Automated Brain Segmentation on Computed Tomographic Images Using Perceptual Loss Based Convolutional Neural Networks

被引:0
作者
Son, Won Jun [1 ]
Ahn, Sung Jun [2 ]
Lee, Ji Young [3 ]
Lee, Hyunyeol [1 ]
机构
[1] Kyungpook Natl Univ, Sch Elect & Elect Engn, 80 Daehak Ro, Daegu 41075, South Korea
[2] Yonsei Univ, Coll Med, Gangnam Severance Hosp, Dept Radiol, Seoul, South Korea
[3] Catholic Univ Korea, Seoul St Marys Hosp, Coll Med, Dept Radiol, 222 Banpo Daero, Seoul 06591, South Korea
关键词
Magnetic resonance imaging; Computed tomography; Brain segmentation; Deep learning; Perceptual loss; TISSUE SEGMENTATION; CT IMAGES;
D O I
10.13104/imri.2024.0023
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Purpose: This study aimed to develop a new convolutional neural network-based deep learning (DL) technique for automated brain tissue segmentation from computed tomographic (CT) scans and to evaluate its performance in comparison to magnetic resonance imaging (MRI)-derived segmentations. Materials and Methods: This multicenter retrospective study collected paired CT and MRI data from 199 healthy individuals across two institutions. The data were divided into a training set (n = 100) and an internal test set (n = 50) from one institution, with additional datasets (n = 49) from the second institution for external validation. Ground truth masks for gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) were generated from T1-weighted MR images. A U-Net-based DL model was trained for each of the three brain regions, with a perceptual loss computed from VGG19. Model performance was evaluated by calculating continuous Dice coefficient (cDice), intersection-over-union (IOU), and 95th percentile Hausdorff distance (HD95). Volumetric estimates from CT-based segmentations were compared with MRI-derived volumes using the coefficient of determination (R2), intraclass correlation coefficients (ICC), and Bland-Altman analysis. Results: The DL network trained with the perceptual loss showed superior performance, compared with that trained without the perceptual loss. In internal tests, evaluation scores (without perceptual loss vs. with perceptual loss) were: cDice = 0.717 vs. 0.765 and HD95 = 6.641 mm vs. 6.314 mm in GM; cDice = 0.730 vs. 0.767 and HD95 = 5.841 mm vs. 5.644 mm in WM; and cDice = 0.600 vs. 0.630 and HD95 = 5.641 mm vs. 5.362 mm in CSF, respectively. Volumetric analyses revealed strong agreement between MRI-derived ground truth and CT-based segmentations with R2 = 0.83/0.90 and 0.85/0.87, and ICC = 0.91/0.94 and 0.92/0.93 for GM and WM, respectively, in internal/external tests. Conclusion: The proposed DL method, enhanced with perceptual loss, improves brain tissue segmentation from CT images. This approach shows promise as an alternative to MRIbased segmentation.
引用
收藏
页码:193 / 201
页数:9
相关论文
共 26 条
[1]  
[Anonymous], Human Rights Council Working Group on the Universal Periodic Review Fourteenth session Geneva, 22 October-5 November 2012 'National report submitted in accordance with paragraph 5 of the annex to Human Rights Council resolution 16/21 Ghana' A/HRC/WG.6/14/GHA/1 10 August 2012 available at https://documents-ddsny.un.org/doc/UNDOC/GEN/G12/158/78/PDF/G1215878.pdf?OpenElement accessed 10 July 2020.
[2]  
Athinoula A, Martinos Center for Biomedical Imaging, Laboratory for Computational Neuroimaging. FreeSurfer
[3]   Specialized gray matter segmentation via a generative adversarial network: application on brain white matter hyperintensities classification [J].
Bawil, Mahdi Bashiri ;
Shamsi, Mousa ;
Bavil, Abolhassan Shakeri ;
Danishvar, Sebelan .
FRONTIERS IN NEUROSCIENCE, 2024, 18
[4]   Cerebral oxygen metabolism from MRI susceptibility [J].
Biondetti, Emma ;
Cho, Junghun ;
Lee, Hyunyeol .
NEUROIMAGE, 2023, 276
[5]   Fully Automated Segmentation of Head CT Neuroanatomy Using Deep Learning [J].
Cai, Jason C. ;
Akkus, Zeynettin ;
Philbrick, Kenneth A. ;
Boonrod, Arunnit ;
Hoodeshenas, Safa ;
Weston, Alexander D. ;
Rouzrokh, Pouria ;
Conte, Gian Marco ;
Zeinoddini, Atefeh ;
Vogelsang, David C. ;
Huang, Qiao ;
Erickson, Bradley J. .
RADIOLOGY-ARTIFICIAL INTELLIGENCE, 2020, 2 (05) :1-12
[6]  
Deepa V., 2015, Int Res J Eng Tech (IRJET), V2, P913
[7]  
Deng J, 2009, PROC CVPR IEEE, P248, DOI 10.1109/CVPRW.2009.5206848
[8]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[9]   Brain Segmentation From Computed Tomography of Healthy Aging and Geriatric Concussion at Variable Spatial Resolutions [J].
Irimia, Andrei ;
Maher, Alexander S. ;
Rostowsky, Kenneth A. ;
Chowdhury, Nahian F. ;
Hwang, Darryl H. ;
Law, E. Meng .
FRONTIERS IN NEUROINFORMATICS, 2019, 13
[10]   Perceptual Losses for Real-Time Style Transfer and Super-Resolution [J].
Johnson, Justin ;
Alahi, Alexandre ;
Li Fei-Fei .
COMPUTER VISION - ECCV 2016, PT II, 2016, 9906 :694-711