Towards an Interpretable Radiomics Model for Classifying Renal Cell Carcinomas Subtypes: A Radiogenomics Assessment

• Published in: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) pp. 1288 - 1292
• Main Authors: Li, Zhi-Cheng, Wu, Guang-yu, Zhang, Jinheng, Wang, Zhongqiu, Liu, Guiqin, Liang, Dong
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.04.2019
• Subjects: Biological system modeling; Computed tomography; Entropy; Feature extraction; Radiomics; renal cell carcinomas; Tumors; VHL
• ISSN: 1945-8452
• DOI: 10.1109/ISBI.2019.8759592

Differentiating clear cell renal cell carcinomas (ccRCC) from non-ccRCC subtypes is of essential importance as they have substantially different prognosis and therapeutic pathways. Radiomics is an imaging-based approach successfully applied in many classification tasks of cancer subtypes. Despite its strong performance, it's challenging to understand why a radiomics model makes a particular prediction. This paper presented an interpretable radiomics model by extracting all-relevant features from multiphasic CT for differentiating ccRCC from non-ccRCC. The biological meaning of radiomics was investigate by assessing the possible radiogenomics link between the imaging features and a key ccRCC driver gene-the von Hippel-Lindau (VHL) mutation. The model with eight all-relevant features achieved an AUC 0.949 and an accuracy 92.9%. Five features were significantly associated with VHL mutation (FDR \mathrm{p}\lt .05). It implied that radiomics model can be accurate and interpretable when the imaging features reflect underlying molecular basis of cancer.