Radiomics and Machine Learning Differentiate Soft-Tissue Lipoma and Liposarcoma Better than Musculoskeletal Radiologists

Figure 1

Radiomics analysis pipeline.Radiomics analysis pipeline for all included patients, showing (a) acquisition of the T1-SE image, followed by (b) soft-tissue lesion segmentation using Slicer 3D and (c) radiomics features extraction using Pyradiomics. (d) Radiomics features were finally used to train and assess the performance of a machine-learning classifier to distinguish liposarcoma and lipoma.

(a)

(b)

(c)

(d)