Optimal Coronary Artery Segmentation Based on Transfer Learning and UNet Architecture

被引：1

作者：

Serrano-Anton, Belen ^{[1
,2
,3
]}

Otero-Cacho, Alberto ^{[1
,2
,3
]}

Lopez-Otero, Diego ^{[4
,5
]}

Diaz-Fernandez, Brais ^{[4
,5
]}

Bastos-Fernandez, Maria ^{[4
,5
]}

Massonis, Gemma ^{[1
]}

Pendon, Santiago ^{[1
]}

Perez-Munuzuri, Vicente ^{[3
,6
]}

Ramon Gonzalez-Juanatey, Jose ^{[4
,5
,7
]}

Munuzuri, Alberto P. ^{[2
,3
]}

机构：

[1] FlowReserve Labs SL, Santiago De Compostela 15782, Spain

[2] Galician Ctr Math Res & Technol CITMAga, Santiago De Compostela 15782, Spain

[3] Univ Santiago de Compostela, Grp Nonlinear Phys, Santiago De Compostela 15782, Spain

[4] Univ Hosp Santiago de Compostela, Cardiol & Intens Cardiac Care Dept, Santiago De Compostela 15706, Spain

[5] Ctr Invest Biomed Red Enfermedades Cardiovasc CIB, Madrid 28029, Spain

[6] Univ Santiago de Compostela, Inst CRETUS, Grp Nonlinear Phys, Santiago De Compostela 15705, Spain

[7] Inst Invest Sanitaria Santiago de Compostela IDIS, Santiago De Compostela 15706, Spain

来源：

SHAPE IN MEDICAL IMAGING, SHAPEMI 2023 | 2023年 / 14350卷

关键词：

Coronary; Artery; Segmentaion; CT; Neural Network;

D O I：

10.1007/978-3-031-46914-5_5

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Recent results demonstrated that the use of AI to perform complicated segmentation of medical images becomes very useful when the coronary arteries are considered. Nevertheless, the different segments of the coronary arteries (distal, middle and proximal) exhibit singularities, mostly linked to section changes and image visibility, that point in the direction to consider each in a singular way. In the present contribution we thoroughly analyse the quality of the segmentation obtained using different neural networks, based on the UNet architecture, applied to the three segments of the coronary arteries. We observe that for proximal segments any of the AI considered provides acceptable segmentations while for distal segments the 3D UNet is not able to recognise the coronary structures. In addition, in the distal region there is a noticeable improvement in the 2D UNet without pre-training compared to the 2D networks with pre-training.

引用

页码：55 / 64

页数：10

共 10 条

[1] A Computationally Efficient Approach to Segmentation of the Aorta and Coronary Arteries Using Deep Learning [J].

Cheung, Wing Keung ;

Bell, Robert ;

Nair, Arjun ;

Menezes, Leon J. ;

Patel, Riyaz ;

Wan, Simon ;

Chou, Kacy ;

Chen, Jiahang ;

Torii, Ryo ;

Davies, Rhodri H. ;

Moon, James C. ;

Alexander, Daniel C. ;

Jacob, Joseph .

IEEE ACCESS, 2021, 9 :108873-108888

[2] Fusing 2D and 3D convolutional neural networks for the segmentation of aorta and coronary arteries from CT images [J].

Gu, Linyan ;

Cai, Xiao-Chuan .

ARTIFICIAL INTELLIGENCE IN MEDICINE, 2021, 121 (121)

[3] Clinical comparison of sub-mm high-resolution non-contrast coronary CMR angiography against coronary CT angiography in patients with low-intermediate risk of coronary artery disease: a single center trial [J].

Hajhosseiny, Reza ;

Rashid, Imran ;

Bustin, Aurelien ;

Munoz, Camila ;

Cruz, Gastao ;

Nazir, Muhummad Sohaib ;

Grigoryan, Karine ;

Ismail, Tevfik F. ;

Preston, Rebecca ;

Neji, Radhouene ;

Kunze, Karl ;

Razavi, Reza ;

Chiribiri, Amedeo ;

Masci, Pier Giorgio ;

Rajani, Ronak ;

Prieto, Claudia ;

Botnar, Rene M. .

