Purpose
Current prostate brachytherapy uses transrectal ultrasound images for implant guidance, where contours of the prostate and organsâatârisk are necessary for treatment planning and dose evaluation. This work aims to develop a deep learningâbased method for male pelvic multiâorgan segmentation on transrectal ultrasound images.
Methods
We developed an anchorâfree mask convolutional neural network (CNN) that consists of three subnetworks, that is, a backbone, a fully convolutional oneâstate object detector (FCOS), and a mask head. The backbone extracts multiâlevel and multiâscale features from an ultrasound (US) image. The FOCS utilizes these features to detect and label (classify) the volumeâofâinterests (VOIs) of organs. In contrast to the design of a previously investigated mask regional CNN (Mask RâCNN), the FCOS is anchorâfree, which can capture the spatial correlation of multiple organs. The mask head performs segmentation on each detected VOI, where a spatial attention strategy is integrated into the mask head to focus on informative feature elements and suppress noise. For evaluation, we retrospectively investigated 83 prostate cancer patients by fivefold crossâvalidation and a holdâout test. The prostate, bladder, rectum, and urethra were segmented and compared with manual contours using the Dice similarity coefficient (DSC), 95% Hausdorff distance (HD95), mean surface distance (MSD), center of mass distance (CMD), and volume difference (VD).
Results
The proposed method visually outperforms two competing methods, showing better agreement with manual contours and fewer misidentified speckles. In the crossâvalidation study, the respective DSC and HD95 results were as follows for each organ: bladder 0.75 ± 0.12, 2.58 ± 0.7 mm; prostate 0.93 ± 0.03, 2.28 ± 0.64 mm; rectum 0.90 ± 0.07, 1.65 ± 0.52 mm; and urethra 0.86 ± 0.07, 1.85 ± 1.71 mm. For the holdâout tests, the DSC and HD95 results were as follows: bladder 0.76 ± 0.13, 2.93 ± 1.29 mm; prostate 0.94 ± 0.03, 2.27 ± 0.79 mm; rectum 0.92 ± 0.03, 1.90 ± 0.28 mm; and urethra 0.85 ± 0.06, 1.81 ± 0.72 mm. Segmentation was performed in under 5 seconds.
Conclusion
The proposed method demonstrated fast and accurate multiâorgan segmentation performance. It can expedite the contouring step of prostate brachytherapy and potentially enable autoâplanning and autoâevaluation.