MétaCan
Menu
Back to cohort

A Comparative Study of Convolutional Layer Depths and Activation Functions in the Detection and Classification of Diabetic Retinopathy

2025· article· W7123349787 on OpenAlexafffund
Saxon Vandenwollenberg, S. Chitte, Sudipta Modak, Esam Abdel-Raheem

Bibliographic record

Venuenot available
Typearticle
Language
FieldMedicine
TopicRetinal Imaging and Analysis
Canadian institutionsUniversity of Windsor
FundersUniversity of Windsor
KeywordsDiabetic retinopathyRetinopathyConvolutional neural networkPattern recognition (psychology)RetinalBinary classificationField (mathematics)

Abstract

fetched live from OpenAlex

Traditional diabetic retinopathy diagnosis is a timeconsuming approach and is limited by the availability of specialists. Deep learning systems are a solution to the constraints, as they can efficiently and accurately detect anomalies in large datasets of retinal images. This work presents a comparative study of convolutional neural networks trained from scratch compared to traditional pretrained models in the field of diabetic retinopathy classification. In this work, four mid-range models are presented that display how different combinations of convolutions, activation functions, and layer depths can be used to achieve high performance in diabetic retinopathy classification without large-scale pretraining. Furthermore, the test performances of these models are compared to several pretrained models in the field to investigate how different architectures affect the accuracy of binary classification. The models are trained and tested on open-source datasets such as Eyepacs, Aptos, Aptos (Gaussian Filtered), and Messidor DR. The highest test accuracy achieved is 87.60 % for the presence of diabetic retinopathy versus the absence of diabetic retinopathy and 88.38 % for the distinction between non-proliferative diabetic retinopathy and proliferative diabetic retinopathy.

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)0.001
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: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.197
Threshold uncertainty score0.362

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
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 head0.041
GPT teacher head0.324
Teacher spread0.283 · 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 designObservational
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

Citations0
Published2025
Admission routes2
Has abstractyes

Explore more

Same topicRetinal Imaging and AnalysisFrench-language works237,207