JOURNAL OF CARDIOVASCULAR MAGNETIC RESONANCE, 2021, 23 (01)

[4] On-Site Computed Tomography-Derived Fractional Flow Reserve Using a Machine-Learning Algorithm - Clinical Effectiveness in a Retrospective Multicenter Cohort - [J].

Kurata, Akira ;

Fukuyama, Naoki ;

Hirai, Kuniaki ;

Kawaguchi, Naoto ;

Tanabe, Yuki ;

Okayama, Hideki ;

Shigemi, Susumu ;

Watanabe, Kouki ;

Uetani, Teruyoshi ;

Ikeda, Shuntaro ;

Inaba, Shinji ;

Kido, Teruhito ;

Itoh, Toshihide ;

Mochizuki, Teruhito .

CIRCULATION JOURNAL, 2019, 83 (07) :1563-1571

[5]

Otero-Cacho A., 2023, Validation of a new model of non-invasive functional assessment of coronary lesions by computer tomography fractional flow reserve

[6] Coronary artery segmentation under class imbalance using a U-Net based architecture on computed tomography angiography images [J].

Pan, Li-Syuan ;

Li, Chia-Wei ;

Su, Shun-Feng ;

Tay, Shee-Yen ;

Tran, Quoc-Viet ;

Chan, Wing P. .

SCIENTIFIC REPORTS, 2021, 11 (01)

[7] AI in Medical Imaging Informatics: Current Challenges and Future Directions [J].

Panayides, Andreas S. ;

Amini, Amir ;

Filipovic, Nenad ;

Sharma, Ashish ;

Tsaftaris, Sotirios A. ;

Young, Alistair ;

Foran, David J. ;

Nhan Do ;

Golemati, Spyretta ;

Kurc, Tahsin ;

Huang, Kun ;

Nikita, Konstantina S. ;

Veasey, Ben P. ;

Zervakis, Michalis ;

Saltz, Joel H. ;

Pattichis, Constantinos S. .

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2020, 24 (07) :1837-1857

[8] Coronary Artery Segmentation Based on Transfer Learning and UNet Architecture on Computed Tomography Coronary Angiography Images [J].

Serrano-Anton, Belen ;

Otero-Cacho, Alberto ;

Lopez-Otero, Diego ;

Diaz-Fernandez, Brais ;

Bastos-Fernandez, Maria ;

Perez-Munuzuri, Vicente ;

Gonzalez-Juanatey, Jose Ramon ;

Munuzuri, Alberto P. P. .

IEEE ACCESS, 2023, 11 :75484-75496

[9] Serial coronary CT angiography-derived fractional flow reserve and plaque progression can predict long-term outcomes of coronary artery disease [J].

Yang, Liu ;

Xu, Peng Peng ;

Schoepf, U. Joseph ;

Tesche, Christian ;

Pillai, Balakrishnan ;

Savage, Rock H. ;

Tang, Chun Xiang ;

Zhou, Fan ;

Wei, Hao Dong ;

Luo, Zhong Qiang ;

Wang, Qing Gen ;

Zhou, Chang Sheng ;

Lu, Meng Jie ;

Lu, Guang Ming ;

Zhang, Long Jiang .

EUROPEAN RADIOLOGY, 2021, 31 (09) :7110-7120

[10] RESPONSES OF ANGIOGRAPHICALLY NORMAL HUMAN CORONARY-ARTERIES TO INTRACORONARY INJECTION OF ACETYLCHOLINE BY AGE AND SEGMENT - POSSIBLE ROLE OF EARLY CORONARY ATHEROSCLEROSIS [J].

YASUE, H ;

MATSUYAMA, K ;

OKUMURA, K ;

MORIKAMI, Y ;

OGAWA, H .

CIRCULATION, 1990, 81 (02) :482-490

← 1 →