Automatic Multiparametric Magnetic Resonance Imaging-Based Prostate Lesions Assessment with Unsupervised Domain Adaptation

Multiparametric magnetic resonance imaging (mpMRI) has emerged as a valuable diagnostic tool in prostate lesion assessment. However, training convolutional neural networks (CNNs) inevitably involves magnetic resonance (MR) images from multiple cohorts. There always exists variation in scanning protocol among cohorts, inducing significant changes in data distribution between source and target domains. This challenge has greatly limited clinical adoption on a large scale. Herein, a coarse mask-guided deep domain adaptation network (CMD(2)A-Net) is proposed to develop a fully automated framework for prostate lesion detection and classification (PLDC). No category or mask label is required from the target domain. A coarse segmentation module is trained to cover the possible lesion-related regions, so that attention maps can be generated to dedicate the local feature extraction of lesions within those regions. Experiments are performed on 512 mpMRI sets from datasets of PROSTATEx (330 sets) and two cohorts, A (74 sets) and B (108 sets). Using ensemble learning, CMD(2)A-Net accomplishes an AUC of 0.921 in cohort A and 0.913 in cohort B, demonstrating its transferability from a large-scale public dataset PROSTATEx to small-scale target domains. Results from an ablation study also support its effectiveness in classification between benign and malignant lesions, compared to the state-of-the-art models. An interactive preprint version of the article can be found here: .

Automated summary

In this study, a coarse mask-guided deep domain adaptation network (CMD(2)A-Net) is proposed for automated prostate lesion detection and classification. The experiments demonstrate that CMD(2)A-Net performs well on multiple datasets and achieves better results in benign and malignant lesion classification compared to existing models.