The Library
Dense steerable filter CNNs for exploiting rotational symmetry in histology images
Tools
Graham, Simon, Epstein, D. B. A. and Rajpoot, Nasir M. (Nasir Mahmood) (2020) Dense steerable filter CNNs for exploiting rotational symmetry in histology images. IEEE Transactions on Medical Imaging, 39 (12). pp. 4124-4136. doi:10.1109/TMI.2020.3013246 ISSN 0278-0062.
|
PDF
WRAP-dense-steerable-filter-CNNs-exploiting-rotational-symmetry-histology-images-Rajpoot-2020.pdf - Accepted Version - Requires a PDF viewer. Download (8Mb) | Preview |
Official URL: http://dx.doi.org/10.1109/TMI.2020.3013246
Abstract
Histology images are inherently symmetric under rotation, where each orientation is equally as likely to appear. However, this rotational symmetry is not widely utilised as prior knowledge in modern Convolutional Neural Networks (CNNs), resulting in data hungry models that learn independent features at each orientation. Allowing CNNs to be rotation-equivariant removes the necessity to learn this set of transformations from the data and instead frees up model capacity, allowing more discriminative features to be learned. This reduction in the number of required parameters also reduces the risk of overfitting. In this paper, we propose Dense Steerable Filter CNNs (DSF-CNNs) that use group convolutions with multiple rotated copies of each filter in a densely connected framework. Each filter is defined as a linear combination of steerable basis filters, enabling exact rotation and decreasing the number of trainable parameters compared to standard filters. We also provide the first in-depth comparison of different rotation-equivariant CNNs for histology image analysis and demonstrate the advantage of encoding rotational symmetry into modern architectures. We show that DSF-CNNs achieve state-of-the-art performance, with significantly fewer parameters, when applied to three different tasks in the area of computational pathology: breast tumour classification, colon gland segmentation and multi-tissue nuclear segmentation.
Item Type: | Journal Article | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
Subjects: | Q Science > QM Human anatomy | |||||||||
Divisions: | Faculty of Science, Engineering and Medicine > Science > Computer Science Faculty of Science, Engineering and Medicine > Science > Mathematics |
|||||||||
Library of Congress Subject Headings (LCSH): | Histology, Pathological -- Computer programs, Image segmentation, Neural networks (Computer science), Machine learning, Pathology -- Data processing| | |||||||||
Journal or Publication Title: | IEEE Transactions on Medical Imaging | |||||||||
Publisher: | IEEE | |||||||||
ISSN: | 0278-0062 | |||||||||
Official Date: | December 2020 | |||||||||
Dates: |
|
|||||||||
Volume: | 39 | |||||||||
Number: | 12 | |||||||||
Page Range: | pp. 4124-4136 | |||||||||
DOI: | 10.1109/TMI.2020.3013246 | |||||||||
Status: | Peer Reviewed | |||||||||
Publication Status: | Published | |||||||||
Reuse Statement (publisher, data, author rights): | © 2020 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: | 5 August 2020 | |||||||||
Date of first compliant Open Access: | 6 August 2020 | |||||||||
RIOXX Funder/Project Grant: |
|
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |
Downloads
Downloads per month over past year