Brandao, P, Zisimopoulos, O, Mazomenos, E orcid.org/0000-0003-0357-5996 et al. (9 more authors) (2018) Towards a Computed-Aided Diagnosis System in Colonoscopy: Automatic Polyp Segmentation Using Convolution Neural Networks. Journal of Medical Robotics Research, 03 (02). 1840002. p. 1840002. ISSN 2424-905X
Abstract
Early diagnosis is essential for the successful treatment of bowel cancers including colorectal cancer (CRC), and capsule endoscopic imaging with robotic actuation can be a valuable diagnostic tool when combined with automated image analysis. We present a deep learning rooted detection and segmentation framework for recognizing lesions in colonoscopy and capsule endoscopy images. We restructure established convolution architectures, such as VGG and ResNets, by converting them into fully-connected convolution networks (FCNs), fine-tune them and study their capabilities for polyp segmentation and detection. We additionally use shape-from-shading (SfS) to recover depth and provide a richer representation of the tissue’s structure in colonoscopy images. Depth is incorporated into our network models as an additional input channel to the RGB information and we demonstrate that the resulting network yields improved performance. Our networks are tested on publicly available datasets and the most accurate segmentation model achieved a mean segmentation interception over union (IU) of 47.78% and 56.95% on the ETIS-Larib and CVC-Colon datasets, respectively. For polyp detection, the top performing models we propose surpass the current state-of-the-art with detection recalls superior to 90% for all datasets tested. To our knowledge, we present the first work to use FCNs for polyp segmentation in addition to proposing a novel combination of SfS and RGB that boosts performance.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | Electronic version of an article published as Journal of Medical Robotics Research, 03, 02, 2018, 1840002, www.doi.org/10.1142/s2424905x18400020 © World Scientific Publishing Company https://www.worldscientific.com/worldscinet/jmrr |
Keywords: | Convolutional neural networks; colonoscopy; computer-aided diagnosis |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Electronic & Electrical Engineering (Leeds) > Robotics, Autonomous Systems & Sensing (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 05 Mar 2020 14:01 |
Last Modified: | 04 Jul 2020 14:33 |
Status: | Published |
Publisher: | World Scientific Publishing Co Pte Ltd |
Identification Number: | 10.1142/s2424905x18400020 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:158057 |