Predicting diabetic macular edema treatment responses using OCT: Dataset and methods of APTOS competition

Weiyi Zhang; Peranut Chotcomwongse; Yinwen Li; Pusheng Xu; Ruijie Yao; Lianhao Zhou; Yuxuan Zhou; Hui Feng; Qiping Zhou; Xinyue Wang; Shoujin Huang; Zihao Jin; Florence H.T. Chung; Shujun Wang; Yalin Zheng; Mingguang He; Danli Shi; Paisan Ruamviboonsuk

doi:10.1016/j.media.2026.103942

Predicting diabetic macular edema treatment responses using OCT: Dataset and methods of APTOS competition

Weiyi Zhang
, Peranut Chotcomwongse
, Yinwen Li
, Pusheng Xu
, Ruijie Yao
, Lianhao Zhou
, Yuxuan Zhou
, Hui Feng
, Qiping Zhou
, Xinyue Wang
, Shoujin Huang
, Zihao Jin
, Florence H.T. Chung
, Shujun Wang
, Yalin Zheng
, Mingguang He (Corresponding Author)
, Danli Shi (Corresponding Author)
, Paisan Ruamviboonsuk (Corresponding Author)

Research output: Journal article publication › Short survey › Academic research › peer-review

1 Citation (Scopus)

Abstract

Diabetic macular edema (DME) significantly contributes to visual impairment in diabetic patients. Treatment responses to intravitreal therapies vary, highlighting the need for patient stratification to predict therapeutic benefits and enable personalized strategies. To our knowledge, this study is the first to explore pre-treatment stratification for predicting DME treatment responses. To advance this research, we organized the 2nd Asia-Pacific Tele-Ophthalmology Society (APTOS) Big Data Competition in 2021. The competition focused on improving predictive accuracy for anti-VEGF therapy responses using ophthalmic OCT images. We provided a dataset containing tens of thousands of OCT images from 2000 patients with labels across four sub-tasks. This paper details the competition’s structure, dataset, leading methods, and evaluation metrics. The competition attracted strong scientific community participation, with 170 teams initially registering and 41 reaching the final round. The top-performing team achieved an AUC of 80.06 %, highlighting the potential of AI in personalized DME treatment and clinical decision-making.

Original language	English
Article number	103942
Pages (from-to)	1-17
Number of pages	17
Journal	Medical Image Analysis
Volume	109
Issue number	1
DOIs	https://doi.org/10.1016/j.media.2026.103942
Publication status	E-pub ahead of print - 13 Jan 2026

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Anti-VEGF therapy
Big data competition
Diabetic macular edema
Optical coherence tomography
Treatment response prediction

ASJC Scopus subject areas

Radiological and Ultrasound Technology
Radiology Nuclear Medicine and imaging
Computer Vision and Pattern Recognition
Health Informatics
Computer Graphics and Computer-Aided Design

More information

10.1016/j.media.2026.103942

http://hdl.handle.net/10397/116731

Cite this

Zhang, W., Chotcomwongse, P., Li, Y., Xu, P., Yao, R., Zhou, L., Zhou, Y., Feng, H., Zhou, Q., Wang, X., Huang, S., Jin, Z., Chung, F. H. T., Wang, S., Zheng, Y., He, M., Shi, D., & Ruamviboonsuk, P. (2026). Predicting diabetic macular edema treatment responses using OCT: Dataset and methods of APTOS competition. Medical Image Analysis, 109(1), 1-17. Article 103942. Advance online publication. https://doi.org/10.1016/j.media.2026.103942

@article{a118fc721c8c44098d70e1c40a84e712,

title = "Predicting diabetic macular edema treatment responses using OCT: Dataset and methods of APTOS competition",

abstract = "Diabetic macular edema (DME) significantly contributes to visual impairment in diabetic patients. Treatment responses to intravitreal therapies vary, highlighting the need for patient stratification to predict therapeutic benefits and enable personalized strategies. To our knowledge, this study is the first to explore pre-treatment stratification for predicting DME treatment responses. To advance this research, we organized the 2nd Asia-Pacific Tele-Ophthalmology Society (APTOS) Big Data Competition in 2021. The competition focused on improving predictive accuracy for anti-VEGF therapy responses using ophthalmic OCT images. We provided a dataset containing tens of thousands of OCT images from 2000 patients with labels across four sub-tasks. This paper details the competition{\textquoteright}s structure, dataset, leading methods, and evaluation metrics. The competition attracted strong scientific community participation, with 170 teams initially registering and 41 reaching the final round. The top-performing team achieved an AUC of 80.06 \%, highlighting the potential of AI in personalized DME treatment and clinical decision-making.",

keywords = "Anti-VEGF therapy, Big data competition, Diabetic macular edema, Optical coherence tomography, Treatment response prediction",

