Selective ensemble methods for deep learning segmentation of major vessels in invasive coronary angiography.
invasive coronary angiography
major vessel segmentation
weighted ensemble method
Journal
Medical physics
ISSN: 2473-4209
Titre abrégé: Med Phys
Pays: United States
ID NLM: 0425746
Informations de publication
Date de publication:
Dec 2023
Dec 2023
Historique:
revised:
29
03
2023
received:
10
07
2022
accepted:
26
05
2023
medline:
6
12
2023
pubmed:
13
6
2023
entrez:
13
6
2023
Statut:
ppublish
Résumé
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. 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. 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. 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. 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.
Sections du résumé
BACKGROUND
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
OBJECTIVE
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
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
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
CONCLUSIONS
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.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
7822-7839Informations de copyright
© 2023 The Authors. Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.
Références
World Health Organization. Global Health Estimates 2019: deaths by cause, age, sex, by country and by region, 2000-2019. Geneva: World Health Organization; 2020.
Sianos G, Morel MA, Kappetein AP, et al. The SYNTAX Score: an angiographic tool grading the complexity of coronary artery disease. EuroIntervention. 2005;1(2):219-227.
Thuijs DJFM, Kappetein AP, Serruys PW, et al. Percutaneous coronary intervention versus coronary artery bypass grafting in patients with three-vessel or left main coronary artery disease: 10-year follow-up of the multicentre randomised controlled SYNTAX trial. Lancet. 2019;394(10206):1325-1334.
Morris PD, Curzen N, Gunn JP. Angiography-derived fractional flow reserve: more or less physiology? J Am Heart Assoc. 2020;9(6):e015586.
Tu S, Barbato E, Köszegi Z, et al. Fractional flow reserve calculation from 3-dimensional quantitative coronary angiography and TIMI frame count: a fast computer model to quantify the functional significance of moderately obstructed coronary arteries. JACC Cardiovasc Interv. 2014;7(7):768-777.
Stone PH, Saito S, Takahashi S, et al. Prediction of progression of coronary artery disease and clinical outcomes using vascular profiling of endothelial shear stress and arterial plaque characteristics: the PREDICTION study. Circulation. 2012;126(2):172-181.
Tomaniak M, Katagiri Y, Modolo R, et al. Vulnerable plaques and patients: state-of-the-art. Eur Heart J. 2020;41(31):2997-3004.
Blondel C, Malandain G, Vaillant R, Ayache N. Reconstruction of coronary arteries from a single rotational x-ray projection sequence. IEEE Trans Med Imaging. 2006;25(5):653-663.
Cruz-Aceves I, Oloumi F, Rangayyan RM, Aviña-Cervantes JG, Hernandez-Aguirre A. Automatic segmentation of coronary arteries using Gabor filters and thresholding based on multiobjective optimization. Biomed Signal Process Control. 2016;25:76-85.
Fazlali HR, Karimi N, Soroushmehr SMR, et al. Vessel segmentation and catheter detection in x-ray angiograms using superpixels. Med Biol Eng Comput. 2018;56(9):1515-1530.
Qin B, Jin M, Hao D, et al. Accurate vessel extraction via tensor completion of background layer in x-ray coronary angiograms. Pattern Recognit. 2019;87:38-54.
Iyer K, Najarian CP, Fattah AA, et al. AngioNet: a convolutional neural network for vessel 1 segmentation in x-ray angiography. Sci Rep. 2021;11(1):18066.
Jun TJ, Kweon J, Kim YH, T-Net Kim D. Nested encoder-decoder architecture for the main vessel segmentation in coronary angiography. Neural Networks. 2020;128:216-233.
Yang S, Kweon J, Roh JH, et al. Deep learning segmentation of major vessels in x-ray coronary angiography. Sci Rep. 2019;9(1):16897.
Zhang D, Yang G, Zhao S, et al. Direct quantification of coronary artery stenosis through hierarchical attentive multi-view learning. IEEE Trans Med Imaging. 2020;39(12):4322-4334.
Moon JH, Lee DY, Cha WC, et al. Automatic stenosis recognition from coronary angiography using convolutional neural networks. Comput Methods Programs Biomed. 2021;198:105819.
Silva JL, Menezes MN, Rodrigues T, Silva B, Pinto FJ, Oliveira AL. Encoder-decoder architectures for clinically relevant coronary artery segmentation. In: Computational Advances in Bio and Medical Sciences; Springer International Publishing; 2022:63-78.
Zhao C, Vij A, Malhotra S, et al. Automatic extraction and stenosis evaluation of coronary arteries in invasive coronary angiograms. Comput Biol Med. 2021;136:104667.
Zhu X, Cheng Z, Wang S, Chen X, Lu G. Coronary angiography image segmentation based on PSPNet. Comput Methods Programs Biomed. 2021;200:105897.
Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Medical Image Computing and Computer-Assisted Intervention; Springer International Publishing; 2015:234-241.
Zhao L, Li D, Chen J, Wan T. Automated coronary tree segmentation for x-ray angiography sequences using fully-convolutional neural networks. In: IEEE International Conference on Visual Communications and Image Processing; 2018:1-4.
