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

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 i...