The Library

Self-path : self-supervision for classification of pathology images with limited annotations

Tools

Koohbanani, Navid Alemi, Unnikrishnan, Balagopal, Khurram, Syed Ali, Krishnaswamy, Pavitra and Rajpoot, Nasir M. (Nasir Mahmood) (2021) Self-path : self-supervision for classification of pathology images with limited annotations. IEEE Transactions on Medical Imaging, 40 (10). pp. 2845-2856. doi:10.1109/TMI.2021.3056023 ISSN 0278-0062.

Preview

PDF
WRAP-Self-path-self-supervision-classification-pathology-images-limited-annotations-Rajpoot-2021.pdf - Accepted Version - Requires a PDF viewer.
Download (2993Kb) | Preview

Official URL: http://dx.doi.org/10.1109/TMI.2021.3056023

Request Changes to record.

Abstract

While high-resolution pathology images lend themselves well to ‘data hungry’ deep learning algorithms, obtaining exhaustive annotations on these images for learning is a major challenge. In this paper, we propose a self-supervised convolutional neural network (CNN) framework to leverage unlabeled data for learning generalizable and domain invariant representations in pathology images. Our proposed framework, termed as Self-Path, employs multi-task learning where the main task is tissue classification and pretext tasks are a variety of self-supervised tasks with labels inherent to the input images. We introduce novel pathology-specific self-supervision tasks that leverage contextual, multi-resolution and semantic features in pathology images for semi-supervised learning and domain adaptation. We investigate the effectiveness of Self-Path on 3 different pathology datasets. Our results show that Self-Path with the pathology-specific pretext tasks achieves state-of-the-art performance for semi-supervised learning when small amounts of labeled data are available. Further, we show that Self-Path improves domain adaptation for histopathology image classification when there is no labeled data available for the target domain. This approach can potentially be employed for other applications in computational pathology, where annotation budget is often limited or large amount of unlabeled image data is available.

Item Type:

Journal Article

Subjects:

Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
R Medicine > RB Pathology
R Medicine > RC Internal medicine

Divisions:

Faculty of Science, Engineering and Medicine > Science > Computer Science

Library of Congress Subject Headings (LCSH):

Pathology -- Data processing, Diagnostic imaging -- Digital techniques, Neural networks (Computer science)

Journal or Publication Title:

IEEE Transactions on Medical Imaging

Publisher:

IEEE

ISSN:

0278-0062

Official Date:

October 2021

Dates:

Date	Event
October 2021	Published
1 February 2021	Available
16 January 2021	Accepted

Volume:

Number:

Page Range:

pp. 2845-2856

DOI:

10.1109/TMI.2021.3056023

Status:

Peer Reviewed

Publication Status:

Published

Reuse Statement (publisher, data, author rights):

© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Access rights to Published version:

Restricted or Subscription Access

Date of first compliant deposit:

1 February 2021

Date of first compliant Open Access:

1 February 2021

RIOXX Funder/Project Grant:

Project/Grant ID	RIOXX Funder Name	Funder ID
UNSPECIFIED	Alan Turing Institute	http://dx.doi.org/10.13039/100012338
MR/P015476/1	[MRC] Medical Research Council	http://dx.doi.org/10.13039/501100000265
UNSPECIFIED	UK Research and Innovation	http://dx.doi.org/10.13039/100014013