Value of radiomics-based automatic grading of muscle edema in polymyositis/dermatomyositis based on MRI fat-suppressed T2-weighted images.

BACKGROUND: The precise and objective assessment of thigh muscle edema is pivotal in diagnosing and monitoring the treatment of dermatomyositis (DM) and polymyositis (PM). PURPOSE: Radiomic features are extracted from fat-suppressed (FS) T2-weighted (T2W) magnetic resonance imaging (MRI) of thigh muscles to enable automatic grading of muscle edema in cases of polymyositis and dermatomyositis. MATERIAL AND METHODS: A total of 241 MR images were analyzed and classified into five levels using the Stramare criteria. The correlation between muscle edema grading and T2-mapping values was assessed using Spearman's correlation. The dataset was divided into a 7:3 ratio of training (168 samples) and testing (73 samples). Thigh muscle boundaries in FS T2W images were manually delineated with 3D-Slicer. Radiomics features were extracted using Python 3.7, applying Z-score normalization, Pearson correlation analysis, and recursive feature elimination for reduction. A Naive Bayes classifier was trained, and diagnostic performance was evaluated using receiver operating characteristic (ROC) curves and comparing sensitivity and specificity with senior doctors. RESULTS: A total of 1198 radiomics parameters were extracted and reduced to 18 features for Naive Bayes modeling. In the testing set, the model achieved an area under the ROC curve of 0.97, sensitivity of 0.85, specificity of 0.98, and accuracy of 0.91. The Naive Bayes classifier demonstrated grading performance comparable to senior doctors. A significant correlation (r = 0.82, P <0.05) was observed between Stramare edema grading and T2-mapping values. CONCLUSION: The Naive Bayes model, utilizing radiomics features extracted from thigh FS T2W images, accurately assesses the severity of muscle edema in cases of PM/DM.

Fat-suppressed T2-weighted MRI appearance of subchondral insufficiency fracture of the femoral head.

OBJECTIVE: Our aims were to investigate the imaging appearance of subchondral insufficiency fracture (SIF) of the femoral head based on fat-suppressed T2-weighted MRI, and evaluate its correlation with the clinical outcomes following conservative treatment. MATERIALS AND METHODS: We retrospectively evaluated 40 hips in 37 patients with SIF of the femoral head (12 males and 25 females; mean age 55.8 years, range 22-78 years). MRI examinations were performed within 3 months after the onset of hip pain. Using fat-suppressed T2-weighted imaging, we evaluated the hips for the intensity of the subchondral bone (corresponding to the area superior to the low intensity band on T1-weighted images) as well as bone marrow edema, joint effusion, and presence of the band lesion. We then correlated the intensity of the subchondral bone with clinical outcomes. RESULTS: The hips were classified into three types based on subchondral intensity on fat-suppressed T2-weighted images: type 1 (21 hips) showed high intensity, type 2 (eight hips) showed heterogeneous intensity, and type 3 (11 hips) showed low intensity. The mean period between pain onset and MRI examination was significantly longer for type 2 hips than for type 1. Healing rates were 86 % for type 1, 75 % for type 2, and 18 % for type 3. CONCLUSION: SIF cases were classified into three types based on subchondral intensity on fat-suppressed T2-weighted imaging performed within 3 months after pain onset. Type 3 SIF tended to be intractable to conservative treatment compared to type 1 and type 2.

Intratumoral and Peritumoral Edema Radiomics Based on Fat-Suppressed T2- Weighted Imaging for Preoperative Prediction of Triple-Negative Breast Cancer.

AIM: Our aim was to explore the feasibility of using radiomics data derived from intratumoral and peritumoral edema on fat-suppressed T2-weighted imaging (T2 FS) to distinguish triple-negative breast cancer (TNBC) from non-triple-negative breast cancer (non-TNBC). METHODS: This retrospective study enrolled 174 breast cancer patients. According to the MRI examination time, patients before 2021 were divided into training (n = 119) or internal test (n = 30) cohorts at a ratio of 8:2. Patients from 2022 were included in the external test cohort (n = 25). Four regions of interest for each lesion were defined: intratumoral regions, peritumoral edema regions, regions with a combination of intratumoral and peritumoral edema, and regions with a combination of intratumoral and 5-mm peritumoral. Four radiomic signatures were built using the least absolute shrinkage and selection operator (LASSO) method after selecting features. Furthermore, a radio mic-radiological model was constructed using a combination of intratumoral and peritumoral edema regions along with clinical-radiologic features. Area under the receiver operating characteristic curve (AUC) calculations, decision curve analysis, and calibration curve analysis were performed to assess the performance of each model. RESULTS: The radiomic-radiological model showed the highest AUC values of 0.906 (0.788-1.000) and 82.5 (0.622-0.947) in both the internal and external test sets, respectively. The radiology-radiomic model exhibited excellent predictive performance, as evidenced by the calibration curves and decision curve analysis. CONCLUSION: The ensemble model based on T2 FS-based radiomic features of intratumoral and peritumoral edema, along with radiological factors, performed better in distinguishing TNBC from non-TNBC than a single model. We explored the possibility of developing explainable models to support the clinical decision-making process.

Value of fat-suppressed T2-weighted imaging for predicting short-term pain relief after sclerotherapy for venous malformations in the extremities.

PURPOSE: This study aimed to evaluate the value of fat-suppressed T2-weighted imaging (FS-T2WI) for predicting short-term pain relief after polidocanol sclerotherapy for painful venous malformations (VMs) in the extremities. MATERIALS AND METHODS: This retrospective study included patients with painful VMs in the extremities between October 2014 and September 2021, had their first sclerotherapy without history of surgical therapy, and underwent magnetic resonance imaging before sclerotherapy. Pain relief was assessed 2 months after 3% polidocanol sclerotherapy and was categorized as follows: progression, no change, partial relief, or free of pain. The associations between pain relief and imaging features on FS-T2WI were analyzed. RESULTS: The study included 51 patients. The no change, partial relief, and free of pain groups included 6 (11.8%), 25 (49.0%), and 20 (39.2%) patients, respectively. No patient experienced progressive pain. The lesion diameter was ≤ 50 mm in 13 (65.0%) patients in the free of pain group, whereas it was > 50 mm in all patients in the no change group (p = 0.019). The lesions showed well-defined margin in 15 (75.0%) patients in the free of pain group, whereas they showed ill-defined margin in 5 (83.3%) patients in the no change group (p = 0.034). The most common morphological type was cavitary in the free of pain group (14 [70.0%] patients), whereas there was no patient with cavitary type lesion in the no change group (p = 0.003). Drainage vein was demonstrated in 6 (100%), 22 (88.0%), and 11 (55.0%) patients in the no change, partial relief, and free of pain group, respectively (p = 0.011). CONCLUSION: A lesion size of 50 mm or less, a well-defined margin, a cavitary type, and no drainage vein on FS-T2WI were significant features for predicting short-term pain relief after polidocanol sclerotherapy for painful VMs in the extremities.