Semi-automatic classification of prostate cancer on multi-parametric MR imaging using a multi-channel 3D convolutional neural network

Abstract

Objective: To present a deep learning-based approach for semi-automatic prostate cancer classification based on multi-parametric magnetic resonance (MR) imaging using a 3D convolutional neural network (CNN).

Methods: Two hundred patients with a total of 318 lesions for which histological correlation was available were analyzed. A novel CNN was designed, trained, and validated using different combinations of distinct MRI sequences as input (e.g., T2-weighted, apparent diffusion coefficient (ADC), diffusion-weighted images, and K-trans) and the effect of different sequences on the network's performance was tested and discussed. The particular choice of modeling approach was justified by testing all relevant data combinations. The model was trained and validated using eightfold cross-validation.

Results: In terms of detection of significant prostate cancer defined by biopsy results as the reference standard, the 3D CNN achieved an area under the curve (AUC) of the receiver operating characteristics ranging from 0.89 (88.6% and 90.0% for sensitivity and specificity respectively) to 0.91 (81.2% and 90.5% for sensitivity and specificity respectively) with an average AUC of 0.897 for the ADC, DWI, and K-trans input combination. The other combinations scored less in terms of overall performance and average AUC, where the difference in performance was significant with a p value of 0.02 when using T2w and K-trans; and 0.00025 when using T2w, ADC, and DWI. Prostate cancer classification performance is thus comparable to that reported for experienced radiologists using the prostate imaging reporting and data system (PI-RADS). Lesion size and largest diameter had no effect on the network's performance.

Conclusion: The diagnostic performance of the 3D CNN in detecting clinically significant prostate cancer is characterized by a good AUC and sensitivity and high specificity.

Key points: • Prostate cancer classification using a deep learning model is feasible and it allows direct processing of MR sequences without prior lesion segmentation. • Prostate cancer classification performance as measured by AUC is comparable to that of an experienced radiologist. • Perfusion MR images (K-trans), followed by DWI and ADC, have the highest effect on the overall performance; whereas T2w images show hardly any improvement.

Keywords: Convolutional neural networks; Deep learning; Multi-parametric MRI; Prostate cancer; Three-dimensional images.