Exploratory Radiomics in Computed Tomography Perfusion of Prostate Cancer

Abstract

Background/aim: An evaluation if radiomic features of CT perfusion (CTP) can predict tumor grade and aggressiveness in prostate cancer was performed.

Materials and methods: Forty-seven patients had biopsy-confirmed prostate cancer, and received a CTP. Blood volume (BV), blood flow (BF) and mean transit time (MTT) maps were derived and 1,701 radiomic features were determined per patient. Regression models were built to estimate post-surgical Gleason score (GS), microvessel density (MVD) and distinguish between the different risk groups.

Results: Six out of the 47 patients had to be excluded from further analysis. A weak relationship between postsurgical GS and one radiomic parameter was found (R²=0.21, p=0.01). The same parameter combined with MTT inter-quartile range was prognostic for the risk group categorisation (AUC=0.81). Two different radiomic parameters were able to distinguish between low-intermediate risk and high-intermediate risk (AUC=0.77). Four parameters correlated with MVD (R2=0.53, p<0.02).

Conclusion: This exploratory study shows the potential of radiomics to classify prostate cancer.

Keywords: Radiomics; computed tomography perfusion; prostate cancer.