Previously submitted to: JMIR Medical Informatics (no longer under consideration since Aug 31, 2026)
Date Submitted: Aug 4, 2026
Open Peer Review Period: Aug 31, 2026 - Aug 31, 2026
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Diabetic retinopathy classification algorithm based on a multi-feature fusion network model with dual attention mechanism
ABSTRACT
Background:
Background:
Diabetic retinopathy, the most common microvascular complication of diabetes, is difficult to detect early due to its subtle initial lesions. Current screening methods often miss these minute lesions, such as microaneurysms and exudates.
Objective:
Objective:
To overcome the limitation of insufficient sensitivity for detecting minute lesions inherent in existing screening methods, a diabetic retinopathy classification algorithm is proposed based on a multi-feature fusion network model with a dual attention mechanism.
Methods:
Methods:
First, contrast-limited adaptive histogram equalization and Gaussian difference amplification enhancement algorithms are employed. These algorithms effectively extract multi-lesion features of microaneurysms, hemorrhages, and exudates. This process enriches the training dataset with enhanced lesion representations across different stages. Simultaneously, a dual spatial-channel attention module is designed. The spatial attention module employs deformable convolution to dynamically focus on multi-scale lesion regions. The channel attention module utilizes global context awareness to filter discriminative features. The dual attention module is then embedded within the YOLOv8 backbone network. It is combined with a dynamic weight allocation strategy to form the multi-feature fusion network model. This model enhances the accuracy of identifying subtle lesions.
Results:
Results:
The proposed algorithm achieves accuracies of 96.90% and 92.72% on the APTOS 2019 and IDRiD datasets, respectively, for five-class classification.
Conclusions:
Conclusions:
The study provides a highly robust solution for clinical diabetic retinopathy screening and demonstrates significant potential for clinical application.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.