Metraipolis › archive › dc_ff35804475c1

Improving Calibration of Black-Box Radiology AI Using Test-Time Augmentation — arXiv:2609.29931

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29931
License (as archived)
CC0-1.0
Archived
2026-10-08T05:25:29.691Z
SHA-256 of the archived text
373cce46781d731b090fad709ca4e3514477658d37baa1ed8d1c2b8613e457b0
Stable URL of this page
https://metraipolis.com/documento/dc_ff35804475c1

How to cite

Improving Calibration of Black-Box Radiology AI Using Test-Time Augmentation — arXiv:2609.29931 — arXiv (en), https://arxiv.org/abs/2609.29931 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff35804475c1 (Metraipolis archive dc_ff35804475c1, sha256 373cce46781d731b090fad709ca4e3514477658d37baa1ed8d1c2b8613e457b0)
BibTeX
@misc{dcff35804475c1,
  title = {Improving Calibration of Black-Box Radiology AI Using Test-Time Augmentation — arXiv:2609.29931},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29931},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff35804475c1; sha256 373cce46781d731b090fad709ca4e3514477658d37baa1ed8d1c2b8613e457b0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29931. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Radiology AI systems increasingly inform clinical decisions such as triage, follow-up imaging, and treatment planning. For these decisions to be made safely, model outputs must be well calibrated, meaning predicted probabilities accurately reflect true risk. Many standard techniques for improving calibration, such as MC Dropout and Deep Ensembles, require access to model parameters or retraining. However, proprietary clinical AI systems operate as black boxes, preventing access to the model's internals. To that end, we propose a model-agnostic framework for improving calibration of black-box models using clinically grounded test-time augmentation (TTA). Our framework applies geometric and physics-inspired 3D CT perturbations and learns probability-level aggregation strategies without access to model internals or the original training data. Across pulmonary embolism and intracranial hemorrhage detection tasks, DualTTA achieved the strongest overall calibration among TTA methods, reducing the Expected Calibration Error by 54% (0.239 -> 0.109) and 43% (0.051 -> 0.029), respectively, while requiring only input-output access. Additionally, DualTTA outperformed uncertainty estimation techniques that require access to model internals, such as Temperature Scaling, MC Dropout, and Deep Ensembles, in most calibration metrics. These results demonstrate that learned TTA aggregation can improve the calibration of clinical AI systems, providing a practical approach for improving the reliability of black-box medical AI.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.HC).
Categorie arXiv: Machine Learning (cs.LG) ; Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2609.29931 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T04:50:17.687Z dalla pagina https://arxiv.org/catchup/cs.HC/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).