An automated method of identifying incorrectly labelled images based on the sequences of loss functions of deep learning networks

• URL: http://arxiv.org/abs/2607.02594v1
• Date: Wed, 01 Jul 2026 08:19:38 GMT
• Title: An automated method of identifying incorrectly labelled images based on the sequences of loss functions of deep learning networks
• Abstract summary: Up to 10% of manually labelled medical images may be incorrect, degrading model performance.<n>This paper proposes an automated method to identify incorrectly labelled medical images by analyzing sequences of loss functions.<n>Identified images can be reviewed and relabelled by experts, improving dataset quality and model performance.
• Score: 17.829950558862947
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning is widely applied in medical image analysis, but up to 10% of manually labelled images may be incorrect, degrading model performance. This paper proposes an automated method to identify incorrectly labelled medical images by analyzing sequences of loss functions from deep learning classification networks over multiple training epochs. Identified images can be reviewed and relabelled by experts, improving dataset quality and model performance. Two experiments validate the method on a fundus image dataset for referable diabetic retinopathy screening. In the first, 6% (648) of 10,788 gold-standard labels were intentionally flipped. The method identified 75.31% (488) of the flipped samples, with only 4.85% (492) false positives among correctly labelled samples. In the second, reviewing and correcting the 980 identified samples (9.1% of the dataset) and retraining the model improved best accuracy on an independent test set from 95.93% (with 6% label noise) to 96.50% (with 1.5% noise), approaching the ideal 96.57% (with 0% noise). The results demonstrate the method's effectiveness in improving model performance through automated label quality control.

Related papers

• Model Confidence-Guided Multi-Image Fusion of Fundus Images for Diabetic Retinopathy Diagnosis [0.0]
  Early screening for eye diseases is critical in low- and middle-income countries where access to care is limited.<n>We investigate whether a confidence-guided, multi-image diabetic retinopathy diagnosis framework can integrate image filtering with confidence-aware predictions for reliable screening at capture.
  arXiv  Detail & Related papers  (2026-07-03T23:48:32Z)
• X-Mark: Saliency-Guided Robust Dataset Ownership Verification for Medical Imaging [67.85884025186755]
  High-quality medical imaging datasets are essential for training deep learning models, but their unauthorized use raises serious copyright and ethical concerns.<n>Medical imaging presents a unique challenge for existing dataset ownership verification methods designed for natural images.<n>We propose X-Mark, a sample-specific clean-label watermarking method for chest x-ray copyright protection.
  arXiv  Detail & Related papers  (2026-02-10T00:03:43Z)
• Fixed-Threshold Evaluation of a Hybrid CNN-ViT for AI-Generated Image Detection Across Photos and Art [0.0]
  We introduce fixed-threshold evaluation that holds decision thresholds, selected once on clean validation data, fixed across all post-processing transformations.<n>Our hybrid approach achieves balanced crossdomain performance: 91.4% accuracy on tinygenimage photos, 89.7% accuracy on AiData art/graphics, and 98.3% (competitive) on CIFAKE.
  arXiv  Detail & Related papers  (2025-12-25T05:19:09Z)
• GRASP-PsONet: Gradient-based Removal of Spurious Patterns for PsOriasis Severity Classification [0.0]
  We propose a framework to automatically flag problematic training images that introduce spurious correlations.<n>Removing 8.2% of flagged images improves model AUC-ROC by 5% (85% to 90%) on a held out test set.<n>When applied to a subset of training data rated by two dermatologists, the method identifies over 90% of cases with inter-rater disagreement.
  arXiv  Detail & Related papers  (2025-06-27T03:42:09Z)
• Diabetic Retinopathy Detection Based on Convolutional Neural Networks with SMOTE and CLAHE Techniques Applied to Fundus Images [0.0]
  Diabetic retinopathy (DR) is one of the major complications in diabetic patients' eyes.<n>This study aims to evaluate the accuracy of artificial intelligence (AI) in diagnosing DR.
  arXiv  Detail & Related papers  (2025-04-08T05:38:53Z)
• Self-Supervised Radiograph Anatomical Region Classification -- How Clean Is Your Real-World Data? [10.5757425746568]
  We show the effectiveness of self-supervised methods in assigning one of 14 anatomical region classes in our in-house dataset of 48,434 skeletal radiographs.<n>We achieve a strong linear evaluation accuracy of 96.6% with a single model and 97.7% using an ensemble approach.
  arXiv  Detail & Related papers  (2024-12-20T15:07:55Z)
• Improving the accuracy of automated labeling of specimen images datasets via a confidence-based process [9.0255922670433]
  We present and validate an approach that can greatly improve automatic labeling accuracy. We demonstrate that a naive model that produced 86% initial accuracy can achieve improved performance. After validating the approach in a number of ways, we annotate a large dataset of over 600,000 herbarium specimens.
  arXiv  Detail & Related papers  (2024-11-15T09:39:12Z)
• Uncertainty-inspired Open Set Learning for Retinal Anomaly Identification [71.06194656633447]
  We establish an uncertainty-inspired open-set (UIOS) model, which was trained with fundus images of 9 retinal conditions. Our UIOS model with thresholding strategy achieved an F1 score of 99.55%, 97.01% and 91.91% for the internal testing set. UIOS correctly predicted high uncertainty scores, which would prompt the need for a manual check in the datasets of non-target categories retinal diseases, low-quality fundus images, and non-fundus images.
  arXiv  Detail & Related papers  (2023-04-08T10:47:41Z)
• Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders [50.689585476660554]
  We propose a new fine-tuning strategy that includes positive-pair loss relaxation and random sentence sampling. Our approach consistently improves overall zero-shot pathology classification across four chest X-ray datasets and three pre-trained models.
  arXiv  Detail & Related papers  (2022-12-14T06:04:18Z)
• Seamless Iterative Semi-Supervised Correction of Imperfect Labels in Microscopy Images [57.42492501915773]
  In-vitro tests are an alternative to animal testing for the toxicity of medical devices. Human fatigue plays a role in error making, making the use of deep learning appealing. We propose Seamless Iterative Semi-Supervised correction of Imperfect labels (SISSI) Our method successfully provides an adaptive early learning correction technique for object detection.
  arXiv  Detail & Related papers  (2022-08-05T18:52:20Z)
• (Certified!!) Adversarial Robustness for Free! [116.6052628829344]
  We certify 71% accuracy on ImageNet under adversarial perturbations constrained to be within a 2-norm of 0.5. We obtain these results using only pretrained diffusion models and image classifiers, without requiring any fine tuning or retraining of model parameters.
  arXiv  Detail & Related papers  (2022-06-21T17:27:27Z)
• Self-Supervised Learning as a Means To Reduce the Need for Labeled Data in Medical Image Analysis [64.4093648042484]
  We use a dataset of chest X-ray images with bounding box labels for 13 different classes of anomalies. We show that it is possible to achieve similar performance to a fully supervised model in terms of mean average precision and accuracy with only 60% of the labeled data.
  arXiv  Detail & Related papers  (2022-06-01T09:20:30Z)
• To be Critical: Self-Calibrated Weakly Supervised Learning for Salient Object Detection [95.21700830273221]
  Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. We propose a self-calibrated training strategy by explicitly establishing a mutual calibration loop between pseudo labels and network predictions. We prove that even a much smaller dataset with well-matched annotations can facilitate models to achieve better performance as well as generalizability.
  arXiv  Detail & Related papers  (2021-09-04T02:45:22Z)

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.