TY - JOUR
T1 - Real-Time Quality Assessment of Pediatric MRI via Semi-Supervised Deep Nonlocal Residual Neural Networks
AU - Liu, Siyuan
AU - Thung, Kim Han
AU - Lin, Weili
AU - Yap, Pew Thian
AU - Shen, DInggang
N1 - Funding Information:
Manuscript received May 10, 2019; revised April 28, 2020; accepted April 29, 2020. Date of publication May 8, 2020; date of current version July 14, 2020. This work was supported in part by NIH under Grant AG053867, Grant EB006733, Grant MH117943, Grant MH104324, and Grant MH110274 and in part by the efforts of the UNC/UMN Baby Connec-tome Project Consortium. The associate editor coordinating the review of this manuscript and approving it for publication was Prof. Sos S. Agaian. (Corresponding authors: Pew-Thian Yap; Dinggang Shen.) Siyuan Liu, Kim-Han Thung, Weili Lin, and Pew-Thian Yap are with the Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 USA, and also with the Biomedical Research Imaging Center (BRIC), University of North Carolina at Chapel Hill, Chapel Hill, NC 27599 USA (e-mail: ptyap@med.unc.edu).
Publisher Copyright:
© 1992-2012 IEEE.
PY - 2020
Y1 - 2020
N2 - In this paper, we introduce an image quality assessment (IQA) method for pediatric T1- and T2-weighted MR images. IQA is first performed slice-wise using a nonlocal residual neural network (NR-Net) and then volume-wise by agglomerating the slice QA results using random forest. Our method requires only a small amount of quality-annotated images for training and is designed to be robust to annotation noise that might occur due to rater errors and the inevitable mix of good and bad slices in an image volume. Using a small set of quality-assessed images, we pre-train NR-Net to annotate each image slice with an initial quality rating (i.e., pass, questionable, fail), which we then refine by semi-supervised learning and iterative self-training. Experimental results demonstrate that our method, trained using only samples of modest size, exhibit great generalizability, capable of real-time (milliseconds per volume) large-scale IQA with near-perfect accuracy.
AB - In this paper, we introduce an image quality assessment (IQA) method for pediatric T1- and T2-weighted MR images. IQA is first performed slice-wise using a nonlocal residual neural network (NR-Net) and then volume-wise by agglomerating the slice QA results using random forest. Our method requires only a small amount of quality-annotated images for training and is designed to be robust to annotation noise that might occur due to rater errors and the inevitable mix of good and bad slices in an image volume. Using a small set of quality-assessed images, we pre-train NR-Net to annotate each image slice with an initial quality rating (i.e., pass, questionable, fail), which we then refine by semi-supervised learning and iterative self-training. Experimental results demonstrate that our method, trained using only samples of modest size, exhibit great generalizability, capable of real-time (milliseconds per volume) large-scale IQA with near-perfect accuracy.
KW - Image quality assessment
KW - nonlocal residual networks
KW - self-training
KW - semi-supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85088504206&partnerID=8YFLogxK
U2 - 10.1109/TIP.2020.2992079
DO - 10.1109/TIP.2020.2992079
M3 - Article
AN - SCOPUS:85088504206
SN - 1057-7149
VL - 29
SP - 7697
EP - 7706
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
M1 - 9090293
ER -