Accurate and Explainable Cataract Detection Using Eye Images Taken by Hand-held Slit-lamp Cameras
Bibliographic record
Abstract
Cataract is a leading cause of visual impairment in the elderly. With a greying population globally, there is a pressing need to improve the accessibility of cataract screening. Hand-held Slit-lamp Cameras (HSCs) are often preferred in community eye screening due to their great portability and accessibility. However, the image quality from HSCs is generally inferior to that from conventional bulky fundus cameras. In this paper, we extend the pre-trained ResNet-18 neural network to analyze a limited number of HSC images (n=187) for cataract detection. Model accuracy is improved through augmenting training data samples and complementing the visual features with patients’ vision measurements. Explainability (of focal model areas for decision making) is attained via extracting the saliency maps using the Grad-CAM method. Our model achieves a high accuracy of 0.96, on par with state-of-the-art results reported in the literature. Our approach demonstrates the potential of large-scale community-based cataract detection using HSCs and our highly accurate and explainable AI-assisted model.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".