Skip to main content

Development of a deep learning model to classify choroidal melanoma risk factors based on color fundus photographs.

Journal articles  - Journal Article
Suri, H; Lentz, PC; Leske, DA; Mousavi, M; D'Souza, HS; Qureshi, MB; Iezzi, R; Varatharajah, Y; Dalvin, LA
Published in: AJO Int
December 11, 2025

Choroidal melanoma is the most common malignant primary intraocular tumor and can develop either de novo or from a preexisting choroidal nevus, a benign pigmented lesion. Key risk factors for the transformation of choroidal nevus into melanoma include tumor diameter > 5 mm, tumor thickness > 2 mm, orange pigment, subretinal fluid, and low internal reflectivity on ultrasound. However, the assessment of many of these risk factors requires multimodal imaging equipment and skilled subspecialists, only available at tertiary referral centers. In this study, we developed and validated a deep learning approach to identifying these risk factors based solely on fundus images of choroidal nevi. Results indicate acceptable to excellent predictive performance for detection of all five risk factors. These findings suggest that deep learning models may be valuable tools for identifying high-risk choroidal nevi, particularly in resource-limited settings.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

AJO Int

DOI

EISSN

2950-2535

Publication Date

December 11, 2025

Volume

2

Issue

4

Location

United States
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Suri, H., Lentz, P. C., Leske, D. A., Mousavi, M., D’Souza, H. S., Qureshi, M. B., … Dalvin, L. A. (2025). Development of a deep learning model to classify choroidal melanoma risk factors based on color fundus photographs. AJO Int, 2(4). https://doi.org/10.1016/j.ajoint.2025.100167
Suri, Huzaifa, P Connor Lentz, David A. Leske, Mostafa Mousavi, Haley S. D’Souza, Muhammad B. Qureshi, Raymond Iezzi, Yogatheesan Varatharajah, and Lauren A. Dalvin. “Development of a deep learning model to classify choroidal melanoma risk factors based on color fundus photographs.” AJO Int 2, no. 4 (December 11, 2025). https://doi.org/10.1016/j.ajoint.2025.100167.
Suri H, Lentz PC, Leske DA, Mousavi M, D’Souza HS, Qureshi MB, et al. Development of a deep learning model to classify choroidal melanoma risk factors based on color fundus photographs. AJO Int. 2025 Dec 11;2(4).
Suri, Huzaifa, et al. “Development of a deep learning model to classify choroidal melanoma risk factors based on color fundus photographs.” AJO Int, vol. 2, no. 4, Dec. 2025. Pubmed, doi:10.1016/j.ajoint.2025.100167.
Suri H, Lentz PC, Leske DA, Mousavi M, D’Souza HS, Qureshi MB, Iezzi R, Varatharajah Y, Dalvin LA. Development of a deep learning model to classify choroidal melanoma risk factors based on color fundus photographs. AJO Int. 2025 Dec 11;2(4).

Published In

AJO Int

DOI

EISSN

2950-2535

Publication Date

December 11, 2025

Volume

2

Issue

4

Location

United States