Hierarchical Nonlocal Residual Networks for Image Quality Assessment of Pediatric Diffusion MRI With Limited and Noisy Annotations

• Published in: IEEE transactions on medical imaging Vol. 39; no. 11; pp. 3691 - 3702
• Main Authors: Liu, Siyuan, Thung, Kim-Han, Lin, Weili, Shen, Dinggang, Yap, Pew-Thian
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.11.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Agglomerates; Annotations; Child; Data models; Deep learning; Diffusion Magnetic Resonance Imaging; Diffusion rate; Feature extraction; hierarchical nonlocal residual networks; Humans; Image Processing, Computer-Assisted; Image quality; Image quality assessment; Iterative methods; Magnetic resonance imaging; Noise measurement; Pediatrics; Quality assessment; Quality control; Residual neural networks; self-training; Semi-supervised learning; Semisupervised learning; Training
• ISSN: 0278-0062; 1558-254X; 1558-254X
• DOI: 10.1109/TMI.2020.3002708

Fast and automated image quality assessment (IQA) of diffusion MR images is crucial for making timely decisions for rescans. However, learning a model for this task is challenging as the number of annotated data is limited and the annotation labels might not always be correct. As a remedy, we will introduce in this paper an automatic image quality assessment (IQA) method based on hierarchical non-local residual networks for pediatric diffusion MR images. Our IQA is performed in three sequential stages, i.e., 1) slice-wise IQA , where a nonlocal residual network is first pre-trained to annotate each slice with an initial quality rating (i.e., pass/questionable/fail), which is subsequently refined via iterative semi-supervised learning and slice self-training; 2) volume-wise IQA , which agglomerates the features extracted from the slices of a volume, and uses a nonlocal network to annotate the quality rating for each volume via iterative volume self-training; and 3) subject-wise IQA , which ensembles the volumetric IQA results to determine the overall image quality pertaining to a subject. Experimental results demonstrate that our method, trained using only samples of modest size, exhibits great generalizability, and is capable of conducting rapid hierarchical IQA with near-perfect accuracy.