View in EDS

Context-Aware Convolutional Neural Network for Grading of Colorectal Cancer Histology Images.

Saved in:
Bibliographic Details
Title: Context-Aware Convolutional Neural Network for Grading of Colorectal Cancer Histology Images.
Authors: Shaban, Muhammad1 (AUTHOR) m.shaban@warwick.ac.uk, Awan, Ruqayya1 (AUTHOR) r.awan.1@warwick.ac.uk, Fraz, Muhammad Moazam1 (AUTHOR) ayesha.azam@warwick.ac.uk, Azam, Ayesha1 (AUTHOR) n.m.rajpoot@warwick.ac.uk, Tsang, Yee-Wah2 (AUTHOR) r.awan.1@warwick.ac.uk, Snead, David2 (AUTHOR), Rajpoot, Nasir M.1 (AUTHOR) n.m.rajpoot@warwick.ac.uk
Source: IEEE Transactions on Medical Imaging. Jul2020, Vol. 39 Issue 7, p2395-2405. 11p.
Subjects: Convolutional neural networks, Image segmentation, Deep learning, Tumor grading, Colorectal cancer
Abstract: Digital histology images are amenable to the application of convolutional neural networks (CNNs) for analysis due to the sheer size of pixel data present in them. CNNs are generally used for representation learning from small image patches (e.g. $224\times 224$) extracted from digital histology images due to computational and memory constraints. However, this approach does not incorporate high-resolution contextual information in histology images. We propose a novel way to incorporate a larger context by a context-aware neural network based on images with a dimension of $1792\times 1792$ pixels. The proposed framework first encodes the local representation of a histology image into high dimensional features then aggregates the features by considering their spatial organization to make a final prediction. We evaluated the proposed method on two colorectal cancer datasets for the task of cancer grading. Our method outperformed the traditional patch-based approaches, problem-specific methods, and existing context-based methods. We also presented a comprehensive analysis of different variants of the proposed method. [ABSTRACT FROM AUTHOR]
Copyright of IEEE Transactions on Medical Imaging is the property of IEEE and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:Digital histology images are amenable to the application of convolutional neural networks (CNNs) for analysis due to the sheer size of pixel data present in them. CNNs are generally used for representation learning from small image patches (e.g. $224\times 224$) extracted from digital histology images due to computational and memory constraints. However, this approach does not incorporate high-resolution contextual information in histology images. We propose a novel way to incorporate a larger context by a context-aware neural network based on images with a dimension of $1792\times 1792$ pixels. The proposed framework first encodes the local representation of a histology image into high dimensional features then aggregates the features by considering their spatial organization to make a final prediction. We evaluated the proposed method on two colorectal cancer datasets for the task of cancer grading. Our method outperformed the traditional patch-based approaches, problem-specific methods, and existing context-based methods. We also presented a comprehensive analysis of different variants of the proposed method. [ABSTRACT FROM AUTHOR]
ISSN:02780062
DOI:10.1109/TMI.2020.2971006