A combination of computer extracted measurements of prostate capsule shape and tumor texture on MRI to predict biochemical recurrence post treatment

• Published in: Journal of clinical oncology Vol. 35; no. 15_suppl; p. e16554
• Main Authors: Shiradkar, Rakesh, Ghose, Soumya, Purysko, Andrei, Madabhushi, Anant
• Format: Journal Article
• Language: English
• Published: 20.05.2017
• ISSN: 0732-183X; 1527-7755
• DOI: 10.1200/JCO.2017.35.15_suppl.e16554

Abstract only e16554 Background: Prostate cancer (PCa) biochemical recurrence (BCR) occurs in a significant proportion of men after treatment and is associated with increased mortality. Identifying PCa patients at risk of BCR following definitive therapy may help identify patients who might benefit from adjuvant therapy. Multi-parametric MRI (mpMRI) is being increasingly used in pre-treatment staging and risk stratification of PCa. In this work, we sought to explore whether a combination of computer extracted features relating to prostate capsule shape and tumor texture from pre-treatment mpMRI is predictive of BCR post treatment. Methods: This single center and retrospective study included 80 men with PCa who underwent pre-treatment 3T mpMRI and were followed for > 3 years post treatment. These men were grouped into a training set D 1 (N = 50, 25 each of BCR+ and BCR-) and an independent validation set D 2 (N = 30, 10 BCR+ and 20 BCR-). The prostate capsule and cancer region of interest (ROI) were annotated on mpMRI by a single experienced radiologist. Shape features (curvature and orientation) were extracted from a surface of interest where statistically significant differences were observed between BCR+ and BCR- patients in the training set. Radiomic features for capturing tumor textural patterns (including 1 st and 2 nd order statistics, Gabor and Haralick) were extracted from within the radiologist annotated cancer ROIs. Features from D 1 were used to train random forest classifiers, one each with shape (C s ) and radiomic (C R ) features. A fused Bayesian classifier (C R+S ) was created by integrating decisions from both C s and C R . Results: The classifiers C s , C R and C R+S were evaluated on independent validation set D 2 , resulting in area under the curve (AUCs) of 0.71, 0.81 and 0.84 respectively. C s added value in patients who had extra prostatic spread of PCa, but suffered from mpMRI intensity artefacts that affected performance of C R . Conclusions: Integrating prostate capsule shape and tumor radiomic features from pre-treatment mpMRI enabled prediction of PCa BCR after treatment. Multi-site validation is needed to establish the robustness of the approach.