Associations between Statin/Omega3 Usage and MRI-Based Radiomics Signatures in Prostate Cancer

Abstract

Prostate cancer is the most common noncutaneous cancer and the second leading cause of cancer deaths among American men. Statins and omega-3 are two medications recently found to correlate with prostate cancer risk and aggressiveness, but the observed associations are complex and controversial. We therefore explore the novel application of radiomics in studying statin and omega-3 usage in prostate cancer patients. On MRIs of 91 prostate cancer patients, two regions of interest (ROIs), the whole prostate and the peripheral region of the prostate, were manually segmented. From each ROI, 944 radiomic features were extracted after field bias correction and normalization. Heatmaps were generated to study the radiomic feature patterns against statin or omega-3 usage. Radiomics models were trained on selected features and evaluated with 500-round threefold cross-validation for each drug/ROI combination. On the 1500 validation datasets, the radiomics model achieved average AUCs of 0.70, 0.74, 0.78, and 0.72 for omega-3/prostate, omega-3/peripheral, statin/prostate, and statin/peripheral, respectively. As the first study to analyze radiomics in relation to statin and omega-3 uses in prostate cancer patients, our study preliminarily established the existence of imaging-identifiable tissue-level changes in the prostate and illustrated the potential usefulness of radiomics for further exploring these medications' effects and mechanisms in prostate cancer.

Keywords: MRI; artificial intelligence; omega-3; prostate cancer; radiomics; statin.

Figure 1

Example contours of the prostate region of interest (ROI) (blue) and the peripheral zone ROI (red).

Figure 2

A schematic drawing of the data analysis workflow. Four independent combinations were analyzed, and their corresponding models were developed to study the effects of each drug on each region of interest (ROI).

Figure 3

Heatmaps showing the radiomics feature pattern across the patient population with the usage of omega-3 and statin for (A) the prostate ROI and (B) the peripheral ROI.

Figure 4

Average ROC curves of the radiomics model for (A) omega-3 usage prediction based on prostate ROI, (B) omega-3 usage prediction based on peripheral ROI, (C) statin usage prediction based on prostate ROI, and (D) statin usage prediction based on peripheral ROI. The ROC curves are averaged from the 1500 validation test sets.

Figure 5

Area under the curve (AUC) and precision AUC (PRAUC) achieved on the 1500 validation sets by the radiomics model for (A) omega-3 usage prediction based on prostate ROI, (B) omega-3 usage prediction based on peripheral ROI, (C) statin usage prediction based on prostate ROI, and (D) statin usage prediction based on peripheral ROI. The radiomic features used in each model are also listed.