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

Adaptable image quality assessment using meta-reinforcement learning of task amenability

Saeed, SU; Fu, Y; Stavrinides, V; Baum, ZMC; Yang, Q; Rusu, M; Fan, RE; ... Hu, Y; + view all (2021) Adaptable image quality assessment using meta-reinforcement learning of task amenability. In: Simplifying Medical Ultrasound. (pp. pp. 191-201). Springer: Cham, Switzerland. Green open access

[thumbnail of 2108.04359v1.pdf] Text
2108.04359v1.pdf - Accepted version
Access restricted to UCL open access staff until 14 April 2022.

Download (1MB)

Abstract

The performance of many medical image analysis tasks are strongly associated with image data quality. When developing modern deep learning algorithms, rather than relying on subjective (human-based) image quality assessment (IQA), task amenability potentially provides an objective measure of task-specific image quality. To predict task amenability, an IQA agent is trained using reinforcement learning (RL) with a simultaneously optimised task predictor, such as a classification or segmentation neural network. In this work, we develop transfer learning or adaptation strategies to increase the adaptability of both the IQA agent and the task predictor so that they are less dependent on high-quality, expert-labelled training data. The proposed transfer learning strategy re-formulates the original RL problem for task amenability in a meta-reinforcement learning (meta-RL) framework. The resulting algorithm facilitates efficient adaptation of the agent to different definitions of image quality, each with its own Markov decision process environment including different images, labels and an adaptable task predictor. Our work demonstrates that the IQA agents pre-trained on non-expert task labels can be adapted to predict task amenability as defined by expert task labels, using only a small set of expert labels. Using 6644 clinical ultrasound images from 249 prostate cancer patients, our results for image classification and segmentation tasks show that the proposed IQA method can be adapted using data with as few as respective 19.7 % % and 29.6 % % expert-reviewed consensus labels and still achieve comparable IQA and task performance, which would otherwise require a training dataset with 100 % % expert labels.

Type: Proceedings paper
Title: Adaptable image quality assessment using meta-reinforcement learning of task amenability
Event: International Workshop on Advances in Simplifying Medical Ultrasound
ISBN-13: 978-3-030-87582-4
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-030-87583-1_19
Publisher version: https://doi.org/10.1007/978-3-030-87583-1_19
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.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences > Div of Surgery and Interventional Sci
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences > Div of Surgery and Interventional Sci > Department of Targeted Intervention
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
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10135065
Downloads since deposit
0Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item