Towards an Interpretable Radiomics Model for Classifying Renal Cell Carcinomas Subtypes: A Radiogenomics Assessment
- Resource Type
- Conference
- Authors
- Li, Zhi-Cheng; Wu, Guang-yu; Zhang, Jinheng; Wang, Zhongqiu; Liu, Guiqin; Liang, Dong
- Source
- 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019) Biomedical Imaging (ISBI 2019), 2019 IEEE 16th International Symposium on. :1288-1292 Apr, 2019
- Subject
- Bioengineering
Tumors
Computed tomography
Feature extraction
Biological system modeling
Entropy
Radiomics
renal cell carcinomas
VHL
- Language
- ISSN
- 1945-8452
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.