Vessel segmentation for X-ray coronary angiography using ensemble methods with deep learning and filter-based features

Zijun Gao; Lu Wang; Reza Soroushmehr; Alexander Wood; Jonathan Gryak; Brahmajee Nallamothu; Kayvan Najarian

doi:10.1186/s12880-022-00734-4

Vessel segmentation for X-ray coronary angiography using ensemble methods with deep learning and filter-based features

BMC Med Imaging. 2022 Jan 19;22(1):10. doi: 10.1186/s12880-022-00734-4.

Authors

Zijun Gao^#¹, Lu Wang^#², Reza Soroushmehr^{2

3

4}, Alexander Wood², Jonathan Gryak^{2

3}, Brahmajee Nallamothu^{5

6}, Kayvan Najarian^{2

3

7

8

4}

Affiliations

¹ Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, USA. zijung@umich.edu.
² Department of Computational Medicine and Bioinformatics, University of Michigan, Ann Arbor, USA.
³ Michigan Institute for Data Science (MIDAS), University of Michigan, Ann Arbor, USA.
⁴ Michigan Center for Integrative Research in Critical Care (MCIRCC), University of Michigan, Ann Arbor, USA.
⁵ Department of Internal Medicine, University of Michigan, Ann Arbor, USA.
⁶ Division of Cardiovascular Diseases, University of Michigan, Ann Arbor, USA.
⁷ Department of Emergency Medicine, University of Michigan, Ann Arbor, USA.
⁸ Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, USA.

^# Contributed equally.

Abstract

Background: Automated segmentation of coronary arteries is a crucial step for computer-aided coronary artery disease (CAD) diagnosis and treatment planning. Correct delineation of the coronary artery is challenging in X-ray coronary angiography (XCA) due to the low signal-to-noise ratio and confounding background structures.

Methods: A novel ensemble framework for coronary artery segmentation in XCA images is proposed, which utilizes deep learning and filter-based features to construct models using the gradient boosting decision tree (GBDT) and deep forest classifiers. The proposed method was trained and tested on 130 XCA images. For each pixel of interest in the XCA images, a 37-dimensional feature vector was constructed based on (1) the statistics of multi-scale filtering responses in the morphological, spatial, and frequency domains; and (2) the feature maps obtained from trained deep neural networks. The performance of these models was compared with those of common deep neural networks on metrics including precision, sensitivity, specificity, F1 score, AUROC (the area under the receiver operating characteristic curve), and IoU (intersection over union).

Results: With hybrid under-sampling methods, the best performing GBDT model achieved a mean F1 score of 0.874, AUROC of 0.947, sensitivity of 0.902, and specificity of 0.992; while the best performing deep forest model obtained a mean F1 score of 0.867, AUROC of 0.95, sensitivity of 0.867, and specificity of 0.993. Compared with the evaluated deep neural networks, both models had better or comparable performance for all evaluated metrics with lower standard deviations over the test images.

Conclusions: The proposed feature-based ensemble method outperformed common deep convolutional neural networks in most performance metrics while yielding more consistent results. Such a method can be used to facilitate the assessment of stenosis and improve the quality of care in patients with CAD.

Keywords: Deep learning; Ensemble learning; Medical image segmentation; X-ray coronary angiography.

MeSH terms

Coronary Angiography / methods*
Coronary Disease / diagnostic imaging*
Coronary Vessels / diagnostic imaging*
Deep Learning*
Humans
Image Processing, Computer-Assisted / methods*