RADR: A Robust Domain-Adversarial-based Framework for Automated Diabetic Retinopathy Severity Classification

Sara Mı́nguez Monedero, Fabian Westhaeusser, Ehsan Yaghoubi, Simone Frintrop, Marina Zimmermann
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:1026-1039, 2024.

Abstract

Diabetic retinopathy (DR), a potentially vision-threatening condition, necessitates accurate diagnosis and staging, which deep-learning models can facilitate. However, these models often struggle with robustness in clinical practice due to distribution shifts caused by variations in data acquisition protocols and hardware. We propose RADR, a novel deep-learning framework for DR severity classification, aimed at generalization across diverse datasets and clinic cameras. Our work builds upon existing research: we combine several ideas to perform extensive dataset curation, preprocessing, and enrichment with camera information. We then use a domain adversarial training regime, which encourages our model to extract features that are both task-relevant and invariant to domain shifts. We explore our framework in its various levels of complexity in combination with multiple data augmentations policies in an ablative fashion. Experimental results demonstrate the effectiveness of our proposed method, achieving competitive performance to multiple state-of-the-art models on three unseen external datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-monedero24a, title = {RADR: A Robust Domain-Adversarial-based Framework for Automated Diabetic Retinopathy Severity Classification}, author = {Monedero, Sara M{\'\i}nguez and Westhaeusser, Fabian and Yaghoubi, Ehsan and Frintrop, Simone and Zimmermann, Marina}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {1026--1039}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/monedero24a/monedero24a.pdf}, url = {https://proceedings.mlr.press/v250/monedero24a.html}, abstract = {Diabetic retinopathy (DR), a potentially vision-threatening condition, necessitates accurate diagnosis and staging, which deep-learning models can facilitate. However, these models often struggle with robustness in clinical practice due to distribution shifts caused by variations in data acquisition protocols and hardware. We propose RADR, a novel deep-learning framework for DR severity classification, aimed at generalization across diverse datasets and clinic cameras. Our work builds upon existing research: we combine several ideas to perform extensive dataset curation, preprocessing, and enrichment with camera information. We then use a domain adversarial training regime, which encourages our model to extract features that are both task-relevant and invariant to domain shifts. We explore our framework in its various levels of complexity in combination with multiple data augmentations policies in an ablative fashion. Experimental results demonstrate the effectiveness of our proposed method, achieving competitive performance to multiple state-of-the-art models on three unseen external datasets.} }
Endnote
%0 Conference Paper %T RADR: A Robust Domain-Adversarial-based Framework for Automated Diabetic Retinopathy Severity Classification %A Sara Mı́nguez Monedero %A Fabian Westhaeusser %A Ehsan Yaghoubi %A Simone Frintrop %A Marina Zimmermann %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-monedero24a %I PMLR %P 1026--1039 %U https://proceedings.mlr.press/v250/monedero24a.html %V 250 %X Diabetic retinopathy (DR), a potentially vision-threatening condition, necessitates accurate diagnosis and staging, which deep-learning models can facilitate. However, these models often struggle with robustness in clinical practice due to distribution shifts caused by variations in data acquisition protocols and hardware. We propose RADR, a novel deep-learning framework for DR severity classification, aimed at generalization across diverse datasets and clinic cameras. Our work builds upon existing research: we combine several ideas to perform extensive dataset curation, preprocessing, and enrichment with camera information. We then use a domain adversarial training regime, which encourages our model to extract features that are both task-relevant and invariant to domain shifts. We explore our framework in its various levels of complexity in combination with multiple data augmentations policies in an ablative fashion. Experimental results demonstrate the effectiveness of our proposed method, achieving competitive performance to multiple state-of-the-art models on three unseen external datasets.
APA
Monedero, S.M., Westhaeusser, F., Yaghoubi, E., Frintrop, S. & Zimmermann, M.. (2024). RADR: A Robust Domain-Adversarial-based Framework for Automated Diabetic Retinopathy Severity Classification. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:1026-1039 Available from https://proceedings.mlr.press/v250/monedero24a.html.

Related Material