healthy controls with no history of eye- or thyroid-related or other autoimmune diseases. Patients with mild TAO were subdivided into active and inactive groups based on their clinical activity scores. The T2 of each EOM was measured over a large and small area of interest on T2-mapping images with and without FS. Receiver operating characteristic (ROC) curves were used to evaluate the diagnostic efficacy of T2 for detecting TAO activity.

The T2 was significantly and heterogeneously higher in the active group than in the inactive and control groups (P < 0.05). FS-T2-mapping images had better signal display within and at the edges of the EOMs than those without FS. It was possible to observe high-signal aggregation visible in the periphery of some EOMs, and the central part showed relatively low signals. The maximum T2 measured in small or large areas with and without FS had good diagnostic efficacy for TAO activity, with that of no-FS being better (the area under the ROC curve of the maximum T2 measured in a small area and a large area without FS was 1.0 and 1.0 and P values of < 0.001 and < 0.001, respectively).

Maximal T2 with or without FS can facilitate the early clinical detection of mild TAO activity. The maximum T2 in a small area can facilitate active staging of patients with mild TAO.

In the end stage of kidney disease, abnormal levels of blood calcium, phosphorus, and parathyroid hormone lead to bone metabolism disorders, manifesting as osteoporosis or fibrocystic osteoarthritis. X-ray, CT, and MR are useful for detecting bone lesions in dialysis patients, but currently, computer vision has not yet been used for this purpose.

ResNet is a powerful deep CNN model, which has not yet been used to distinguish between the bones of dialysis patients and healthy people. Therefore, this study aimed to investigate the ability of the Resnet50 model to identify the bone of dialysis patients from normal bone.

CT images of 200 cases (100 dialysis patients and 100 healthy people aged 31-72 years with male:female ratio of 51:49) were randomly divided into the training and testing groups at the ratio of 8:2. The module of ‘torch’ was used to train the model of Resnet50 for the current task of image classification. In the test cohort, the accuracy, sensitivity, and specificity with hyper-parameter=0 were 60%, 65%, and 55%, respectively. When the hyper-parameter was 0.6 or 0.7 versus 0, the accuracy was significantly higher (P<0.05). When the hyper-parameter was another number, the accuracy was not significantly different from that with no hyper-parameter (P>0.05).

This study has indicated computer vision to be suitable for identifying bone changes caused by dialysis; a hyper-parameter has been found necessary for improving model accuracy. The ResNet50 model with hyper-parameter = 0.7 has exhibited 90% sensitivity in identifying the bone of dialysis patients.

Individuals with depression have an increased risk of cardiovascular disease, and more often have a poor prognosis with cardiovascular disease. This study aimed to investigate the impact of depression on Left Ventricular (LV) alterations using Cardiovascular Magnetic Resonance Feature-tracking (CMR-FT).

Seven anesthetized, healthy Chinese miniature swine were included in the study. Basic data, including CMR scans at baseline and after 14 days of depression modeling, were collected. Behavioral tests, including the Open-field Test (OFT), Sucrose Preference Test (SPT), and measurements of the time taken to consume a specific amount of food and sugar, were conducted to assess the success of the depression models. CMR cine images were acquired and CVI software was employed to analyze Global Longitudinal Strain (GLS), Global Circumferential Strain (GCS), and Global Radial Strain (GRS). Late Gadolinium Enhancement (LGE) imaging was used to detect myocardial infarction and/or scar.

The outcomes demonstrated successful depression modeling, indicated by reduced scores in the OFT and SPT, as well as an extended time to intake food and sugar compared to baseline. However, no significant differences were observed in LV End-diastolic Volume (LVEDV), LV End-systolic Volume (LVESV), LV Ejection Fraction (LVEF), LV End-diastolic Myocardial Mass (LVMASSED), and Cardiac Output (CO) before and after modeling. Regarding LV global strain parameters, there was a downward trend in GRS (25.35% ± 6.9% vs. 22.86% ± 6.4%, P=0.021), GCS (-16.71% ± 4.2% vs. -14.78% ± 2.3%, P=0.043), and GLS (-17.66% ± 2.9% vs. -14.53% ± 2.5%, P=0.056), respectively, after modeling. GRS and GCS were significantly reduced after modeling compared to baseline.

The study suggests that depression may contribute to early LV systolic dysfunction, particularly affecting LV GCS and GRS.

