Medical image segmentation is a key topic in image processing and computer vision. Existing literature mainly focuses on single-organ segmentation. However, since maximizing the concentration of radiotherapy drugs in the target area with protecting the surrounding organs is essential for making effective radiotherapy plan, multiorgan segmentation has won more and more attention. An improved Mask R-CNN (region-based convolutional neural network) model is proposed for multiorgan segmentation to aid esophageal radiation treatment. Due to the fact that organ boundaries may be fuzzy and organ shapes are various, original Mask R-CNN works well on natural image segmentation while leaves something to be desired on the multiorgan segmentation task. Addressing it, the advantages of this method are threefold: (1) a ROI (region of interest) generation method is presented in the RPN (region proposal network) which is able to utilize multiscale semantic features. (2) A prebackground classification subnetwork is integrated to the original mask generation branch to improve the precision of multiorgan segmentation. (3) 4341 CT images of 44 patients are collected and annotated to evaluate the proposed method. Additionally, extensive experiments on the collected dataset demonstrate that the proposed method can segment the heart, right lung, left lung, planning target volume (PTV), and clinical target volume (CTV) accurately and efficiently. Specifically, less than 5% of the cases were missed detection or false detection on the test set, which shows a great potential for real clinical usage.
LSI: Latent semantic inference for natural image segmentation
