Radiomics and Deep Learning Model for Benign and Malignant Soft Tissue Tumors Differentiation of Extremities and Trunk.

RATIONALE AND OBJECTIVES

To develop radiomics and deep learning models for differentiating malignant and benign soft tissue tumors (STTs) preoperatively based on fat saturation T2-weighted imaging (FS-T2WI) of patients.

MATERIALS AND METHODS

Data of 115 patients with STTs of extremities and trunk were collected from our hospital as the training set, and data of other 70 patients were collected from another center as the external validation set. Outlined Regions of interest included the intratumor and the peritumor region extending outward by 5 mm, then the corresponding radiomics features were extracted respectively. Deep learning was performed using pretrained 3D ResNet algorithms, and deep learning features were extracted from the entire FS-T2WI of patients. Recursive feature elimination and least absolute shrinkage and selection operator were used to select the radiomics and deep learning features with predictive value. Five machine learning algorithms were applied to build radiomics models, the area under the ROC curve (AUC) in the validation set were used to evaluate the diagnostic performance, and decision curve analysis (DCA) was used to evaluate the clinical benefit of models.

RESULTS

Based on 20 selected deep learning and radiomics features, the deep learning radiomics (DLR) model had the best predictive performance in the validation set, with an AUC of 0.9410. DCA and calibration curves showed that the DLR model had better clinical net benefit and goodness of fit.

CONCLUSION

By extracting more features from FS-T2WI, the DLR model is a noninvasive, low-cost, and highly accurate preoperative differential diagnosis of benign and malignant STTs.