The metastasis of primary breast invasive lobular carcinoma to the gastrointestinal tract and skin is a rare phenomenon, with the simultaneous occurrence of both transfers being more uncommon.

This article reports a case of a patient with hormone receptor-positive, HER2-negative breast invasive lobular carcinoma with gastrointestinal tract and skin metastases. The patient was assessed by a second-look ultrasound and diagnosed by subsequent ultrasound-guided needle biopsy. Following endocrine therapy, a favorable effect was observed, with significant regression of the primary breast lesion, cutaneous metastases, and gastrointestinal metastases.

Patients with breast invasive lobular carcinoma should be alert to the possibility of breast cancer metastasis, even if there are no obvious symptoms or signs, when they encounter rapidly progressive cutaneous nodules or plaques, or if they possess gastrointestinal abnormalities. For patients with negative breast ultrasonography for the first time, after combining mammography, Contrast-enhanced Spectral Mammography (CESM) or Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) examinations, if breast cancer is highly suspected, second-look ultrasound is particularly crucial at this juncture, which is the key prerequisite for breast needle biopsy and obtaining the gold standard of pathology.

Carotid duplex ultrasonography (DUS) is the primary screening tool for carotid artery stenosis, but has low reliability. MHR, which is the ratio of monocytes to high-density lipoprotein cholesterol (HDL-C), can be a marker for the degree and distribution of extracranial and intracranial atherosclerotic stenosis.

We determined the diagnostic value of DUS+MHR for internal carotid artery (ICA) stenosis.

We divided 273 hospitalized patients into non-stenosis (<50%) and ICA stenosis (≥50%) groups based on Digital Subtraction Angiography (DSA). We determined the peak systolic velocity (PSV) in the ICA on DUS, calculated the MHR, and investigated their relationship with ICA stenosis.

On DSA, 34.1% (93/273) patients had moderate-to-severe ICA stenosis. DUS and DSA showed low concordance for detecting ICA stenosis (kappa = 0.390). With increasing age, the incidence of moderate-to-severe ICA stenosis increased. PSV, monocyte count, and MHR were significantly greater in the stenosis group than in the non-stenosis group (P < 0.001), while the HDL-C level was significantly lower (P = 0.001). PSV (OR: 1.020, 95% CI: 1.011–1.029, P < 0.001) and MHR (OR: 5.662, 95% CI: 1.945–16.482, P = 0.002) were independent risk factors for ICA stenosis. The area under the receiver operating characteristic curve of PSV+MHR (0.819) was significantly higher than that of PSV or MHR alone (77.42% sensitivity, P = 0.0207; 73.89% specificity, P = 0.0032).

The combination of ICA PSV on DUS and MHR is better than PSV alone at identifying ICA stenosis and is well-suited to screen high-risk patients.

Endometrial Cancer (EC) is a highly heterogeneous cancer comprising both histological and molecular subtypes. Using a non-invasive modality method to trigger these subtypes as early as possible can aid clinicians in establishing individualized treatment.

The study aimed to clarify the value of the Apparent Diffusion Coefficient (ADC) of EC MRI in determining molecular subtypes.

We retrospectively recruited 109 patients with pathologically proven EC (78 endometrioid cancers and 31 non-endometrioid cancers) with available molecular classification from a tertiary centre. MRI was prospectively performed a month prior to surgery; images were blindly interpreted by two experienced radiologists with consensus reading. The ADC value was measured by an experienced radiologist on the commercially available processing workstation. Interoperator measurement consistency was calculated.

Our sample comprised 17 PLOE, 32 MSI-H, 31 NSMP, and 29 P53abn ECs. Clinical information did not differ significantly among the groups. The maximum diameter and volume of the lesions differed among the groups. The ADC value in the maximal area (ADCarea) or region of interest (ROI, ADCroi) in the P53abn group was higher than that in the other groups (894.0 ±12.6 and 817.5 ± 83.3 x10-6 mm2/s). The ADC mean values were significantly different between the P53abn group and the other groups (P = 0.000). The nomogram showed the highest discriminative ability to distinguish P53abn EC from other types (AUC: 0.859).

Our results have suggested the quantitative MR characteristics (ADC values) derived from preoperative EC MRI to provide useful information in preoperatively determining P53abn cancer.

The incidence of stroke is rising, and it is the second major cause of mortality and the third leading cause of disability globally. The goal of this study was to rapidly and accurately identify carotid plaques and automatically quantify plaque burden using our automated tracking and segmentation US-video system.

