analiza aiqbench
This paper tackles a practical constraint in medical imaging: labeling pixel-level lesions in chest X-rays is costly. It proposes an active learning method that adds a spatial-coverage term to uncertainty sampling, so annotation effort spreads across anatomical regions instead of clustering. The reported result (95% of fully supervised performance with 24% of the data, versus 29% for the best baseline) is promising, but it rests on an in-house cohort plus public benchmarks, so readers should check generalization across scanners and patient populations.
SPARCL: Spatially Adaptive Regional Coverage for Active Learning in Chest X-ray Analysis
arXiv:2610.17808v1 Announce Type: cross Abstract: 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.
Abstract: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.
Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)
arXiv:2610.17808 [cs.CV]
(or arXiv:2610.17808v2 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.17808 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 282 cuvinte
Subiecte conexe
Does preservation make sense before we know how to revive?
LessWrong · 15 iun. 2026
Physics-Guided Spatiotemporal Learning for Coastal Wave Peak Period Estimation from Video
arXiv · 12 iun. 2026
The Machines that Make the Machines
NVIDIA · 7 oct. 2026
Efficient Neural Field Learning via Adaptive Coverage and Focused Sampling
arXiv · 6 oct. 2026