Work

Artificial intelligence in cataract grading system: a LOCS III-based hybrid model achieving high-precision classification

Year: 2025

Type: article

Abstract: Purpose: To design an artificial intelligence (AI) algorithm based on the Lens Opacities Classification System III (LOCS III) to realize automatic diagnosis of cataracts and classification of its. Methods: This retrospective study develops an AI-based neural network to diagnose cataracts and grade lens opacity. According to the LOCS III, cataracts are classified into Nuclear Opalescence (NO), Nuclear Color (NC), Cortical(C) and Posterior subcapsular(P). The newly developed neural network system uses grayscale, binarization, cluster analysis, "dilation-corrosion" and other methods to process and analyze the images, then the study need to test and evaluate the generalization ability of the system. Results: The new neural network system can identify 100% of lens anatomy. It has an accuracy of 92.28%-100% in the diagnosis of nuclear cataract, cortical cataract and posterior subcapsular cataract. The classification accuracy rate of the system for cataract NO, NC, C, P is between 90.88% and 100%, the Area Under the Curve (AUC) is between 96.68% and 100%. Conclusion: A novel cataract diagnostic and grading system can be developed based on the AI recognition algorithm, which establishes an automatic cataract diagnosis and grading scheme. The system facilitates rapid and accurate cataract diagnosis and grading.

Source: Frontiers in Cell and Developmental Biology

DOI: 10.3389/fcell.2025.1669696

Authors: Gege Tang, Jie Zhang, Yingqi Du, Dexun Jiang, Yanhua Qi, Nan Zhou

Institutions: Harbin Medical University, Second Affiliated Hospital of Harbin Medical University, Harbin Institute of Technology, Harbin University

Language: English

Topic: Retinal Imaging and Analysis

Subfield: Radiology, Nuclear Medicine and Imaging

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: gold

Estimated APC paid: $3,801