Prostate Segmentation on Magnetic Resonance Imaging

Abstract

Automatic and precise segmentation of the prostate is beneficial to various diagnostic and therapeutic procedures on magnetic resonance imaging. However, the work is very challenging because of the heterogeneity of prostate tissue, the lack of clearly defined boundaries, and the wide variation in prostate shape between individuals. Based on the segmentation scheme for the prostate and its lesion regions, a new deep convolution neural network is proposed in this research. To acquire excellent segmentation performance with consistency in both appearance and space, CRF-RNN is added on top of the network. By introducing an attention mechanism, the network is made to focus more feature on the prostate zones in both channel and spatial dimensions. In addition, a new dense block is created to stabilize parameter updates and prevent gradients from disappearing as the network deepens. Finally, the model was trained and validated using the real prostate dataset of 180 patients with four cross-validations. The proposed model achieves 95% HD, 86.82%, 93.90%, 94.11%, 93.8%, 7.84% for prostate, 79.2%, 89.51%, 88.43%, 89.31%, 8.39% for lesion area in segmentation in terms of IOU, Dice score, accuracy, and sensitivity. Compared to the state-of-the-art models FCN, U-Net, U-Net++ and ResU-Net, the segmentation model shows more promising results. With an outstanding achievement in automated segmentation of prostate and lesion regions, the presented model highlights the ability of the novel deep convolutional neural network to facilitate clinical disease intervention and management.

Keywords

• Dense block
• magnetic resonance imaging
• convolution neural network
• attention mechanism
• CRF-RNN