Comparative validation of AI and non-AI methods in MRI volumetry to diagnose Parkinsonian syndromes (vol 13, 3439, 2023)

作     者：Song, Joomee Hahm, Juyoung Lee, Jisoo Lim, Chae Yeon Chung, Myung Jin Youn, Jinyoung Cho, Jin Whan Ahn, Jong Hyeon Kim, Kyungsu 

作者机构：Department of Neurology and Neuroscience Center Samsung Medical Center Sungkyunkwan University School of Medicine Seoul Republic of Korea Medical AI Research Center Research Institute for Future Medicine Samsung Medical Center Seoul Republic of Korea Department of Biostatistics Columbia University New York NY USA Department of Electrical and Computer Engineering University of Maryland College Park MD USA Department of Medical Device Management and Research SAIHST Sungkyunkwan University Seoul Republic of Korea Department of Radiology Samsung Medical Center Sungkyunkwan University School of Medicine Seoul Republic of Korea Department of Data Convergence and Future Medicine Sungkyunkwan University School of Medicine Seoul Republic of Korea Department of Radiology Massachusetts General Brigham and Harvard Medical School Boston MA USA 

出 版 物：《SCIENTIFIC REPORTS》 (Sci. Rep.)

年 卷 期：2023年第13卷第1期

页      面：1-13页

核心收录：

基　　金：Samsung Medical Center, (SMX1210791) Ministry of Trade, Industry and Energy, MOTIE Ministry of Food and Drug Safety, MFDS, (20014111, 202011B08-02, KMDF_PR_20200901_0014-2021-02) Ministry of Food and Drug Safety, MFDS Ministry of Science, ICT and Future Planning, MSIP, (2021R1F1A106153511) Ministry of Science, ICT and Future Planning, MSIP Ministry of Health and Welfare, MOHW National Research Foundation of Korea, NRF 

摘      要：Automated segmentation and volumetry of brain magnetic resonance imaging (MRI) scans are essential for the diagnosis of Parkinson’s disease (PD) and Parkinson’s plus syndromes (P-plus). To enhance the diagnostic performance, we adopt deep learning (DL) models in brain MRI segmentation and compared their performance with the gold-standard non-DL method. We collected brain MRI scans of healthy controls (\(n=105\)) and patients with PD (\(n=105\)), multiple systemic atrophy (\(n=132\)), and progressive supranuclear palsy (\(n=69\)) at Samsung Medical Center from January 2017 to December 2020. Using the gold-standard non-DL model, FreeSurfer (FS), we segmented six brain structures: midbrain, pons, caudate, putamen, pallidum, and third ventricle, and considered them as annotated data for DL models, the representative convolutional neural network (CNN) and vision transformer (ViT)-based models. Dice scores and the area under the curve (AUC) for differentiating normal, PD, and P-plus cases were calculated to determine the measure to which FS performance can be reproduced as-is while increasing speed by the DL approaches. The segmentation times of CNN and ViT for the six brain structures per patient were 51.26 ± 2.50 and 1101.82 ± 22.31 s, respectively, being 14 to 300 times faster than FS (15,735 ± 1.07 s). Dice scores of both DL models were sufficiently high ( 0.85) so their AUCs for disease classification were not inferior to that of FS. For classification of normal vs. P-plus and PD vs. P-plus (except multiple systemic atrophy - Parkinsonian type) based on all brain parts, the DL models and FS showed AUCs above 0.8, demonstrating the clinical value of DL models in addition to FS. DL significantly reduces the analysis time without compromising the performance of brain segmentation and differential diagnosis. Our findings may contribute to the adoption of DL brain MRI segmentation in clinical settings and advance brain research.