Liang D, Qiu J, Wang L, et al. Coronary angiography video segmentation method for assisting cardiovascular disease interventional treatment. BMC Med Imaging. 2020;20(1):65.
Wan T, Chen J, Zhang Z, Li D, Qin Z. Automatic vessel segmentation in x-ray angiogram using spatio-temporal fully-convolutional neural network. Biomed Signal Process Control. 2021;68:102646.
Wang L, Liang D, Yin X, et al. Coronary artery segmentation in angiographic videos utilizing spatial-temporal information. BMC Med Imaging. 2020;20(1):110.
Brown G, Wyatt J, Harris R, Yao X. Diversity creation methods: a survey and categorisation. Inf Fusion. 2005;6(1):5-20.
Dietterich TG. Ensemble methods in machine learning. International Workshop on Multiple Classifier Systems (MCS). Springer-Verlag:1-15.
Ganaie MA, Hu M, Tanveer M, Suganthan PN. Ensemble deep learning: a review. Eng Appl Artif Intell. 2022;115:105151.
Sundaresan V, Zamboni G, Rothwell PM, Jenkinson M, Griffanti L. Triplanar ensemble U-Net model for white matter hyperintensities segmentation on MR images. Med Image Anal. 2021;73:102184.
Lyu Q, Shan H, Wang G. MRI super-resolution with ensemble learning and complementary priors. IEEE Trans Comput Imaging. 2020;6:615-624.
Sohail A, Khan A, Nisar H, Tabassum S, Zameer A. Mitotic nuclei analysis in breast cancer histopathology images using deep ensemble classifier. Med Image Anal. 2021;72:102121.
Calisto MB, Lai-Yuen SK. AdaEn-Net: an ensemble of adaptive 2D-3D Fully Convolutional Networks for medical image segmentation. Neural Networks. 2020;126:76-94.
Byrne N, Clough JR, Montana G, King AP. A persistent homology-based topological loss function for multi-class CNN segmentation of cardiac MRI. International Workshop on Statistical Atlases and Computational Models of the Heart. Springer Nature Switzerland AG; 3-13.
Caliva F, Iriondo C, Martinez AM, Majumdar S, Pedoia V. Distance map loss penalty term for semantic segmentation. In: International Conference on Medical Imaging with Deep Learning. 2019.
Gerl S, Paetzold JC, He H, et al. A distance-based loss for smooth and continuous skin layer segmentation in optoacoustic images. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer Nature Switzerland AG; 309-319.
EL Jurdi R, Petitjean C, Honeine P, Cheplygina V, Abdallah F. A surprisingly effective perimeter-based loss for medical image segmentation. Med Imag Deep Learning. 2021:127-136.
Kervadec H, Bouchtiba J, Desrosiers C, Granger E, Dolz J, Ben Ayed I. Boundary loss for highly unbalanced segmentation. Med Image Anal. 2021;67:101851.
Shit S, Paetzold JC, Sekuboyina A, et al. clDice - A novel topology-preserving loss function for tubular structure segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021:16560-16569.
Zhou ZH, Wu J, Tang W. Ensembling neural networks: many could be better than all. Artif Intell. 2002;137(1-2):239-263.
Couteaux V, Si-Mohamed S, Renard-Penna R, et al. Kidney cortex segmentation in 2D CT with U-Nets ensemble aggregation. Diagn Interv Imaging. 2019;100(4):211-217.
Kang J, Gwak J. Ensemble of instance segmentation models for polyp segmentation in colonoscopy images. IEEE Access. 2019;7:26440-26447.
Murugesan GK, Nalawade S, Ganesh C, et al. Multidimensional and multiresolution ensemble networks for brain tumor segmentation. International MICCAI Brainlesion Workshop. Springer Nature Switzerland AG; 448-457.
Weisman AJ, Kieler MW, Perlman SB, et al. Convolutional neural networks for automated PET/CT detection of diseased lymph node burden in patients with lymphoma. Radiol Artif Intell. 2020;2(5):e200016.
Winzeck S, Mocking SJT, Bezerra R, et al. Ensemble of convolutional neural networks improves automated segmentation of acute ischemic lesions using multiparametric diffusion-weighted MRI. Am J Neuroradiol. 2019;40(6):938-945.
Chassagnon G, Vakalopoulou M, Régent A, et al. Deep learning-based approach for automated assessment of interstitial lung disease in systemic sclerosis on CT images. Radiol Artif Intell. 2020;2(4):e190006.
Mondal C, Hasan MK, Jawad MT, et al. Acute lymphoblastic leukemia detection from microscopic images using weighted ensemble of convolutional neural networks. Published online 2021:arXiv preprint arXiv:2105.03995.
Zhai S, Gu R, Lei W, Wang G. Myocardial edema and scar segmentation using a coarse-to-fine framework with weighted ensemble. Myocardial Pathology Segmentation Combining Multi-Sequence CMR Challenge. Springer Nature Switzerland AG; 49-59.
