Deep Segmentation-Emendation Model for Gland Instance Segmentation

Accurate and automated gland instance segmentation on histology microscopy images can assist pathologists to diagnose the malignancy degree of colorectal adenocarcinoma. To address this problem, many deep convolutional neural network (DCNN) based methods have been proposed, most of which aim to generate better segmentation by improving the model structure and loss function. Few of them, however, focus on further emendating the inferred predictions, thus missing a chance to refine the obtained segmentation results. In this paper, we propose the deep segmentation-emendation (DSE) model for gland instance segmentation. This model consists of a segmentation network (Seg-Net) and an emendation network (Eme-Net). The Seg-Net is dedicated to generating segmentation results, and the Eme-Net learns to predict the inconsistency between the ground truth and the segmentation results generated by Seg-Net. The predictions made by Eme-Net can in turn be used to refine the segmentation result. We evaluated our DSE model against five recent deep learning models on the 2015 MICCAI Gland Segmentation challenge (GlaS) dataset and against two deep learning models on the colorectal adenocarcinoma (CRAG) dataset. Our results indicate that using Eme-Net results in significant improvement in segmentation accuracy, and the proposed DSE model is able to substantially outperform all the rest models in gland instance segmentation on both datasets.

[1]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[2]  Zhe Chen,et al.  Progressive LiDAR adaptation for road detection , 2019, IEEE/CAA Journal of Automatica Sinica.

[3]  Hao Chen,et al.  DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Yang Li,et al.  Gland Instance Segmentation Using Deep Multichannel Neural Networks , 2016, IEEE Transactions on Biomedical Engineering.

[5]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[6]  David B. A. Epstein,et al.  Glandular Morphometrics for Objective Grading of Colorectal Adenocarcinoma Histology Images , 2017, Scientific Reports.

[7]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[8]  Wendy Frankel,et al.  Protocol for the examination of specimens from patients with primary carcinomas of the colon and rectum. , 2008, Archives of pathology & laboratory medicine.

[9]  Hao Chen,et al.  MILD‐Net: Minimal information loss dilated network for gland instance segmentation in colon histology images , 2018, Medical Image Anal..

[10]  Hao Chen,et al.  Gland segmentation in colon histology images: The glas challenge contest , 2016, Medical Image Anal..

[11]  Xin Yang,et al.  A Deep Model with Shape-Preserving Loss for Gland Instance Segmentation , 2018, MICCAI.

[12]  Hanlin L. Wang,et al.  Colorectal carcinoma: Pathologic aspects. , 2012, Journal of gastrointestinal oncology.