Noise-aware dynamic convolution for improved generalizability of retinal disease diagnosis using optical coherence tomography images.

Overview

1. Indian Institute of Science, Department of Computational and Data Sciences, Bangalore, Karnataka, India
2. Indian Institute of Science, TANUH-AI Centre of Excellence in Healthcare, Bangalore, Karnataka, India

Abstract

Significance: Optical coherence tomography (OCT) is widely used for the diagnosis of retinal diseases. However, deep learning models trained on a single dataset often degrade when deployed across scanners and clinical sites due to device-dependent speckle variability and acquisition differences, limiting their reliability in real-world screening.

Aim: We aim to develop a lightweight deep learning framework that leverages speckle characteristics in OCT images to improve cross-scanner generalizability for retinal disease classification while preserving real-time inference efficiency.

Approach: We propose NA-DyCNN, a noise-aware dynamic convolutional neural network that minimizes the expected classification risk over multiple stochastic realizations of multiplicative speckle perturbations and regularizes the dynamic routing mechanism to produce scanner-invariant kernel mixtures. The framework was evaluated using over 105,000 B-scans from three heterogeneous OCT cohorts under strict zero-shot cross-dataset transfer.

Results: NA-DyCNN consistently outperformed lightweight baselines across four zero-shot cross-dataset transfer scenarios, achieving up to 92.87% accuracy, a weighted F2 score of 92.89%, and Cohen’s κ of up to 0.896, demonstrating improved robustness and generalization under cross-dataset shifts. The model maintained high efficiency with only 0.4 M parameters and an inference latency of 0.53 ms per B-scan on an NVIDIA GB10 GPU.

Conclusions: Modeling postacquisition speckle variability during training improves the generalizability of OCT classifiers without increasing the inference cost, thereby enabling the more reliable deployment of artificial intelligence (AI)-assisted retinal screening across heterogeneous imaging systems.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data, not to its authors' code: see the Data section.

The paper's code and data availability statement is in the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

• data.mendeley.com/datasets/8kt969dhx6, at Mendeley Data; found in “Code and Data Availability”
• data.mendeley.com/datasets/rscbjbr9sj, at Mendeley Data; found in “Code and Data Availability”
• figshare:3492707, at figshare; found in the references
• figshare:3492722, at figshare; found in the references
• kaggle.com/datasets/obulisainaren, at Kaggle; found in “Code and Data Availability”

Code and Data Availability

All datasets used in this study are publicly available from their respective sources. The UCSD retinal OCT dataset is available at: https://data.mendeley.com/datasets/rscbjbr9sj/2. The NEH retinal OCT dataset can be accessed at: https://data.mendeley.com/datasets/8kt969dhx6/2. The OCT-C8 dataset is available via Kaggle at: https://www.kaggle.com/datasets/obulisainaren/retinal-oct-c8. All datasets were used in accordance with their respective usage policies and licenses.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 2 authors, 6 keywords, 9 MeSH terms, 1 funder, 13 references.

Cite

This paper

Chutani, D., & Yalavarthy, P. K. (2026). Noise-aware dynamic convolution for improved generalizability of retinal disease diagnosis using optical coherence tomography images. Journal of biomedical optics, 31(8), 086006. https://doi.org/10.1117/1.jbo.31.8.086006

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.1038/s41598-026-51120-x [code]

A compact and interpretable multi-source framework for heterogeneous medical image classification.

Journal: Scientific reports

In common: data.mendeley.com/datasets/rscbjbr9sj, other

[2] doi:10.3389/frai.2026.1849571

NeuroPlast: a learnable activation function evaluated under knowledge distillation for medical image classification.

Journal: Frontiers in artificial intelligence

In common: data.mendeley.com/datasets/rscbjbr9sj

[3] doi:10.21037/qims-2025-aw-2093 [code]

Outer retinal band segmentation in healthy subjects: comparative study between human grading and deep convolutional neural networks.

Journal: Quantitative imaging in medicine and surgery

In common: other, 1 reference

[4] doi:10.3390/s26165121 [code]

Electrophysiological Signatures of Sarcopenia: A Systematic Review of sEMG Features, Fatigue Indices and AI-Based Classifiers.

Journal: Sensors (Basel, Switzerland)

In common: other, 1 reference

[5] doi:10.1088/1741-2552/ae4927 [code]

Fuzzing the brain: automated stress testing for the safety of ML-driven neurostimulation.

Journal: Journal of neural engineering

In common: 1 reference

[6] doi:10.3390/jimaging12060251

3D Deep Learning for Brain Tumor Segmentation and Survival Prediction: A Comprehensive Multi-Modal Analysis Using the BraTS2020 Dataset.

Journal: Journal of imaging

In common: 1 reference

[7] doi:10.3389/fnins.2026.1770672 [code]

Multivariate age-related variations in quantitative MRI maps: widespread age-related differences revisited.

Journal: Frontiers in neuroscience

In common: 1 reference

[8] doi:10.1038/s41598-026-48881-w

SleepPACNet: new convolutional neural network considering phase-amplitude coupling for automatic sleep stage classification using single-channel electroencephalogram.

Journal: Scientific reports

In common: 1 reference

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.