Scale- and Slice-aware Net (S² aNet) for 3D segmentation of organs and musculoskeletal structures in pelvic MRI

MRI of organs and musculoskeletal structures in the female pelvis presents a unique display of pelvic anatomy. Automated segmentation of pelvic structures plays an important role in personalized diagnosis and treatment on pelvic structures disease. Pelvic organ systems are very complicated, and it is a challenging task for 3D segmentation of massive pelvic structures on MRI.

A new Scale- and Slice-aware Net ( $$ aNet) is presented for 3D dense segmentation of 54 organs and musculoskeletal structures in female pelvic MR images. A Scale-aware module is designed to capture the spatial and semantic information of different-scale structures. A Slice-aware module is introduced to model similar spatial relationships of consecutive slices in 3D data. Moreover, $$ aNet leverages a weight-adaptive loss optimization strategy to reinforce the supervision with more discriminative capability on hard samples and categories.

Experiments have been performed on a pelvic MRI cohort of 27 MR images from 27 patient cases. Across the cohort and 54 categories of organs and musculoskeletal structures manually delineated, $$ aNet was shown to outperform the UNet framework and other state-of-the-art fully convolutional networks in terms of sensitivity, Dice similarity coefficient and relative volume difference.

The experimental results on the pelvic 3D MR dataset show that the proposed $$ aNet achieves excellent segmentation results compared to other state-of-the-art models. To our knowledge, $$ aNet is the first model to achieve 3D dense segmentation for 54 musculoskeletal structures on pelvic MRI, which will be leveraged to the clinical application under the support of more cases in the future.