Graham, Simon, Chen, Hao, Gamper, Jevgenij, Dou, Qi, Heng, Pheng-Ann, Snead, David, Tsang, Yee Wah and Rajpoot, Nasir M. (Nasir Mahmood) (2019) MILD-Net : Minimal information loss dilated network for gland instance segmentation in colon histology images. Medical Image Analysis, 52 . pp. 199-211. doi:10.1016/j.media.2018.12.001 ISSN 1361-8415.

Preview

PDF WRAP-MILD-Net-minimal-information-loss-dilated-histology-images-Rajpoot-2018.pdf - Accepted Version - Requires a PDF viewer. Available under License Creative Commons Attribution Non-commercial No Derivatives 4.0. Download (28Mb) | Preview

Request Changes to record.

Abstract

The analysis of glandular morphology within colon histopathology images is an important step in determining the grade of colon cancer. Despite the importance of this task, manual segmentation is laborious, time-consuming and can suffer from subjectivity among pathologists. The rise of computational pathology has led to the development of automated methods for gland segmentation that aim to overcome the challenges of manual segmentation. However, this task is non-trivial due to the large variability in glandular appearance and the difficulty in differentiating between certain glandular and non-glandular histological structures. Furthermore, a measure of uncertainty is essential for diagnostic decision making. To address these challenges, we propose a fully convolutional neural network that counters the loss of information caused by max-pooling by re-introducing the original image at multiple points within the network. We also use atrous spatial pyramid pooling with varying dilation rates for preserving the resolution and multi-level aggregation. To incorporate uncertainty, we introduce random transformations during test time for an enhanced segmentation result that simultaneously generates an uncertainty map, highlighting areas of ambiguity. We show that this map can be used to define a metric for disregarding predictions with high uncertainty. The proposed network achieves state-of-the-art performance on the GlaS challenge dataset and on a second independent colorectal adenocarcinoma dataset. In addition, we perform gland instance segmentation on whole-slide images from two further datasets to highlight the generalisability of our method. As an extension, we introduce MILD-Net for simultaneous gland and lumen segmentation, to increase the diagnostic power of the network.

Item Type:	Journal Article
Subjects:	R Medicine > RB Pathology R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer)
Divisions:	Faculty of Science, Engineering and Medicine > Science > Computer Science Faculty of Science, Engineering and Medicine > Science > Mathematics
Library of Congress Subject Headings (LCSH):	Colon (Anatomy) -- Cancer -- Diagnosis, Rectum -- Cancer -- Diagnosis, Adenocarcinoma, Histology, Pathological
Journal or Publication Title:	Medical Image Analysis
Publisher:	Elsevier Science BV
ISSN:	1361-8415
Official Date:	February 2019
Dates:	Date Event February 2019 Published 20 December 2018 Available 14 December 2018 Accepted
Volume:	52
Page Range:	pp. 199-211
DOI:	10.1016/j.media.2018.12.001
Status:	Peer Reviewed
Publication Status:	Published
Access rights to Published version:	Restricted or Subscription Access
Date of first compliant deposit:	25 January 2019
Date of first compliant Open Access:	20 December 2019
RIOXX Funder/Project Grant:	Project/Grant ID RIOXX Funder Name Funder ID UNSPECIFIED University of Warwick http://dx.doi.org/10.13039/501100000741 UNSPECIFIED Chinese University of Hong Kong http://dx.doi.org/10.13039/501100004853 UNSPECIFIED Innovation and Technology Commission http://dx.doi.org/10.13039/501100003452

Request changes or add full text files to a record

Repository staff actions (login required)

View Item

Downloads