Zheng H, Zhang Y, Yang L, et al. A new ensemble learning framework for 3D biomedical image segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence. 2019:5909-5916.
Hann E, Popescu IA, Zhang Q, et al. Deep neural network ensemble for on-the-fly quality control-driven segmentation of cardiac MRI T1 mapping. Med Image Anal. 2021;71:102029.
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: Proceedings - IEEE Conference on Computer Vision and Pattern Recognition. 2017:2261-2269.
Acosta O, Mylona E, Le Dain M, et al. Multi-atlas-based segmentation of prostatic urethra from planning CT imaging to quantify dose distribution in prostate cancer radiotherapy. Radiother Oncol. 2017;125(3):492-499.
Karimi D, Salcudean SE. Reducing the hausdorff distance in medical image segmentation with convolutional neural networks. IEEE Trans Med Imaging. 2020;39(2):499-513.
Lee TC, Kashyap RL, Chu CN. Building skeleton models via 3-D medial surface axis thinning algorithms. CVGIP Graph Model Image Process. 1994;56(6):462-478.
Ardizzone E, Pirrone R, Gambino O, Radosta S. Blood vessels and feature points detection on retinal images. In: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2008:2246-2249.
Liu F, Xia Y, Yang D, Yuille A, Xu D. An alarm system for segmentation algorithm based on shape model. In: Proceedings of the IEEE International Conference on Computer Vision. 2019:10651-10660.
Sandfort V, Yan K, Graffy PM, Pickhardt PJ, Summers RM. Use of variational autoencoders with unsupervised learning to detect incorrect organ segmentations at CT. Radiol Artif Intell. 2021;3(4):e200218.
Schlegl T, Seeböck P, Waldstein SM, Schmidt-Erfurth U, Langs G. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. International Conference on Information Processing in Medical Imaging (IPMI). Springer International Publishing AG, 146-147.
Xia Y, Zhang Y, Liu F, Shen W, Yuille AL. Synthesize then compare: detecting failures and anomalies for semantic segmentation. European Conference on Computer Vision (ECCV). Springer Nature Switzerland AG:145-161.
Huo Y, Kassab GS. The scaling of blood flow resistance: from a single vessel to the entire distal tree. Biophys J. 2009;96(2):339-346.
Išgum I, Staring M, Rutten A, Prokop M, Viergever MA, Van Ginneken B. Multi-atlas-based segmentation with local decision fusion-application to cardiac and aortic segmentation in CT scans. IEEE Trans Med Imaging. 2009;28(7):1000-1010.
Lorenzo-Valdés M, Sanchez-Ortiz GI, Mohiaddin R, Rueckert D. Atlas-based segmentation and tracking of 3D cardiac MR images using non-rigid registration. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Springer-Verlag Berlin Heidelberg:642-650.
Shah R, Yow E, Jones WS, et al. Comparison of visual assessment of coronary stenosis with independent quantitative coronary angiography: findings from the Prospective Multicenter Imaging Study for Evaluation of Chest Pain (PROMISE) trial. Am Heart J. 2017;184:1-9.
Zhai M, Du T, Yang R, Zhang H. Coronary artery vascular segmentation on limited data via pseudo-precise label. In: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 2019:816-819.
Cavalcante R, Sotomi Y, Mancone M, et al. Impact of the SYNTAX scores i and II in patients with diabetes and multivessel coronary disease: a pooled analysis of patient level data from the SYNTAX, PRECOMBAT, and BEST trials. Eur Heart J. 2017;38(25):1969-1977.
Cho H, Lee JG, Kang SJ, et al. Angiography-based machine learning for predicting fractional flow reserve in intermediate coronary artery lesions. J Am Heart Assoc. 2019;8(4):e011685.
Asano T, Katagiri Y, Chang CC, et al. Angiography-Derived Fractional Flow Reserve in the SYNTAX II Trial: feasibility, diagnostic performance of quantitative flow ratio, and clinical prognostic value of functional SYNTAX score derived from quantitative flow ratio in patients with 3-vessel dis. JACC Cardiovasc Interv. 2019;12(3):259-270.
Ono M, Serruys PW, Patel MR, et al. A prospective multicenter validation study for a novel angiography-derived physiological assessment software: rationale and design of the radiographic imaging validation and evaluation for Angio-iFR (ReVEAL iFR) study. Am Heart J. 2021;239:19-26.
Kweon J, Kang SJ, Kim YH, et al. Impact of coronary lumen reconstruction on the estimation of endothelial shear stress: in vivo comparison of three-dimensional quantitative coronary angiography and three-dimensional fusion combining optical coherent tomography. Eur Heart J Cardiovasc Imaging. 2018;19(10):1134-1141.
Wu W, Samant S, de Zwart G, et al. 3D reconstruction of coronary artery bifurcations from coronary angiography and optical coherence tomography: feasibility, validation, and reproducibility. Sci Rep. 2020;10(1):18049.
Halon DA, Sapoznikov D, Lewis BS, Gotsman MS. Localization of lesions in the coronary circulation. Am J Cardiol. 1983;52(8):921-926.