Gradient based Severity Labeling for Biomarker Classification in OCT
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908848738009088 |
|---|---|
| author | Kokilepersaud, Kiran Prabhushankar, Mohit AlRegib, Ghassan Corona, Stephanie Trejo Wykoff, Charles |
| author_facet | Kokilepersaud, Kiran Prabhushankar, Mohit AlRegib, Ghassan Corona, Stephanie Trejo Wykoff, Charles |
| contents | In this paper, we propose a novel selection strategy for contrastive learning for medical images. On natural images, contrastive learning uses augmentations to select positive and negative pairs for the contrastive loss. However, in the medical domain, arbitrary augmentations have the potential to distort small localized regions that contain the biomarkers we are interested in detecting. A more intuitive approach is to select samples with similar disease severity characteristics, since these samples are more likely to have similar structures related to the progression of a disease. To enable this, we introduce a method that generates disease severity labels for unlabeled OCT scans on the basis of gradient responses from an anomaly detection algorithm. These labels are used to train a supervised contrastive learning setup to improve biomarker classification accuracy by as much as 6% above self-supervised baselines for key indicators of Diabetic Retinopathy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19907 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Gradient based Severity Labeling for Biomarker Classification in OCT Kokilepersaud, Kiran Prabhushankar, Mohit AlRegib, Ghassan Corona, Stephanie Trejo Wykoff, Charles Computer Vision and Pattern Recognition Machine Learning In this paper, we propose a novel selection strategy for contrastive learning for medical images. On natural images, contrastive learning uses augmentations to select positive and negative pairs for the contrastive loss. However, in the medical domain, arbitrary augmentations have the potential to distort small localized regions that contain the biomarkers we are interested in detecting. A more intuitive approach is to select samples with similar disease severity characteristics, since these samples are more likely to have similar structures related to the progression of a disease. To enable this, we introduce a method that generates disease severity labels for unlabeled OCT scans on the basis of gradient responses from an anomaly detection algorithm. These labels are used to train a supervised contrastive learning setup to improve biomarker classification accuracy by as much as 6% above self-supervised baselines for key indicators of Diabetic Retinopathy. |
| title | Gradient based Severity Labeling for Biomarker Classification in OCT |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2602.19907 |