author = "Weiyi Zhang and Peranut Chotcomwongse and Yinwen Li and Pusheng Xu and Ruijie Yao and Lianhao Zhou and Yuxuan Zhou and Hui Feng and Qiping Zhou and Xinyue Wang and Shoujin Huang and Zihao Jin and Chung, \{Florence H.T.\} and Shujun Wang and Yalin Zheng and Mingguang He and Danli Shi and Paisan Ruamviboonsuk",

note = "Publisher Copyright: {\textcopyright} 2026 The Author(s).",

year = "2026",

month = jan,

day = "13",

doi = "10.1016/j.media.2026.103942",

language = "English",

volume = "109",

pages = "1--17",

journal = "Medical Image Analysis",

issn = "1361-8415",

publisher = "Elsevier B.V.",

number = "1",

}

Zhang, W, Chotcomwongse, P, Li, Y, Xu, P, Yao, R, Zhou, L, Zhou, Y, Feng, H, Zhou, Q, Wang, X, Huang, S, Jin, Z, Chung, FHT, Wang, S, Zheng, Y, He, M , Shi, D & Ruamviboonsuk, P 2026, 'Predicting diabetic macular edema treatment responses using OCT: Dataset and methods of APTOS competition', Medical Image Analysis, vol. 109, no. 1, 103942, pp. 1-17. https://doi.org/10.1016/j.media.2026.103942

TY - JOUR

T1 - Predicting diabetic macular edema treatment responses using OCT: Dataset and methods of APTOS competition

AU - Zhang, Weiyi

AU - Chotcomwongse, Peranut

AU - Li, Yinwen

AU - Xu, Pusheng

AU - Yao, Ruijie

AU - Zhou, Lianhao

AU - Zhou, Yuxuan

AU - Feng, Hui

AU - Zhou, Qiping

AU - Wang, Xinyue

AU - Huang, Shoujin

AU - Jin, Zihao

AU - Chung, Florence H.T.

AU - Wang, Shujun

AU - Zheng, Yalin

AU - He, Mingguang

AU - Shi, Danli

AU - Ruamviboonsuk, Paisan

PY - 2026/1/13

Y1 - 2026/1/13

N2 - Diabetic macular edema (DME) significantly contributes to visual impairment in diabetic patients. Treatment responses to intravitreal therapies vary, highlighting the need for patient stratification to predict therapeutic benefits and enable personalized strategies. To our knowledge, this study is the first to explore pre-treatment stratification for predicting DME treatment responses. To advance this research, we organized the 2nd Asia-Pacific Tele-Ophthalmology Society (APTOS) Big Data Competition in 2021. The competition focused on improving predictive accuracy for anti-VEGF therapy responses using ophthalmic OCT images. We provided a dataset containing tens of thousands of OCT images from 2000 patients with labels across four sub-tasks. This paper details the competition’s structure, dataset, leading methods, and evaluation metrics. The competition attracted strong scientific community participation, with 170 teams initially registering and 41 reaching the final round. The top-performing team achieved an AUC of 80.06 %, highlighting the potential of AI in personalized DME treatment and clinical decision-making.

AB - Diabetic macular edema (DME) significantly contributes to visual impairment in diabetic patients. Treatment responses to intravitreal therapies vary, highlighting the need for patient stratification to predict therapeutic benefits and enable personalized strategies. To our knowledge, this study is the first to explore pre-treatment stratification for predicting DME treatment responses. To advance this research, we organized the 2nd Asia-Pacific Tele-Ophthalmology Society (APTOS) Big Data Competition in 2021. The competition focused on improving predictive accuracy for anti-VEGF therapy responses using ophthalmic OCT images. We provided a dataset containing tens of thousands of OCT images from 2000 patients with labels across four sub-tasks. This paper details the competition’s structure, dataset, leading methods, and evaluation metrics. The competition attracted strong scientific community participation, with 170 teams initially registering and 41 reaching the final round. The top-performing team achieved an AUC of 80.06 %, highlighting the potential of AI in personalized DME treatment and clinical decision-making.

KW - Anti-VEGF therapy

KW - Big data competition

KW - Diabetic macular edema

KW - Optical coherence tomography

KW - Treatment response prediction

UR - https://www.scopus.com/pages/publications/105027912638

U2 - 10.1016/j.media.2026.103942

DO - 10.1016/j.media.2026.103942

M3 - Short survey

C2 - 41564632

AN - SCOPUS:105027912638

SN - 1361-8415

VL - 109

SP - 1

EP - 17

JO - Medical Image Analysis

JF - Medical Image Analysis

IS - 1

M1 - 103942

ER -

Predicting diabetic macular edema treatment responses using OCT: Dataset and methods of APTOS competition

Abstract

UN SDGs

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this