aiqbench analysis
This research addresses the critical challenge of deploying AI radiomic systems in clinical settings by developing a statistical framework to quantify model sensitivity to CT acquisition parameters. By identifying specific parameter regions that enhance cross-dataset robustness, the study offers actionable insights for improving the reliability and transferability of predictive models across heterogeneous multicenter environments. The work directly advances machine learning methodology within medical imaging, focusing on generalization rather than just raw performance metrics.
A Statistical Multi-Objective Framework for Assessing Sensitivity of Radiomic AI Models to Acquisition Parameters
arXiv:2605.14667v2 Announce Type: replace Abstract: A main barrier for the deployment of AI radiomic systems in clinical routine is their drop in performance under heterogeneous multicentre acquisition protocols. This work presents a performance-oriented framework for quantifying scan parameter sensitivity of radiomic AI models, while identifying clinically significant parameter regions associated with improved cross-dataset robustness. Mixed-effects modelling in combination with a hierarchical Pareto-based strategy is used to quantify the influence of acquisition parameters and select critical values associated to low performance of predictive models. We apply our framework to lung cancer diagnosis in CT scans using two independent multicentre datasets (a public dataset and own-collected private data) and several state-of-the-art architectures. To evaluate transferability of results, CT parameters were selected using the private data and validated on the public set. With the selected configurations, validation in low performance conditions has 0.72 ([0.59,0.86], 95% CI) accuracy and 0.71 ([0.58, 0. 84], 95% CI) F1Score, while in high performance ones, we obtain 0.88 ([0.7, 1.0], 95% CI) accuracy with 0.87 ([0.69, 1.0], 95% CI) F1Score.
Abstract:A main barrier for the deployment of AI radiomic systems in clinical routine is their drop in performance under heterogeneous multicentre acquisition protocols. This work presents a performance-oriented framework for quantifying scan parameter sensitivity of radiomic AI models, while identifying clinically significant parameter regions associated with improved cross-dataset robustness. Mixed-effects modelling in combination with a hierarchical Pareto-based strategy is used to quantify the influence of acquisition parameters and select critical values associated to low performance of predictive models. We apply our framework to lung cancer diagnosis in CT scans using two independent multicentre datasets (a public dataset and own-collected private data) and several state-of-the-art architectures. To evaluate transferability of results, CT parameters were selected using the private data and validated on the public set. With the selected configurations, validation in low performance conditions has 0.72 ([0.59,0.86], 95% CI) accuracy and 0.71 ([0.58, 0. 84], 95% CI) F1Score, while in high performance ones, we obtain 0.88 ([0.7, 1.0], 95% CI) accuracy with 0.87 ([0.69, 1.0], 95% CI) F1Score.
Artificial Intelligence (cs.AI)
arXiv:2605.14667 [cs.AI]
(or arXiv:2605.14667v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2605.14667 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.
Full text under the publisher's open licence · 259 words
Related coverage
The Continual Constitutional Convention: How language models revise the documents that govern them
AI Alignment Forum · Oct 13, 2026
Generative Augmentation of Imbalanced Flight Records for Flight Diversion Prediction: A Multi-objective Optimisation Framework
arXiv · Jul 21, 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · Sep 17, 2026
The Entangled Dimensions of Decision Theory
LessWrong · Jul 30, 2026