How Sensitive Are Radiomic AI Models to Acquisition Parameters?
For clinical deployment of radiomic AI, this work provides a method to identify robust acquisition protocols, addressing the barrier of performance drops under heterogeneous multicentre conditions.
The paper presents a framework to quantify how acquisition parameters affect radiomic AI model performance, identifying optimal CT settings (tube current ≥200 mA, pitch ≤1.5, slice thickness ≤1.25 mm) that improve sensitivity from 0.79 to 0.90 and specificity from 0.47 to 0.79 in lung cancer diagnosis.
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. We formulate a mixed-effects framework for quantifying the influence that clinically relevant acquisition parameters have on models performance, while accounting for subject-level random effects. We have applied our framework to lung cancer diagnosis in CT scans using two independent multicentre datasets (a public database and own-collected data) and several SoA architectures. To evaluate across-database reproducibility, CT parameters have been adjusted using the data collected and tested on the public set. The optimal configuration selected is the current of the X-ray tube >= 200 mA, spiral pitch <= 1.5, slice thickness <= 1.25 mm, which balances diagnostic quality with low radiation dose. These configuration push metrics from 0.79+-0.04 sensitivity, 0.47+-0.10 specificity in low quality scans to 0.90+-0.10 sensitivity, 0.79 +- 0.13 specificity in high quality ones.