Development and Evaluation of MR-Based Radiogenomic Models to Differentiate Atypical Lipomatous Tumors from Lipomas

Abstract

Background: The aim of this study was to develop and validate radiogenomic models to predict the MDM2 gene amplification status and differentiate between ALTs and lipomas on preoperative MR images. Methods: MR images were obtained in 257 patients diagnosed with ALTs (n = 65) or lipomas (n = 192) using histology and the MDM2 gene analysis as a reference standard. The protocols included T2-, T1-, and fat-suppressed contrast-enhanced T1-weighted sequences. Additionally, 50 patients were obtained from a different hospital for external testing. Radiomic features were selected using mRMR. Using repeated nested cross-validation, the machine-learning models were trained on radiomic features and demographic information. For comparison, the external test set was evaluated by three radiology residents and one attending radiologist. Results: A LASSO classifier trained on radiomic features from all sequences performed best, with an AUC of 0.88, 70% sensitivity, 81% specificity, and 76% accuracy. In comparison, the radiology residents achieved 60–70% accuracy, 55–80% sensitivity, and 63–77% specificity, while the attending radiologist achieved 90% accuracy, 96% sensitivity, and 87% specificity. Conclusion: A radiogenomic model combining features from multiple MR sequences showed the best performance in predicting the MDM2 gene amplification status. The model showed a higher accuracy compared to the radiology residents, though lower compared to the attending radiologist.

The impact of radiomics in the management of soft tissue sarcoma

“…One study [ 28 ] examined the associations between temporal alterations observed in MRI, based on qualitative/semi-quantitative features and radiomics features, and the survival outcomes and histopathological characteristics. Foreman et al [ 48 ] developed radiogenomic models with the purpose of predicting the MDM2 gene amplification status and distinguishing between atypical lipomatous tumours and lipomas based on preoperative MRI scans. Nine studies assessed the role of radiomics features for evaluating the toxicity, management and treatment responses of patients with STSs treated with radiotherapy and/or chemotherapy [ 23 , 44 , 49 – 55 ].…”

“…In another study, Timbergen et al [ 47 ] evaluated MRI radiomics models for distinguishing between desmoid-type fibromatosis and STSs. As previously mentioned, Foreman et al [ 48 ] attempted to develop radiogenomic models with the goal of distinguishing between atypical lipomatous tumours and lipomas by analysing the MDM2 gene amplification status using preoperative MRI scans. Aouadi et al [ 60 ] examined several datasets, in particular the LIPO dataset [ 61 ] for distinguishing between well-differentiated liposarcoma and lipoma, and the Desmoid dataset [ 61 ] for differentiating desmoid-type fibromatosis from extremity STSs.…”

“…Two datasets were specifically analysed for STSs, the first (LIPO) to classify well-differentiated liposarcoma or lipoma, and the second (Desmoid) to classify desmoid-type fibromatosis or extremity STSs The best radiomics approach achieved an AUC of 0.86 for the LIPO dataset and 0.844 for Desmoid dataset. The best deep convolutional neural networks approach achieved an AUC of 0.982 for the LIPO dataset and 0.961 for Desmoid dataset 10.1002/jmri.28331 Lee et al (Republic of Korea) [ 30 ] March 2023 Risk stratification Retrospective MRI 72 1132 To investigate the effectiveness of a radiomics model using T2-weighted Dixon sequence in differentiating the degree of STSs margin infiltration The radiomics model constructed with radiomic volume and shape and other T2 features showed the highest AUC (0.821) both for the models generated by LASSO + RF and LASSO + SMOTE + RF algorithms 10.3390/cancers15072150 Foreman et al (Germany) [ 48 ] 2023 Apr Diagnosis and Radiogenomics Retrospective MRI 307 312 To build and validate radiogenomic models aimed at predicting the MDM2 gene amplification status and differentiating between atypical lipomatous tumours and lipomas using preoperative MRI scans The LASSO classifier, utilising radiomic features extracted from all imaging sequences, exhibited excellent performance, achieving an AUC of 0.88 in the testing dataset 10.1093/jamiaopen/ooad025 Casale et al (Belgium) [ 34 ] 2023 Apr Risk stratification Retrospective MRI 47 102 To propose a methodology that utilised formal logic models to predict the risk of metastases and recurrence in patients with extremity STSs by analysing MRI radiomic features The sensitivity and specificity of the methodology were found to be 0.81 and 0.67, respectively 10.1177/02841851231179933 Zhu et al (China) [ 43 ] 2023 Jun Radiogenomics Ret...…”

Sarculator: how to improve further prognostication of all sarcomas

“…However, this study serves as a proof of concept, laying the groundwork for further developments. Other studies have investigated the role of radiomics both in discriminating between benign and malignant soft-tissue tumors [41,42] and in distinguishing between lipoma and liposarcoma/ atypical lipomatous tumors [43,44]. Additionally, other studies have explored the potential of radiomics for identifying high-grade STS [45].…”