Related Experiment Video
Updated: Jan 17, 2026

04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
3.3K
Artificial intelligence in cataract grading system: a LOCS III-based hybrid model achieving high-precision
Gege Tang1, Jie Zhang2, Yingqi Du1
1Department of Ophthalmology, The Second Affiliated Hospital, Harbin Medical University, Harbin, China.
Frontiers in Cell and Developmental Biology
|September 25, 2025
Summary
An AI algorithm accurately diagnoses and grades cataracts, classifying lens opacities. This artificial intelligence system offers rapid and precise cataract detection and grading.
Area of Science:
- Ophthalmology
- Artificial Intelligence
- Medical Imaging
Background:
- Cataracts are a leading cause of vision impairment.
- Accurate diagnosis and grading of cataracts are crucial for effective treatment.
- Existing methods for cataract assessment can be subjective and time-consuming.
Purpose of the Study:
- To develop an artificial intelligence (AI) algorithm for automatic cataract diagnosis and classification.
- To base the AI algorithm on the Lens Opacities Classification System III (LOCS III).
Main Methods:
- A retrospective study utilizing an AI-based neural network.
- The system employs image processing techniques like grayscale analysis, binarization, cluster analysis, and morphological operations (dilation-corrosion).
- Evaluation of the system's generalization ability was performed.
Main Results:
- The AI system achieved 100% accuracy in identifying lens anatomy.
- Diagnostic accuracy for nuclear, cortical, and posterior subcapsular cataracts ranged from 92.28% to 100%.
- Classification accuracy for specific cataract types (NO, NC, C, P) was between 90.88% and 100%, with Area Under the Curve (AUC) values from 96.68% to 100%.
Conclusions:
- A novel AI-driven system for cataract diagnosis and grading has been developed.
- The system provides an automated scheme for rapid and accurate cataract assessment.
- This AI algorithm facilitates efficient and precise clinical decision-making in ophthalmology.

