A review of machine learning methods for retinal blood vessel segmentation and artery/vein classification |
| |
| Affiliation: | 1. VAMPIRE project, Computing (SSEN), University of Dundee, Dundee DD1 4HN, UK;2. VAMPIRE project, Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh EH16 4SB, UK;3. Madras Diabetes Research Foundation and Dr. Mohan’s Diabetes Specialities Centre, Gopalapuram, Chennai 600086, India;4. Division of Population Health and Genomics, Ninewells Hospital and Medical School, University of Dundee, Dundee, DD1 9SY, UK;1. College of Computer Science, Nankai University, Tianjin, China;2. Beijing Shanggong Medical Technology Co. Ltd., China;3. State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Science, Beijing 100190, China;4. Key Laboratory for Medical Data Analysis and Statistical Research of Tianjin, China;1. Zhuhai Interventional Medical Center, Zhuhai Precision Medical Center, Zhuhai People’s Hospital, Zhuhai Hospital Affiliated with Jinan University, Jinan University, Zhuhai, Guangdong 519000, PR China;2. Department of Cardiology, Zhuhai People’s Hospital, Zhuhai Hospital Affiliated with Jinan University, Jinan University, Zhuhai, Guangdong 519000, PR China;3. Department of Obstetrics, Zhuhai People’s Hospital, Zhuhai Hospital Affiliated with Jinan University, Jinan University, Zhuhai, Guangdong 519000, PR China;1. Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy;2. Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy |
| |
| Abstract: | The eye affords a unique opportunity to inspect a rich part of the human microvasculature non-invasively via retinal imaging. Retinal blood vessel segmentation and classification are prime steps for the diagnosis and risk assessment of microvascular and systemic diseases. A high volume of techniques based on deep learning have been published in recent years. In this context, we review 158 papers published between 2012 and 2020, focussing on methods based on machine and deep learning (DL) for automatic vessel segmentation and classification for fundus camera images. We divide the methods into various classes by task (segmentation or artery-vein classification), technique (supervised or unsupervised, deep and non-deep learning, hand-crafted methods) and more specific algorithms (e.g. multiscale, morphology). We discuss advantages and limitations, and include tables summarising results at-a-glance. Finally, we attempt to assess the quantitative merit of DL methods in terms of accuracy improvement compared to other methods. The results allow us to offer our views on the outlook for vessel segmentation and classification for fundus camera images. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
