Home Publications Research Grants Inventions & Patents Awards Additional Research Activities Faculties & Institutions Research Areas

Direct head-to-head comparison of convolutional long short-term memory and transformer networks for artificial Intelligence-based quantification of atherosclerotic plaque and stenosis from coronary CT angiography

Manral N, Lin A, Park C, McElhinney P, Killekar A, Matsumoto H, Kwiecinski J, Pieszko K, Razipour A, Grodecki K, Doris M, Kwan AC, Han D, Kuronuma K, Tomasino GF, Tzolos E, Shanbhag A, Göller M, Marwan M, Cadet S, Achenbach S, Nicholls SJ, Wong DT, Berman DS, Dweck M, Newby DE, Williams MC, Slomka PJ, Dey D (2023)

---

Publication Type: Conference contribution

Publication year: 2023

Journal

Publisher: SPIE

Book Volume: 12464

Conference Proceedings Title: Progress in Biomedical Optics and Imaging - Proceedings of SPIE

Event location: San Diego, CA

ISBN: 9781510660335

DOI: 10.1117/12.2655556

Abstract

Background: Coronary computed tomography angiography (CCTA) enables non-invasive assessment of luminal stenosis and coronary atherosclerotic plaque. We aimed to directly compare the performance of 2 novel deep learning networks—convolutional long short-term memory and transformer network—for artificial intelligence-based quantification of plaque volume and stenosis severity from CCTA. Methods: This was an international multicenter study of patients undergoing CCTA at 11 sites. The deep learning (DL) convolutional neural networks were trained to segment coronary plaque in 921 patients (5,045 lesions). The training dataset was further split temporally into training (80%) and internal validation (20%) datasets. The primary DL architecture was a hierarchical convolutional long short- term memory (ConvLSTM) network. This was compared against a TransUNet network, which combines the abilities of Vision Transformer with U-Net, enabling the capture of in-depth localization information while modeling long-range dependencies. Following training and internal validation, the both DL networks were applied to an external validation cohort of 162 patients (1,468 lesions) from the SCOT-HEART trial. Results: In the external validation cohort, agreement between DL and expert reader measurements was stronger when using the ConvLSTM network than with TransUNet, for both per-lesion total plaque volume (ICC 0·953 vs 0.830) and percent diameter stenosis (ICC 0·882 vs 0.735; both p<0.001). The ConvLSTM network showed higher per-cross-section overlap with expert reader segmentations (as measured by the Dice coefficient) compared to TransUnet, for vessel wall (0.947 vs 0.946), lumen (0.93 vs 0.92), and calcified plaque (0.87 vs 0.86; p<0.0001 for all), with similar execution times. Conclusions: In a direct comparison with external validation, the ConvLSTM network yielded higher agreement with expert readers for quantification of total plaque volume and stenosis severity compared to TransUnet, with faster execution times.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Manral, N., Lin, A., Park, C., McElhinney, P., Killekar, A., Matsumoto, H.,... Dey, D. (2023). Direct head-to-head comparison of convolutional long short-term memory and transformer networks for artificial Intelligence-based quantification of atherosclerotic plaque and stenosis from coronary CT angiography. In Olivier Colliot, Ivana Isgum (Eds.), Progress in Biomedical Optics and Imaging - Proceedings of SPIE. San Diego, CA, US: SPIE.

MLA:

Manral, Nipun, et al. "Direct head-to-head comparison of convolutional long short-term memory and transformer networks for artificial Intelligence-based quantification of atherosclerotic plaque and stenosis from coronary CT angiography." Proceedings of the Medical Imaging 2023: Image Processing, San Diego, CA Ed. Olivier Colliot, Ivana Isgum, SPIE, 2023.

BibTeX: Download