Radiomics Texture Analysis of Bone Marrow Alterations in MRI Knee Examinations

The value of 2D and 3D MRI texture models in Grade II and III anterior cruciate ligament injuries

OBJECTIVE

To evaluate the diagnostic value 2D and 3D texture models for Grade II and III anterior cruciate ligament (ACL) injuries.

MATERIALS AND METHODS

Patients diagnosed with grade II and III ACL injuries through MRI examinations at our Hospital from January 2023 to December 2023 will be collected as the experimental group (n = 166). These cases were randomly stratified into training and validation sets with a ratio of 7:3. ACL was delineated, and texture features were extracted to establish both 2D and 3D models. The models were evaluated using a test set of patients who underwent surgery for confirmation(n = 81). Diagnostic performance was assessed using the area under the receiver operating characteristic curve (AUC). Differences were compared using the DeLong test. The clinical value of texture models were assessed using clinical decision curve and calibration curves.

RESULTS

A total of 247 cases from a single center were included. 2D and 3D texture models were constructed using three algorithms: RandomForest, Extra Trees, and XGBoost. For 2D texture models, the AUC values for the training, validation, and test sets were (0.998, 0.873, 0.697), (0.930, 0.778, 0.615), and (1.000, 0.821, 0.755), respectively. Corresponding AUC values for 3D models were (0.939, 0.899, 0.861), (0.852, 0.831, 0.826), and (0.982, 0.890, 0.728), respectively. DeLong test results, combined with clinical decision curve and calibration analysis, indicated that the 3D texture model using Random Forest outperformed others.

CONCLUSION

The 3D model using Random Forest showed high validity and stability in the diagnosis of grade II and III ACL injuries.

Infrapatellar fat pad as a source of biomarkers and therapeutic target for knee osteoarthritis

BACKGROUND AND OBJECTIVE

Osteoarthritis (OA) is a multifactorial and highly prevalent disease in elderly adults; however, its pathogenesis, diagnosis, and treatment are unmet needs nowadays. Research efforts have focused on elucidating the molecular mechanisms involved in the pathogenesis, onset, and progression of OA to facilitate early detection and effective therapeutic approaches. Infrapatellar fat pad (IPFP) represents a promising novel source of OA biomarkers given that it is an active player in OA. This review aims to investigate the current literature regarding the potential of the IPFP as a source of diagnostic and prognostic biomarkers for OA as well as potential target for novel therapies.

METHODS

A literature search was conducted in the PubMed database in June 2024. We included cross-sectional and longitudinal studies based on IPFP from human OA patients, oriented in the identification of imaging, biochemical, and molecular biomarkers in the IPFP.

RESULTS

After screening and evaluation, we included a total of 61 studies. Most of the imaging publications (n = 47) on IPFP are based on magnetic resonance imaging (MRI) that revealed potential semiquantitative and quantitative imaging biomarkers linked to inflammation, fibrosis, pain, and joint degeneration imaging parameters. Biochemical and molecular studies (n = 14) pointed out an increase in interleukin-6 (IL-6), fatty acid-binding protein 4 (FABP4), adiponectin, and lysophosphatidylcholine (LysoPC) in the IPFP during OA progression.

CONCLUSIONS

Imaging, biochemical, and molecular studies indicate OA potential biomarkers in the IPFP related to inflammation, lipid dysregulation, and fibrosis. The combination of imaging and biochemical biomarkers could provide a better prediction of OA onset and the identification of OA progressors at an early stage. The IPFP study could also reveal potential therapeutic targets with the vision of better precision medicine.

Machine learning-based radiomics using MRI to differentiate early-stage Duchenne and Becker muscular dystrophy in children

OBJECTIVES

Duchenne muscular dystrophy (DMD) and Becker muscular dystrophy (BMD) present similar symptoms in the early stage, complicating their differentiation. This study aims to develop a classification model using radiomic features from MRI T2-weighted Dixon sequences to increase the accuracy of distinguishing DMD and BMD in the early disease stage.

METHODS

We retrospectively analysed MRI data from 62 patients aged 36-60 months with muscular dystrophy, including 41 with DMD and 21 with BMD. Radiomic features were extracted from in-phase, opposed-phase, water, fat, and postprocessed fat fraction images. We employed a deep learning segmentation method to segment regions of interest automatically. Feature selection included the Mann‒Whitney U test for identifying significant features, Pearson correlation analysis to remove collinear features, and the LASSO regression method to select features with nonzero coefficients. These selected features were then used in various machine learning algorithms to construct the classification model, and their diagnostic performance was compared.

