Poudel, Pranav; Thapa, Shrawan Kumar; Regmi, Sudarshan; Bhattarai, Binod; Stoyanov, Danail; (2024) Task-Aware Active Learning for Endoscopic Polyp Segmentation. In: Bhattarai, B and Ali, S and Rau, A and Caramalau, R and Nguyen, A and Gyawali, P and Namburete, A and Stoyanov, D, (eds.) Data Engineering in Medical Imaging (DEMI 2024). (pp. pp. 155-165). Springer, Cham: Cham, Switzerland.

Text 978-3-031-73748-0_16 Binod.pdf - Accepted Version Access restricted to UCL open access staff until 26 October 2025. Download (664kB)

Abstract

Semantic segmentation of polyps is one of the most important research problems in endoscopic image analysis. One of the main obstacles to researching such a problem is the lack of annotated data. Endoscopic annotations necessitate the specialist knowledge of expert endoscopists, and hence the difficulty of organizing arises along with tremendous costs in time and budget. To address this problem, we investigate an active learning paradigm to reduce the requirement of massive labelled training examples by selecting the most discriminative and diverse unlabeled examples for the task taken into consideration. To this end, we propose a task-aware active learning pipeline that considers not only the uncertainty that the current task model exhibits for a given unlabelled example but also the diversity in the composition of the acquired pool in the feature space of the model. We compare our method with the competitive baselines on two publicly available polyps segmentation benchmark datasets. We observe a significant performance improvement over the compared baselines from the experimental results. The code and implementation details are available at: https://github.com/bhattarailab/endo-active-learn

Download activity - last month

Export as JSONCSVXML

Download activity - last 12 months

Export as JSONCSVXML

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item