A Level Set Method for Gland Segmentation

Chen Wang, Hong Bu, Ji Bao, Chunming Li; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 113-121

Histopathology plays a role as the gold standard in clinic for disease diagnosis. The identification and segmentation of histological structures are the prerequisite to disease diagnosis. With the advent of digital pathology, researchers' attention is attracted by the analysis of digital pathology images. In order to relieve the workload on pathologists, a robust segmentation method is needed in clinic for computer-assisted diagnosis. In this paper, we propose a level set framework to achieve gland image segmentation. The input image is divided into two parts, which contain glands with lumens and glands without lumens, respectively. Our experiments are performed on the clinical datasets of West China Hospital, Sichuan University. The experimental results show that our method can deal with glands without lumens, thus can obtain a better performance.