Saeed, Shaheer U;
Fu, Yunguan;
Stavrinides, Vasilis;
Baum, Zachary MC;
Yang, Qianye;
Rusu, Mirabela;
Fan, Richard E;
... Hu, Yipeng; + view all
(2022)
Image quality assessment for machine learning tasks using meta-reinforcement learning.
Medical Image Analysis
, 78
, Article 102427. 10.1016/j.media.2022.102427.
Preview |
Text
Saeed_1-s2.0-S1361841522000780-main.pdf Download (2MB) | Preview |
Abstract
In this paper, we consider image quality assessment (IQA) as a measure of how images are amenable with respect to a given downstream task, or task amenability. When the task is performed using machine learning algorithms, such as a neural-network-based task predictor for image classification or segmentation, the performance of the task predictor provides an objective estimate of task amenability. In this work, we use an IQA controller to predict the task amenability which, itself being parameterised by neural networks, can be trained simultaneously with the task predictor. We further develop a meta-reinforcement learning framework to improve the adaptability for both IQA controllers and task predictors, such that they can be fine-tuned efficiently on new datasets or meta-tasks. We demonstrate the efficacy of the proposed task-specific, adaptable IQA approach, using two clinical applications for ultrasound-guided prostate intervention and pneumonia detection on X-ray images.
| Type: | Article |
|---|---|
| Title: | Image quality assessment for machine learning tasks using meta-reinforcement learning |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1016/j.media.2022.102427 |
| Publisher version: | https://doi.org/10.1016/j.media.2022.102427 |
| Language: | English |
| Additional information: | © 2022 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/) |
| Keywords: | Meta-reinforcement learning; Image quality assessment; Task amenability; Meta-learning |
| UCL classification: | 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 Med Phys and Biomedical Eng UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10145876 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
