Automatic Prostate Zonal Segmentation Using Fully Convolutional Network With Feature Pyramid Attention

Our main objective in the paper is to develop a novel deep learning-based algorithm for automatic segmentation of prostate zones and to evaluate the performance of the algorithm on an additional independent testing dataset in comparison with inter-reader agreement between two experts. With IRB approval and HIPAA compliance, we designed a novel convolutional neural network (CNN) for automatic segmentation of the prostatic transition zone (TZ) and peripheral zone (PZ) on T2-weighted (T2w) 3 Tesla (3T) MRI. The total study cohort included 359 MRI scans of patients in subcohorts; 313 scans from a deidentified publicly available dataset (SPIE-AAPM-NCI PROSTATEX challenge) and 46 scans from a large U.S. tertiary referral center (external testing dataset (ETD)). The TZ and PZ contours were manually annotated by research fellows, supervised by expert genitourinary (GU) radiologists. The model was developed using 250 patients and tested internally using the remaining 63 patients from the PROSTATEX (internal testing dataset (ITD)) and tested again (n=46) externally using the ETD. The Dice Similarity Coefficient (DSC) was used to evaluate the segmentation performance. DSCs for PZ and TZ were 0.74±0.08 and 0.86±0.07 in the ITD respectively. In the ETD, DSCs for PZ and TZ were 0.74±0.07 and 0.79±0.12, respectively. The inter-reader consistency (Expert 2 vs. Expert 1) were 0.71±0.13 (PZ) and 0.75±0.14 (TZ). This novel DL algorithm enabled automatic segmentation of PZ and TZ with high accuracy on both ITD and ETD without a performance difference for PZ and less than 10% TZ difference. In the ETD, the proposed method can be comparable to experts in the segmentation of prostate zones. Part of our source code and datasets with annotations is available at https://github.com/ykl-ucla/prostate_zonal_seg.