|
1
|
Jávorszky N, Homonnay B, Gerstenblith G, Bluemke D, Kiss P, Török M, Celentano D, Lai H, Lai S, Kolossváry M. Deep learning-based atherosclerotic coronary plaque segmentation on coronary CT angiography. Eur Radiol 2022; 32:7217-7226. [PMID: 35524783 DOI: 10.1007/s00330-022-08801-8] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2022] [Revised: 03/31/2022] [Accepted: 04/03/2022] [Indexed: 12/14/2022]
Abstract
OBJECTIVES Volumetric evaluation of coronary artery disease (CAD) allows better prediction of cardiac events. However, CAD segmentation is labor intensive. Our objective was to create an open-source deep learning (DL) model to segment coronary plaques on coronary CT angiography (CCTA). METHODS Three hundred eight individuals' 894 CCTA scans with 3035 manually segmented plaques by an expert reader (considered as ground truth) were used to train (186/308, 60%), validate (tune, 61/308, 20%), and test (61/308, 20%) a 3D U-net model. We also evaluated the model on an external test set of 50 individuals with vulnerable plaques acquired at a different site. Furthermore, we applied transfer learning on 77 individuals' data and re-evaluated the model's performance using intra-class correlation coefficient (ICC). RESULTS On the test set, DL outperformed the currently used minimum cost approach method to quantify total: ICC: 0.88 [CI: 0.85-0.91] vs. 0.63 [CI: 0.42-0.76], noncalcified: 0.84 [CI: 0.80-0.88] vs. 0.45 [CI: 0.26-0.59], calcified: 0.99 [CI: 0.98-0.99] vs. 0.96 [CI: 0.94-0.97], and low attenuation noncalcified: 0.25 [CI: 0.13-0.37] vs. -0.01 [CI: -0.13 to 0.11] plaque volumes. On the external dataset, substantial improvement was observed in DL model performance after transfer learning, total: 0.62 [CI: 0.01-0.84] vs. 0.94 [CI: 0.87-0.97], noncalcified: 0.54 [CI: -0.04 to 0.80] vs. 0.93 [CI: 0.86-0.96], calcified: 0.91 [CI:0.85-0.95] vs. 0.95 [CI: 0.91-0.97], and low attenuation noncalcified 0.48 [CI: 0.18-0.69] vs. 0.86 [CI: 0.76-0.92]. CONCLUSIONS Our open-source DL algorithm achieved excellent agreement with expert CAD segmentations. However, transfer learning may be required to achieve accurate segmentations in the case of different plaque characteristics or machinery. KEY POINTS • Deep learning 3D U-net model for coronary segmentation achieves comparable results with expert readers' volumetric plaque quantification. • Transfer learning may be needed to achieve similar results for other scanner and plaque characteristics. • The developed deep learning algorithm is open-source and may be implemented in any CT analysis software.
Collapse
Affiliation(s)
- Natasa Jávorszky
- MTA-SE Cardiovascular Imaging Research Group, Heart and Vascular Center, Semmelweis University, 68 Városmajor str., Budapest, 1122, Hungary
| | - Bálint Homonnay
- Hyperplane Szoftverfejlesző Ltd., 15/d Bartók Béla str., Budapest, 1114, Hungary
| | - Gary Gerstenblith
- Department of Medicine, Johns Hopkins University School of Medicine, 733 N Broadway, Baltimore, MD, 21205, USA
| | - David Bluemke
- University of Wisconsin School of Medicine and Public Health, 750 Highland Ave, Madison, WI, 53726, USA
| | - Péter Kiss
- Centre for Discrete Mathematics and its Applications, University of Warwick, 6 Lord Bhattacharyya Way, Coventry, CV4 7EZ, UK
| | - Mihály Török
- Lain Consulting Ltd., 2/c Kék Golyó str., Budapest, 1123, Hungary
| | - David Celentano
- Department of Epidemiology, Johns Hopkins University Bloomberg School of Public Health, 614 Wolfe N Wolfe St., Baltimore, MD, 21205, USA
| | - Hong Lai
- Department of Radiology, Johns Hopkins University School of Medicine, 601 N Caroline St, Baltimore, MD, 21205, USA.,Institute of Human Virology, University of Maryland School of Medicine, 725 West Lombard St, Baltimore, MD, 21201, USA
| | - Shenghan Lai
- Department of Medicine, Johns Hopkins University School of Medicine, 733 N Broadway, Baltimore, MD, 21205, USA. .,Department of Epidemiology, Johns Hopkins University Bloomberg School of Public Health, 614 Wolfe N Wolfe St., Baltimore, MD, 21205, USA. .,Department of Radiology, Johns Hopkins University School of Medicine, 601 N Caroline St, Baltimore, MD, 21205, USA. .,Institute of Human Virology, University of Maryland School of Medicine, 725 West Lombard St, Baltimore, MD, 21201, USA.
| | - Márton Kolossváry
- MTA-SE Cardiovascular Imaging Research Group, Heart and Vascular Center, Semmelweis University, 68 Városmajor str., Budapest, 1122, Hungary.,Department of Pathology, Johns Hopkins University School of Medicine, 600 N Wolfe St, Baltimore, MD, 21287, USA
| |
Collapse
|