Gradient based Severity Labeling for Biomarker Classification in OCT

• URL: http://arxiv.org/abs/2602.19907v1
• Date: Mon, 23 Feb 2026 14:46:08 GMT
• Title: Gradient based Severity Labeling for Biomarker Classification in OCT
• Authors: Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib, Stephanie Trejo Corona, Charles Wykoff,
• Abstract summary: We propose a novel selection strategy for contrastive learning for medical images.<n>We generate disease severity labels for unlabeled OCT scans on the basis of gradient responses from an anomaly detection algorithm.<n>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 Diabetic Retinopathy.
• Score: 11.838633131911648
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Clinically Labeled Contrastive Learning for OCT Biomarker Classification [12.633032175875865]
  This paper presents a novel strategy for contrastive learning of medical images based on labels that can be extracted from clinical data. We exploit this relationship by using the clinical data as pseudo-labels for our data without biomarker labels. We show performance improvements by as much as 5% in total biomarker detection AUROC.
  arXiv  Detail & Related papers  (2023-05-24T13:51:48Z)
• Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective [51.70661197256033]
  We propose ARCO, a semi-supervised contrastive learning framework with stratified group theory for medical image segmentation. We first propose building ARCO through the concept of variance-reduced estimation and show that certain variance-reduction techniques are particularly beneficial in pixel/voxel-level segmentation tasks. We experimentally validate our approaches on eight benchmarks, i.e., five 2D/3D medical and three semantic segmentation datasets, with different label settings.
  arXiv  Detail & Related papers  (2023-02-03T13:50:25Z)
• Stain-invariant self supervised learning for histopathology image analysis [74.98663573628743]
  We present a self-supervised algorithm for several classification tasks within hematoxylin and eosin stained images of breast cancer. Our method achieves the state-of-the-art performance on several publicly available breast cancer datasets.
  arXiv  Detail & Related papers  (2022-11-14T18:16:36Z)
• Clinical Contrastive Learning for Biomarker Detection [15.510581400494207]
  We exploit the relationship between clinical and biomarker data to improve performance for biomarker classification. This is accomplished by leveraging the larger amount of clinical data as pseudo-labels for our data without biomarker labels. Our method is shown to outperform state of the art self-supervised methods by as much as 5% in terms of accuracy on individual biomarker detection.
  arXiv  Detail & Related papers  (2022-11-09T18:29:56Z)
• Less is More: Adaptive Curriculum Learning for Thyroid Nodule Diagnosis [50.231954872304314]
  We propose an Adaptive Curriculum Learning framework, which adaptively discovers and discards the samples with inconsistent labels. We also contribute TNCD: a Thyroid Nodule Classification dataset.
  arXiv  Detail & Related papers  (2022-07-02T11:50:02Z)
• Texture Characterization of Histopathologic Images Using Ecological Diversity Measures and Discrete Wavelet Transform [82.53597363161228]
  This paper proposes a method for characterizing texture across histopathologic images with a considerable success rate. It is possible to quantify the intrinsic properties of such images with promising accuracy on two HI datasets.
  arXiv  Detail & Related papers  (2022-02-27T02:19:09Z)
• Weakly-supervised learning for image-based classification of primary melanomas into genomic immune subgroups [1.4585861543119112]
  We develop deep learning models to classify gigapixel H&E stained pathology slides into immune subgroups. We leverage a multiple-instance learning approach, which only requires slide-level labels and uses an attention mechanism to highlight regions of high importance to the classification.
  arXiv  Detail & Related papers  (2022-02-23T13:57:35Z)
• Dementia Severity Classification under Small Sample Size and Weak Supervision in Thick Slice MRI [3.0681909921734416]
  Early detection of dementia plays a critical role in developing support strategies. We propose to classify the disease severity based on the Fazekas scale through the visual biomarkers. Small training sample size and weak supervision in form of assigning severity labels to the whole MRI stack are among the main challenges.
  arXiv  Detail & Related papers  (2021-03-18T07:33:57Z)
• Lung Nodule Classification Using Biomarkers, Volumetric Radiomics and 3D CNNs [0.0699049312989311]
  We present a hybrid algorithm to estimate lung malignancy that combines imaging biomarkers from Radiologist's annotation with image classification of CT scans. Our algorithm employs a 3D Convolutional Neural Network (CNN) as well as a Random Forest in order to combine CT imagery with biomarker annotation and radiomic features. We show that a model using image biomarkers alone is more accurate than one that combines biomarkers with volumetric radiomics, 3D CNNs, and semi-supervised learning.
  arXiv  Detail & Related papers  (2020-10-19T18:57:26Z)
• Multi-label Thoracic Disease Image Classification with Cross-Attention Networks [65.37531731899837]
  We propose a novel scheme of Cross-Attention Networks (CAN) for automated thoracic disease classification from chest x-ray images. We also design a new loss function that beyond cross-entropy loss to help cross-attention process and is able to overcome the imbalance between classes and easy-dominated samples within each class.
  arXiv  Detail & Related papers  (2020-07-21T14:37:00Z)
• Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Model [71.80319052891817]
  We present a relation-driven semi-supervised framework for medical image classification. It exploits the unlabeled data by encouraging the prediction consistency of given input under perturbations. Our method outperforms many state-of-the-art semi-supervised learning methods on both single-label and multi-label image classification scenarios.
  arXiv  Detail & Related papers  (2020-05-15T06:57:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.