UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Hybrid Loss with Network Trimming for Disease Recognition in Gastrointestinal Endoscopy

He, Q; Bano, S; Stoyanov, D; Zuo, S; (2021) Hybrid Loss with Network Trimming for Disease Recognition in Gastrointestinal Endoscopy. In: attern Recognition. ICPR International Workshops and Challenges. (pp. pp. 299-306). Springer Nature: Cham, switzerland. Green open access

[thumbnail of EndoTect20_QiHe.pdf] Text
EndoTect20_QiHe.pdf - Accepted version
Access restricted to UCL open access staff until 22 February 2022.

Download (626kB)

Abstract

EndoTect Challenge 2020, which aims at the detection of gastrointestinal diseases and abnormalities, consists of three tasks including Detection, Efficient Detection and Segmentation in endoscopic images. Although pathologies belonging to different classes can be manually separated by experienced experts, however, existing classification models struggle to discriminate them due to low inter-class variability. As a result, the models’ convergence deteriorates. To this end, we propose a hybrid loss function to stabilise model training. For the detection and efficient detection tasks, we utilise ResNet-152 and MobileNetV3 architectures, respectively, along with the hybrid loss function. For the segmentation task, Cascade Mask R-CNN is investigated. In this paper, we report the architecture of our detection and segmentation models and the performance of our methods on HyperKvasir and EndoTect test dataset.

Type: Proceedings paper
Title: Hybrid Loss with Network Trimming for Disease Recognition in Gastrointestinal Endoscopy
Event: 25th International Conference on Pattern Recognition
Location: virtually in Milan, Italy
Dates: 10 January 2021 - 15 March 2021
ISBN-13: 978-3-030-68792-2
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-030-68793-9_22
Publisher version: https://doi.org/10.1007/978-3-030-68793-9_22
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.
Keywords: Endoscopy; Object detection; Polyp segmentation; Computer-assisted intervention
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10125161
Downloads since deposit
1Download
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item