Context-Aware Synergetic Multiplex Network for Multi-organ Segmentation of Cervical Cancer MRI

Generative Adversarial Networks (GANs) have increasingly broken records in solving challenging medical image analyses problems such as medical image de-noising, segmentation, detection, classification or reconstruction. However, to the best of our knowledge, they have not been used for female pelvic multi-organ segmentation. Accurate segmentation of uterine cervical cancer (UCC) organs (i.e., bladder, vagina and tumor) from magnetic resonance imaging (MRI) is crucial for effective UCC staging. However, it is a highly challenging task due to 1) noisy MR images, 2) within-subject large variability in structure and intensity of UCC organs, and 3) across-subject variability. More importantly, there have been very limited works on how to aggregate different interactions across MRI views using GANs for multi-organ segmentation while providing context information. In this work, we propose a novel synergetic multiplex network (SMN) using multi-stage deep learning architecture based on cycle-GAN to segment pelvic multi-organ using complementary multi-view MRI, introducing three major contributions in multi-organ segmentation literature: (1) Modeling the interactions across data views using a novel multiplex architecture composed of multiple layers. Each SMN layer nests a cascade of view-specific context-aware cycle-GANs and synergistically communicates context information to other paralleled view-specific layers via multiplex coupling links. (2) SMN captures shared and complementary information between different views to segment UCC in different MRI views. (3) It enforces the spatial consistency between neighboring pixels within the same tissue for UCC segmentation. Specifically, in a gradual and deep manner, the proposed method improves the segmentation results by iteratively providing more refined context information from other views to train the next segmentation cycle-GAN in the SMN layer. We evaluated our SMN framework using 15 T2w-MR sequences with axial and sagittal views. We show that SMN is robust for the UCC segmentation task by significantly (\(p<0.05\)) outperforming comparison segmentation methods.