AIROGS: Artificial Intelligence for Robust Glaucoma Screening Challenge
De Vente C. Vermeer K.A. Jaccard N. Wang H. Sun H. Khader F. Truhn D. Aimyshev T. Zhanibekuly Y. Le T.-D. Galdran A. Ballester M.A.G. Carneiro G. Devika R.G. Sethumadhavan H.P. Puthussery D. Liu H. Yang Z. Kondo S. Kasai S. Wang E. Durvasula A. Heras J. Zapata M.A. Araujo T. Aresta G. Bogunovic H. Arikan M. Lee Y.C. Cho H.B. Choi Y.H. Qayyum A. Razzak I. Van Ginneken B. Lemij H.G. Sanchez C.I.
1 January 2024Institute of Electrical and Electronics Engineers Inc.
IEEE Transactions on Medical Imaging
2024#43Issue 1542 - 557 pp.
The early detection of glaucoma is essential in preventing visual impairment. Artificial intelligence (AI) can be used to analyze color fundus photographs (CFPs) in a cost-effective manner, making glaucoma screening more accessible. While AI models for glaucoma screening from CFPs have shown promising results in laboratory settings, their performance decreases significantly in real-world scenarios due to the presence of out-of-distribution and low-quality images. To address this issue, we propose the Artificial Intelligence for Robust Glaucoma Screening (AIROGS) challenge. This challenge includes a large dataset of around 113,000 images from about 60,000 patients and 500 different screening centers, and encourages the development of algorithms that are robust to ungradable and unexpected input data. We evaluated solutions from 14 teams in this paper and found that the best teams performed similarly to a set of 20 expert ophthalmologists and optometrists. The highest-scoring team achieved an area under the receiver operating characteristic curve of 0.99 (95% CI: 0.98-0.99) for detecting ungradable images on-the-fly. Additionally, many of the algorithms showed robust performance when tested on three other publicly available datasets. These results demonstrate the feasibility of robust AI-enabled glaucoma screening.
Color fundus photography , glaucoma screening , out-of-distribution detection , retina , robustness
Text of the article Перейти на текст статьи
Quantitative Healthcare Analysis (QurAI) Group, Informatics Institute, Universiteit van Amsterdam, Noord-Holland, Amsterdam, 1098 XH, Netherlands
Department of Biomedical Engineering and Physics, Amsterdam UMC Locatie AMC, Noord-Holland, Amsterdam, 1105 AZ, Netherlands
Diagnostic Image Analysis Group (DIAG), Department of Radiology and Nuclear Medicine, Radboudumc, Gelderland, Nijmegen, 6500 HB, Netherlands
Rotterdam Ophthalmic Institute, The Rotterdam Eye Hospital, Rotterdam, 3011 BH, Netherlands
Project Orbis International Inc., New York, 10017, NY, United States
Peking Union Medical College Hospital, Beijing, 100730, China
Xuanwu Hospital Capital Medical University, Beijing, 100053, China
Department of Automation, Tsinghua University, Beijing, 100190, China
Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, 52074, Germany
CMC Technologies LLP, Nur-Sultan, Z05T0B8, Kazakhstan
KBC, Brussels, 1080, Belgium
Departament de Tecnologies de la Informacio i les Comunicacions (DTIC), Universitat Pompeu Fabra, Barcelona, 08018, Spain
Australian Institute for Machine Learning AIML, University of Adelaide, 5000, SA, Australia
ICREA, Barcelona, 08010, Spain
Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, GU2 7XH, United Kingdom
College of Engineering Trivandrum, Thiruvananthapuram, 695016, India
Founding Minds Software, Thiruvananthapuram, 682030, India
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China
Muroran Institute of Technology, Muroran, 050-0071, Japan
Niigata University of Health and Welfare, Niigata, 950-3102, Japan
Schulich School of Medicine and Dentistry, University of Western Ontario, London, N6A 5C1, ON, Canada
Department of Mathematics and Computer Science, University of La Rioja, Logrono, 26004, Spain
Hospital Vall Hebron, Sant Cugat del Vallés, Barcelona, 08195, Spain
UPRetina, Barcelona, 08195, Spain
Christian Doppler Laboratory for Artificial Intelligence in Retina, Department of Ophthalmology and Optometry, Medical University of Vienna, Vienna, 1090, Austria
Institute of Ophthalmology, University College London, London, EC1V 9EL, United Kingdom
Research Institute for Future Medicine, Samsung Medical Center, Seoul, 06351, South Korea
Department of Digital Health, Samsung Advanced Institute for Health Sciences and Technology (SAIHST), Sungkyunkwan University, Samsung Medical Center, Seoul, 06351, South Korea
Department of Artificial Intelligence and Informatics, Mayo Clinic, Jacksonville, 32224, FL, United States
Department of Biomedical Engineering, Kings College London, London, WC2R 2LS, United Kingdom
School of Computer Science and Engineering, University of New South Wales, Sydney, 3125, NSW, Australia
Quantitative Healthcare Analysis (QurAI) Group
Department of Biomedical Engineering and Physics
Diagnostic Image Analysis Group (DIAG)
Rotterdam Ophthalmic Institute
Project Orbis International Inc.
Peking Union Medical College Hospital
Xuanwu Hospital Capital Medical University
Department of Automation
Department of Diagnostic and Interventional Radiology
CMC Technologies LLP
KBC
Departament de Tecnologies de la Informacio i les Comunicacions (DTIC)
Australian Institute for Machine Learning AIML
ICREA
Centre for Vision
College of Engineering Trivandrum
Founding Minds Software
Institute of Computing Technology
Muroran Institute of Technology
Niigata University of Health and Welfare
Schulich School of Medicine and Dentistry
Department of Mathematics and Computer Science
Hospital Vall Hebron
UPRetina
Christian Doppler Laboratory for Artificial Intelligence in Retina
Institute of Ophthalmology
Research Institute for Future Medicine
Department of Digital Health
Department of Artificial Intelligence and Informatics
Department of Biomedical Engineering
School of Computer Science and Engineering
10 лет помогаем публиковать статьи Международный издатель
Книга Публикация научной статьи Волощук 2026 Book Publication of a scientific article 2026