MétaCan
Menu
Back to cohort
Record W4401110165 · doi:10.1109/cai59869.2024.00024

Accurate and Explainable Cataract Detection Using Eye Images Taken by Hand-held Slit-lamp Cameras

2024· article· en· W4401110165 on OpenAlexaff
Daniel Kai Xiang Fung, Di Wang, Hao Wang, Yongwei Wang, Pengcheng Wu, Yan Yee Hah, Chee Chew Yip, Wee Jin Heng, Tock Han Lim, Cyril Leung, Chunyan Miao

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldMedicine
TopicRetinal Imaging and Analysis
Canadian institutionsBC Research (Canada)
FundersHORIZON EUROPE HealthNg Teng Fong Charitable Foundation
KeywordsSlit lampSlitComputer scienceComputer visionArtificial intelligenceOpticsOptometryMedicinePhysics

Abstract

fetched live from OpenAlex

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 imitation

Not 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.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.226
Threshold uncertainty score0.405

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.015
GPT teacher head0.311
Teacher spread0.296 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

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".

Quick stats

Citations2
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicRetinal Imaging and AnalysisFrench-language works237,207