Prediction of lipomatous soft tissue malignancy on MRI: comparison between machine learning applied to radiomics and deep learning

• Published in: European radiology experimental Vol. 6; no. 1; p. 41
• Main Authors: Fradet, Guillaume, Ayde, Reina, Bottois, Hugo, El Harchaoui, Mohamed, Khaled, Wassef, Drapé, Jean-Luc, Pilleul, Frank, Bouhamama, Amine, Beuf, Olivier, Leporq, Benjamin
• Format: Journal Article
• Language: English
• Published: Vienna Springer Vienna 01.12.2022; Springer Nature B.V; Springer; SpringerOpen
• Subjects: Artificial intelligence; Bioengineering; Cancer; Deep learning; Diagnostic Radiology; Imaging; Internal Medicine; Interventional Radiology; Life Sciences; Machine learning; Magnetic resonance imaging; Medicine; Medicine & Public Health; Neuroradiology; Original; Original Article; Radiology; Sarcoma; Soft tissue neoplasms; Tumors; Ultrasound; Deep learning; Magnetic resonance imaging; Soft tissue neoplasms; Artificial intelligence; Machine learning
• ISSN: 2509-9280; 2509-9280
• DOI: 10.1186/s41747-022-00295-9

Objectives Malignancy of lipomatous soft-tissue tumours diagnosis is suspected on magnetic resonance imaging (MRI) and requires a biopsy. The aim of this study is to compare the performances of MRI radiomic machine learning (ML) analysis with deep learning (DL) to predict malignancy in patients with lipomas oratypical lipomatous tumours. Methods Cohort include 145 patients affected by lipomatous soft tissue tumours with histology and fat-suppressed gadolinium contrast-enhanced T1-weighted MRI pulse sequence. Images were collected between 2010 and 2019 over 78 centres with non-uniform protocols (three different magnetic field strengths (1.0, 1.5 and 3.0 T) on 16 MR systems commercialised by four vendors (General Electric, Siemens, Philips, Toshiba)). Two approaches have been compared: (i) ML from radiomic features with and without batch correction; and (ii) DL from images. Performances were assessed using 10 cross-validation folds from a test set and next in external validation data. Results The best DL model was obtained using ResNet50 (resulting into an area under the curve (AUC) of 0.87 ± 0.11 (95% CI 0.65−1). For ML/radiomics, performances reached AUCs equal to 0.83 ± 0.12 (95% CI 0.59−1) and 0.99 ± 0.02 (95% CI 0.95−1) on test cohort using gradient boosting without and with batch effect correction, respectively. On the external cohort, the AUC of the gradient boosting model was equal to 0.80 and for an optimised decision threshold sensitivity and specificity were equal to 100% and 32% respectively. Conclusions In this context of limited observations, batch-effect corrected ML/radiomics approaches outperformed DL-based models.