We collected 88 common carotid artery transection videos (11048 frames) with a history of atherosclerosis or risk factors for atherosclerosis, which were randomly divided into training, test, and validation sets using a 6:3:1 ratio. We first trained different segmentation models to segment the carotid intima and adventitia, and calculate the maximum plaque burden automatically. Finally, we statistically analyzed the plaque burden calculated automatically by the best model and the results of manual labeling by senior sonographers.

Of the three Artificial Intelligence (AI) models, the Robust Video Matting (RVM) segmentation model's carotid intima and adventitia Dice Coefficients (DC) were the highest, reaching 0.93 and 0.95, respectively. Moreover, the RVM model has shown the strongest correlation coefficient (0.61±0.28) with senior sonographers, and the diagnostic effectiveness between the RVM model and experts was comparable with paired-t test and Bland-Altman analysis [P= 0.632 and ICC 0.01 (95% CI: -0.24~0.27), respectively].

Our findings have indicated that the RVM model can be used in ultrasound carotid video. The RVM model can automatically segment and quantify atherosclerotic plaque burden at the same diagnostic level as senior sonographers. The application of AI to carotid videos offers more precise and effective methods to evaluate carotid atherosclerosis in clinical practice.

Currently, it is difficult to find a solution to the inverse inappropriate problem, which involves restoring a high-resolution image from a low-resolution image contained within a single image. In nature photography, one can capture a wide variety of objects and textures, each with its own characteristics, most notably the high-frequency component. These qualities can be distinguished from each other by looking at the pictures.

The goal is to develop an automated approach to identify thyroid nodules on ultrasound images. The aim of this research is to accurately differentiate thyroid nodules using Deep Learning Technique and to evaluate the effectiveness of different localization techniques.

The method used in this research is to reconstruct a single super-resolution image based on segmentation and classification. The poor-quality ultrasound image is divided into several parts, and the best applicable classification is chosen for each component. Pairs of high- and low-resolution images belonging to the same class are found and used to figure out which image is high-resolution for each segment. Deep learning technology, specifically the Adam classifier, is used to identify carcinoid tumors within thyroid nodules. Measures, such as localization accuracy, sensitivity, specificity, dice loss, ROC, and area under the curve (AUC), are used to evaluate the effectiveness of the techniques.

The results of the proposed method are superior, both statistically and qualitatively, compared to other methods that are considered one of the latest and best technologies. The developed automated approach shows promising results in accurately identifying thyroid nodules on ultrasound images.

The research demonstrates the development of an automated approach to identify thyroid nodules within ultrasound images using super-resolution single-image reconstruction and deep learning technology. The results indicate that the proposed method is superior to the latest and best techniques in terms of accuracy and quality. This research contributes to the advancement of medical imaging and holds the potential to improve the diagnosis and treatment of thyroid nodules.

Previous studies have indicated the abnormality of the globus pallidus in neonates with hyperbilirubinemia.

This study aims to explore the microstructure and cerebral perfusion of globus pallidus in neonatal hyperbilirubinemia by using Diffusion Tensor Imaging (DTI) and Arterial Spin Labeling (ASL) approaches.

Thirty-seven neonates were enrolled in this study, which were classified into Bilirubin-Induced Neurologic Dysfunction (BIND) group (hyperbilirubinemia with BIND, n=12), non-BIND group (hyperbilirubinemia without BIND, n=15), and healthy controls (HC) group (n=10). The quantitative values of globus pallidus were calculated from DTI, including the Apparent Diffusion Coefficient (ADC), the Fractional Anisotropy (FA), and Volume Ratio (VR) values. Additionally, the relative Cerebral Blood Flow (rCBF) values were obtained from ASL.

It was observed that the mean DTI signal of globus pallidus was significantly different among the three groups (p < 0.05). However, there were no significant differences in the rCBF of globus pallidus among the three groups (p > 0.05). A positive correlation was also observed between the fractional anisotropy (FA) value and serum bilirubin level (r = 0.561, p = 0.002), while the VR value showed a negative correlation with serum bilirubin level (r=-0.484, p=0.011). The area under the curve (AUC) of FA, VR, and FA and VR combined was 0.897, 0.858, and 0.933, respectively.

The alterations of microstructure in globus pallidus, especially FA and VR value, may be valuable and sensitive at the early stage of hyperbilirubinemia encephalopathy, suggesting that early hyperbilirubinemia may lead to cytotoxic edema and decreased permeability of the cell membrane.