Clinically significant prostate cancer detection on MRI with self-supervised learning using image context restoration

Amir Bolous; Arun Seetharaman; Indrani Bhattacharya; Richard E. Fan; Simon John Christoph Soerensen; Leo Chen; Pejman Ghanouni; Geoffrey A. Sonn; Mirabela Rusu

doi:10.1117/12.2581557

Translator Disclaimer

15 February 2021 Clinically significant prostate cancer detection on MRI with self-supervised learning using image context restoration

Amir Bolous, Arun Seetharaman, Indrani Bhattacharya, Richard E. Fan, Simon John Christoph Soerensen, Leo Chen, Pejman Ghanouni, Geoffrey A. Sonn, Mirabela Rusu

Author Affiliations +

Proceedings Volume 11597, Medical Imaging 2021: Computer-Aided Diagnosis; 115971M (2021) https://doi.org/10.1117/12.2581557
Event: SPIE Medical Imaging, 2021, Online Only

Abstract

Prostate MRI is increasingly used to help localize and target prostate cancer. Yet, the subtle differences in MRI appearance of cancer compared to normal tissue renders MRI interpretation challenging. Deep learning methods hold promise in automating the detection of prostate cancer on MRI, however such approaches require large, well-curated datasets. Although existing methods that employed fully convolutional neural networks have shown promising results, the lack of labeled data can reduce the generalization of these models. Self-supervised learning provides a promising avenue to learn semantic features from unlabeled data. In this study, we apply the self-supervised strategy of image context restoration to detect prostate cancer on MRI and show this improves model performance for two different architectures (U-Net and Holistically Nested Edge Detector) compared to their purely supervised counterparts. We train our models on MRI exams from 381 men with biopsy confirmed cancer. Our study showed self-supervised models outperform randomly initialized models on an independent test set in a variety of training settings. We performed 3 experiments, where we trained with 5%, 25% and 100% of our labeled data, and observed that the U-Net based pre-training and downstream task outperformed other models. We observed the best improvements when training with 5% of the labeled training data, our selfsupervised U-Nets improve per-pixel Area Under the Curve (AUC, 0.71 vs 0.83) and Dice Similarity coefficient (0.19 vs 0.53). When training with 100% of the data, our U-Net-based pretraining and detection achieved an AUC of 0.85 and Dice similarity coefficient of 0.57.

Conference Presentation

Citation Download Citation

Amir Bolous, Arun Seetharaman, Indrani Bhattacharya, Richard E. Fan, Simon John Christoph Soerensen, Leo Chen, Pejman Ghanouni, Geoffrey A. Sonn, and Mirabela Rusu "Clinically significant prostate cancer detection on MRI with self-supervised learning using image context restoration", Proc. SPIE 11597, Medical Imaging 2021: Computer-Aided Diagnosis, 115971M (15 February 2021); https://doi.org/10.1117/12.2581557

ACCESS THE FULL ARTICLE