Image quality assessment by overlapping task-specific and task-agnostic measures: application to prostate multiparametric MR images for cancer segmentation

Shaheer U. SaeedUniversity College London, Wen YanUniversity College London, Yunguan FuUniversity College London
, Francesco GigantiUniversity College London, Qianye YangUniversity College London, Zachary M. C. BaumUniversity College London, Mirabela RusuStanford University, Richard E. FanStanford University, Geoffrey A. SonnStanford University, Mark EmbertonUniversity College London, Dean C. BarrattUniversity College London, Yipeng HuUniversity College London
IPMI 2021 special issue
Publication date: 2022/02/22
PDF · arXiv · Code · Video


Image quality assessment (IQA) in medical imaging can be used to ensure that downstream clinical tasks can be reliably performed. Quantifying the impact of an image on the specific target tasks, also named as task amenability, is needed. A task-specific IQA has recently been proposed to learn an image-amenability-predicting controller simultaneously with a target task predictor. This allows for the trained IQA controller to measure the impact an image has on the target task performance, when this task is performed using the predictor, e.g. segmentation and classification neural networks in modern clinical applications. In this work, we propose an extension to this task-specific IQA approach, by adding a task-agnostic IQA based on auto-encoding as the target task. Analysing the intersection between low-quality images, deemed by both the task-specific and task-agnostic IQA, may help to differentiate the underpinning factors that caused the poor target task performance. For example, common imaging artefacts may not adversely affect the target task, which would lead to a low task-agnostic quality and a high task-specific quality, whilst individual cases considered clinically challenging, which can not be improved by better imaging equipment or protocols, is likely to result in a high task-agnostic quality but a low task-specific quality. We first describe a flexible reward shaping strategy which allows for the adjustment of weighting between task-agnostic and task-specific quality scoring. Furthermore, we evaluate the proposed reinforcement learning algorithm, using a clinically challenging target task of prostate tumour segmentation on multiparametric magnetic resonance (mpMR) images. Based on experimental results using mpMR images from 850 patients, it was found that a) The task-agnostic IQA may identify artefacts, but with limited impact on the accuracy of cancer segmentation networks. A Dice score of 0.367±0.017 was obtained after rejecting 10% of low quality images, compared to 0.354±0.016 from a non-selective baseline; b} The task-specific IQA alone improved the performance to 0.415±0.020, at the same rejection ratio. However, this system indeed rejected both images that impact task performance due to imaging defects and due to being clinically challenging; and c) The proposed reward shaping strategy, when the task-agnostic and task-specific IQA are weighted appropriately, successfully identified samples that need re-acquisition due to defected imaging process, as opposed to clinically challenging cases due to low contrast in pathological tissues or other equivocacy in radiological presentation.
Our code is available at


reinforcement learning · meta-learning · image quality assessment · reward shaping · task amenability

Bibtex @article{melba:2022:004:saeed, title = "Image quality assessment by overlapping task-specific and task-agnostic measures: application to prostate multiparametric MR images for cancer segmentation", authors = "Saeed, Shaheer U. and Yan, Wen and Fu, Yunguan and Giganti, Francesco and Yang, Qianye and Baum, Zachary M. C. and Rusu, Mirabela and Fan, Richard E. and Sonn, Geoffrey A. and Emberton, Mark and Barratt, Dean C. and Hu, Yipeng", journal = "Machine Learning for Biomedical Imaging", volume = "1", issue = "IPMI 2021 special issue", year = "2022" }

2022:004 cover