mlsanityData to 14 Oct 2026

SPARCL: Spatially Adaptive Regional Coverage for Active Learning in Chest X-ray Analysis

arXiv 2610.17808 ↗First posted 13 Oct 2026cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Pixel-level annotation for chest X-ray (CXR) lesion segmentation is expensive, making active learning (AL) essential. However, existing AL strategies fail to account for the spatial distribution of selected samples, resulting in inconsistent performance across focal (e.g., aortic calcification) and diffuse (e.g., nodules) pathologies. In this paper, we propose SPARCL (Spatially Adaptive Regional Coverage for Active Learning) to dynamically balance predictive uncertainty with cumulative spatial coverage. By employing a concave coverage function, SPARCL imposes diminishing returns on previously annotated regions, naturally directing the annotation budget toward under-labeled areas. Furthermore, an entropy gate reverts the algorithm to standard uncertainty sampling when spatial variation is absent. This coverage objective is monotone submodular, guaranteeing near-optimal greedy batch selection. To address how aggregate metrics like Dice obscure regional failures, we further introduce two metrics---Spatial Inconsistency (SI) and Performance Coverage (PC)---to quantify anatomical fairness across AL rounds. Evaluated on an in-house calcification cohort and public CXR benchmarks, SPARCL reaches 95% of fully supervised performance using only 24% of the data, compared to 29% for the best baseline. Ultimately, SPARCL ensures robust spatial reliability, surfacing regional gains that aggregate metrics miss.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 46 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

33 of 46 references.

References · 33

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,423
  5. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 972
  6. 2017Deep Bayesian Active Learning with Image Datacited by 819
  7. 2017Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentationscited by 620
  8. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 610
  9. 2020A Survey of Deep Active Learningcited by 554
  10. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 432
  11. 2019Learning Loss for Active Learningcited by 336
  12. 2020VinDr-CXR: An open dataset of chest X-rays with radiologist's annotationscited by 239
21 more
  1. 2022Metrics reloaded: Recommendations for image analysis validationcited by 195
  2. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 166
  3. 2019A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysiscited by 151
  4. 2017Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentationcited by 146
  5. 2022Active Learning on a Budget: Opposite Strategies Suit High and Low Budgetscited by 133
  6. 2019ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentationcited by 96
  7. 2022Active Learning Through a Covering Lenscited by 66
  8. 2021Common Limitations of Image Processing Metrics: A Picture Storycited by 59
  9. 2021Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentationcited by 57
  10. 2018CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentationcited by 49
  11. 2021Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentationcited by 45
  12. 2017Cost-Effective Active Learning for Melanoma Segmentationcited by 41
  13. 2020ChestX-Det10: Chest X-ray Dataset on Detection of Thoracic Abnormalitiescited by 38
  14. 2021A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentationcited by 34
  15. 2021All you need are a few pixels: semantic segmentation with PixelPickcited by 31
  16. 2023Active learning for medical image segmentation with stochastic batchescited by 21
  17. 2018MedAL: Deep Active Learning Sampling Method for Medical Image Analysiscited by 20
  18. 2024Predictive Accuracy-Based Active Learning for Medical Image Segmentationcited by 4
  19. 2023EdgeAL: An Edge Estimation Based Active Learning Approach for OCT Segmentationcited by 3
  20. 2023Two-Step Active Learning for Instance Segmentation with Uncertainty and Diversity Samplingcited by 1
  21. 2025Exploring Spatial Diversity for Region-based Active Learningcited by 1

Built on by

Not cited yet.