Transferability of cost-sensitive threshold policies in pneumoniamnist: Calibration, resampling, and image-integrity sensitivity
Imaging and Radiation Research · 30.10.2026 · 9 (1) · 1
DOI: 10.24294/irr026410003 ↗Kurz gefasst
Fachartikel in der Zeitschrift Imaging and Radiation Research, online erschienen am 30.10.2026. Verfasst von Arvy Noleal Osma und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Background
Validation-selected thresholds may fail to retain their apparent error-cost advantage across imaging benchmark partitions, even with satisfactory discrimination.
Objective
To examine transferability of fixed, analytical cost-based, and validation-selected classification policies in PneumoniaMNIST, with threshold-selection uncertainty and sensitivity analyses.
Methods
We analyzed 5,856 28 × 28 pediatric chest radiographs (4,708 training; 524 source validation; 624 testing). Eight exact train-validation overlaps were excluded from validation procedures. A 100-component logistic baseline and compact convolutional neural network (CNN) were evaluated under four hypothetical false-negative/false-positive cost ratios. Revision-stage analyses included 500 validation-threshold resamples, 1,000 paired test resamples, exact-score threshold searches, class-composition standardization, calibration diagnostics, three CNN seeds, training-duplicate removal, and a development-role-separated sensitivity experiment.
Results
Logistic and temperature-scaled CNN test AUCs were 0.921 and 0.925. At equal costs, the logistic tuned-versus-analytical loss difference was −0.0192 per image, whereas the CNN loss difference was +0.0144. CNN temperature scaling increased Brier score from 0.1303 to 0.1325 and test log loss from 0.5524 to 0.5951. At a 2:1 cost ratio, the logistic validation threshold was 0.13, with a bootstrap interval of 0.05–0.63.
Conclusions
Threshold-policy gains were model- and cost-dependent, and validation selection was unstable. All new comparisons are retrospective exploratory benchmark analyses; patient-level independence and clinical utility remain unverified.
Zitieren
APA
Osma, A. N., & Balao, M. A. (2026). Transferability of cost-sensitive threshold policies in pneumoniamnist: Calibration, resampling, and image-integrity sensitivity. Imaging and Radiation Research, 9(1), 1. https://doi.org/10.24294/irr026410003
Vancouver
Osma AN, Balao MA. Transferability of cost-sensitive threshold policies in pneumoniamnist: Calibration, resampling, and image-integrity sensitivity. Imaging and Radiation Research. 2026;9(1):1. doi:10.24294/irr026410003
BibTeX
@article{Osma2026,
author = {Osma, Arvy Noleal and Balao, Mark Andre},
title = {Transferability of cost-sensitive threshold policies in pneumoniamnist: Calibration, resampling, and image-integrity sensitivity},
journal = {Imaging and Radiation Research},
year = {2026},
volume = {9},
number = {1},
pages = {1},
doi = {10.24294/irr026410003}
}
EUVIMED