In:
Machine Learning for Biomedical Imaging, Machine Learning for Biomedical Imaging, Vol. 1, No. IPMI 2021 ( 2022-02-22), p. 1-29
Abstract:
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 〈 em 〉 task-specific 〈 /em 〉 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 〈 em 〉 task-agnostic 〈 /em 〉 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 〈 em 〉 a 〈 /em 〉 ) 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; 〈 em 〉 b 〈 /em 〉 } 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 〈 em 〉 c 〈 /em 〉 ) 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. 〈 br 〉 Our code is available at https://github.com/s-sd/task-amenability/tree/v1
Type of Medium:
Online Resource
ISSN:
2766-905X
DOI:
10.59275/j.melba.2022-a1cc
Language:
English
Publisher:
Machine Learning for Biomedical Imaging
Publication Date:
2022
Bookmarklink