EUVIMEDAtrasti EUVIMED
Open access · CC BY-NC-ND 4.0

Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography

Jeeone Park, Jihoon Kweon, Young In Kim, Inwook Back, Jihye Chae, Jae-Hyung Roh, Do-Yoon Kang, Pil Hyung Lee, Jung-Min Ahn, Soo-Jin Kang, Duk-Woo Park, Seung-Whan Lee and 4 more

Medical Physics · 2023

DOI: 10.1002/mp.16554 ↗

At a glance

Journal article in Medical Physics, 2023. Written by Jeeone Park and 15 co-authors. Institution: Department of Medical Science, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medi…. Major MEDLINE topics: Deep Learning. Cited 29 times so far (Crossref); 69 references. The full text is freely available (open access, CC BY-NC-ND 4.0).

SantraukaSubjectsBibliografiniai duomenysCiteRelated studies

Abstract (original language)

Background

Invasive coronary angiography (ICA) is a primary imaging modality that visualizes the lumen area of coronary arteries for diagnosis and interventional guidance. In the current practice of quantitative coronary analysis (QCA), semi‐automatic segmentation tools require labor‐intensive and time‐consuming manual correction, limiting their application in the catheterization room.

Purpose

This study aims to propose rank‐based selective ensemble methods that improve the segmentation performance and reduce morphological errors that limit fully automated quantification of coronary artery using deep‐learning segmentation of ICA.

Methods

Two selective ensemble methods proposed in this work integrated the weighted ensemble approach with per‐image quality estimation. The segmentation outcomes from five base models with different loss functions were ranked either by mask morphology or estimated dice similarity coefficient (DSC). The final output was determined by imposing different weights according to the ranks. The ranking criteria based on mask morphology were formulated from empirical insight to avoid frequent types of segmentation errors (MSEN), while the estimation of DSCs was performed by comparing the pseudo‐ground truth generated from a meta‐learner (ESEN). Five‐fold cross‐validation was performed with the internal dataset of 7426 coronary angiograms from 2924 patients, and prediction model was externally validated with 556 images of 226 patients.

Results

The selective ensemble methods improved the segmentation performance with DSCs up to 93.07% and provided a better delineation of coronary lesion with local DSCs of up to 93.93%, outperforming all individual models. Proposed methods also minimized the chances of mask disconnection in the most narrowed regions to 2.10%. The robustness of the proposed methods was also evident in the external validation. Inference time for major vessel segmentation was approximately one‐sixth of a second.

Conclusion

Proposed methods successfully reduced morphological errors in the predicted masks and were able to enhance the robustness of the automatic segmentation. The results suggest better applicability of real‐time QCA‐based diagnostic methods in routine clinical settings.

Subjects

MeSH terms (MEDLINE)

Deep LearningHumansCoronary AngiographyHeartCoronary VesselsImage Processing, Computer-Assisted

Author keywords

invasive coronary angiographymajor vessel segmentationweighted ensemble method

Authors and institutions

  • Department of Medical Science, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea.
  • Department of Convergence Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, South Korea.
  • Division of Cardiology, Department of Internal Medicine, Medical Center, University of Ulsan College of Medicine, Asan, Seoul, South Korea.
  • Department of Cardiology, Chungnam National University Sejong Hospital, Chungnam National University School of Medicine, Daejeon, South Korea.

Cite

APA

Park, J., Kweon, J., Kim, Y. I., Back, I., Chae, J., Roh, J. H., Kang, D. Y., Lee, P. H., Ahn, J. M., Kang, S. J., Park, D. W., Lee, S. W., Lee, C. W., Park, S. W., Park, S. J., & Kim, Y. H. (2023). Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography. Medical Physics. https://doi.org/10.1002/mp.16554

Vancouver

Park J, Kweon J, Kim YI, Back I, Chae J, Roh JH, et al. Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography. Medical Physics. 2023. doi:10.1002/mp.16554

BibTeX
@article{Park2023,
  author = {Park, Jeeone and Kweon, Jihoon and Kim, Young In and Back, Inwook and Chae, Jihye and Roh, Jae-Hyung and Kang, Do-Yoon and Lee, Pil Hyung and Ahn, Jung-Min and Kang, Soo-Jin and Park, Duk-Woo and Lee, Seung-Whan and Lee, Cheol Whan and Park, Seong-Wook and Park, Seung-Jung and Kim, Young-Hak},
  title = {Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography},
  journal = {Medical Physics},
  year = {2023},
  doi = {10.1002/mp.16554}
}
Start for free →