RESULTS

Our proposed radiomic and machine learning methods effectively distinguished early DMD and BMD. The machine learning models significantly outperformed the radiologists in terms of accuracy (81.2-90.6% compared with 69.4%), specificity (71.0-86.0% compared with 19.0%), and F1 score (85.2-92.6% compared with 80.5%), while maintaining relatively high sensitivity (85.6-95.0% compared with 95.1%).

CONCLUSION

Radiomics based on Dixon sequences combined with machine learning methods can effectively distinguish between DMD and BMD in the early stages, providing a new and effective tool for the early diagnosis of these muscular dystrophies.

CLINICAL TRIAL NUMBER

Not applicable.

Differential Diagnosis of Diabetic Foot Osteomyelitis and Charcot Neuropathic Osteoarthropathy with Deep Learning Methods

Our study aims to evaluate the potential of a deep learning (DL) algorithm for differentiating the signal intensity of bone marrow between osteomyelitis (OM), Charcot neuropathic osteoarthropathy (CNO), and trauma (TR). The local ethics committee approved this retrospective study. From 148 patients, segmentation resulted in 679 labeled regions for T1-weighted images (comprising 151 CNO, 257 OM, and 271 TR) and 714 labeled regions for T2-weighted images (consisting of 160 CNO, 272 OM, and 282 TR). We employed both multi-class classification (MCC) and binary-class classification (BCC) approaches to compare the classification outcomes of CNO, TR, and OM. The ResNet-50 and the EfficientNet-b0 accuracy values were computed at 96.2% and 97.1%, respectively, for T1-weighted images. Additionally, accuracy values for ResNet-50 and the EfficientNet-b0 were determined at 95.6% and 96.8%, respectively, for T2-weighted images. Also, according to BCC for CNO, OM, and TR, the sensitivity of ResNet-50 is 91.1%, 92.4%, and 96.6% and the sensitivity of EfficientNet-b0 is 93.2%, 97.6%, and 98.1% for T1, respectively. For CNO, OM, and TR, the sensitivity of ResNet-50 is 94.9%, 83.6%, and 97.9% and the sensitivity of EfficientNet-b0 is 95.6%, 85.2%, and 98.6% for T2, respectively. The specificity values of ResNet-50 for CNO, OM, and TR in T1-weighted images are 98.1%, 97.9%, and 94.7% and 98.6%, 97.5%, and 96.7% in T2-weighted images respectively. Similarly, for EfficientNet-b0, the specificity values are 98.9%, 98.7%, and 98.4% and 99.1%, 98.5%, and 98.7% for T1-weighted and T2-weighted images respectively. In the diabetic foot, deep learning methods serve as a non-invasive tool to differentiate CNO, OM, and TR with high accuracy.

Radiomics analysis using magnetic resonance imaging of bone marrow edema for diagnosing knee osteoarthritis

This study aimed to develop and validate a bone marrow edema model using a magnetic resonance imaging-based radiomics nomogram for the diagnosis of osteoarthritis. Clinical and magnetic resonance imaging (MRI) data of 302 patients with and without osteoarthritis were retrospectively collected from April 2022 to October 2023 at Longhua Hospital affiliated with the Shanghai University of Traditional Chinese Medicine. The participants were randomly divided into two groups (a training group, n = 211 and a testing group, n = 91). We used logistic regression to analyze clinical characteristics and established a clinical model. Radiomics signatures were developed by extracting radiomic features from the bone marrow edema area using MRI. A nomogram was developed based on the rad-score and clinical characteristics. The diagnostic performance of the three models was compared using the receiver operating characteristic curve and Delong's test. The accuracy and clinical application value of the nomogram were evaluated using calibration curve and decision curve analysis. Clinical characteristics such as age, radiographic grading, Western Ontario and McMaster Universities Arthritis Index score, and radiological features were significantly correlated with the diagnosis of osteoarthritis. The Rad score was constructed from 11 radiological features. A clinical model was developed to diagnose osteoarthritis (training group: area under the curve [AUC], 0.819; testing group: AUC, 0.815). Radiomics models were used to effectively diagnose osteoarthritis (training group,: AUC, 0.901; testing group: AUC, 0.841). The nomogram model composed of Rad score and clinical characteristics had better diagnostic performance than a simple clinical model (training group: AUC, 0.906; testing group: AUC, 0.845; p < 0.01). Based on DCA, the nomogram model can provide better diagnostic performance in most cases. In conclusion, the MRI-bone marrow edema-based radiomics-clinical nomogram model showed good performance in diagnosing early osteoarthritis.