Abstract
Automated pneumonia screening from chest X-rays can reduce diagnostic delays where radiologists are scarce. Safe deployment requires that model uncertainty reliably signals imminent misclassification when image quality degrades due to hardware limitations. We benchmark four uncertainty quantification (UQ) methods (softmax confidence, ensemble entropy, MC Dropout, temperature scaling) across three compact backbones (MobileNetV3-Small, EfficientNet-B0, ConvNeXt-Tiny) fine-tuned on PneumoniaMNIST. We evaluate all 13 MedMNIST-C corruptions at five severity levels. While all backbones achieve 83–86% clean accuracy, EfficientNet-B0 accuracy collapses to ≈71% at corruption severity 1. MobileNetV3-Small and ConvNeXt-Tiny maintain clean-set performance, though ConvNeXt-Tiny exhibits poor calibration (ECE 16.5%). Temperature scaling consistently reduces ECE; ensemble entropy provides the strongest failure detection (AUROC 0.804 clean). All methods sustain failure detection AUROC above 0.75 under mild corruption but degrade at high severities, demonstrating that image quality monitoring remains essential for safe triage.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/MIRASOL_043.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=ACHWvaycse
BibTex
@InProceedings{ShiNun_Silent_MICCAISAT2026,
author = { Shiaki, Nunsi AND Oladepo, Oluwaferanmi},
title = { { Silent Failures in Degraded Chest X-Rays: Benchmarking Uncertainty Methods for Pneumonia Triage in Resource-Constrained Settings } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17265},
month = {pending},
page = {pending}
}