Five datasets are utilized in this study, i.e. Initiative for Collaborative Computer Vision Benchmarking (I2CVB) [1], PROSTATEx[2] (P-x), and three datasets from Hong Kong hospital local cohorts, LC-A, LC-B, and LC-C. Note that, LC-A and LC-B were acquired from the same MR[3] imaging center. Table 1 shows characteristics of these five datasets. Note that I2CVB is already available online, which has been widely investigated for prostate zone segmentation [4]. It contains 646 T2 images acquired from 36 patients. Fifteen patients were scanned by 3.0-T Siemens scanners and 21 patients by 1.5-T General Electric scanners. Given the segmentation labels on the prostate, central gland, peripheral zone, and lesion, only image slices covering the prostate are selected as our samples. A Mask R-CNN model is employed for prostate segmentation using this dataset. P-x, LC-A, LC-B, and LC-C are mpMRI-based datasets marked with point labels. The four datasets share the same set of category labels (i.e. csPCa and non-csPCa). Dataset, P-x, LC-A, and LC-B, are utilized to evaluate the PLDC performance of our CMD²A-Net, including 330 cases from P-x, 74 cases from LC-A, and 108 cases from LC-B. To avoid “overfit” caused by LC-C (29 cases) with its small size, it is only used for cross-site heterogeneity analysis.