The Library
MILD-Net : minimal information loss dilated network for gland instance segmentation in colon histology images
Tools
Graham, Simon, Chen, Hao, Dou, Qi, Heng, Pheng-Ann and Rajpoot, Nasir M. (Nasir Mahmood) (2018) MILD-Net : minimal information loss dilated network for gland instance segmentation in colon histology images. In: Medical Imaging with Deep Learning (MIDL), Amsterdam, 4-6 Jul 2018 (Unpublished)
PDF
WRAP-MILD-Net-minimal-information-loss-dilated-Graham-2018.pdf - Accepted Version Embargoed item. Restricted access to Repository staff only - Requires a PDF viewer. Download (59Mb) |
Official URL: https://openreview.net/pdf?id=rJgE13soM
Abstract
The analysis of glandular morphology within colon histopathology images is a crucial step in determining the stage 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, within pathological practice, a measure of uncertainty is essential for diagnostic decision making. For example, ambiguous areas may require further examination from numerous pathologists. 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 resolution maintenance 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, as part of MICCAI 2015, and on a second independent colorectal adenocarcinoma dataset.
Item Type: | Conference Item (Paper) | ||||||||
---|---|---|---|---|---|---|---|---|---|
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science Faculty of Science, Engineering and Medicine > Science > Mathematics |
||||||||
Publisher: | MIDL ; Elsevier | ||||||||
Official Date: | 7 June 2018 | ||||||||
Dates: |
|
||||||||
Status: | Peer Reviewed | ||||||||
Publication Status: | Unpublished | ||||||||
Access rights to Published version: | Open Access (Creative Commons) | ||||||||
Date of first compliant deposit: | 12 June 2018 | ||||||||
Conference Paper Type: | Paper | ||||||||
Title of Event: | Medical Imaging with Deep Learning (MIDL) | ||||||||
Type of Event: | Conference | ||||||||
Location of Event: | Amsterdam | ||||||||
Date(s) of Event: | 4-6 Jul 2018 | ||||||||
Related URLs: | |||||||||
Open Access Version: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |