Foundation Models vs. Radiomics for Lung Computed Tomography: A Benchmark of Feature Extractors, Classification Heads, and Segmentation Choices
arXiv:2607.01001v1 Announce Type: cross Abstract: Radiomics is the established approach for CT-based lung cancer phenotyping, yet comparisons with foundation models rarely isolate contributions of feature extractor, classification head, and segmentation choice, or test cross-cohort robustness. We benchmark five feature extractors (Curia, Curia-2, DINOv3, Radiomics2D, Radiomics3D), seven classification heads (TabPFN, TabICL, XGBoost, CatBoost, Random Forest, logistic regression, Ridge), and three segmentation regimes on five tasks: tumor volume and stage classification, 2-year survival predicti
The proliferation of foundation models and increasing sophistication of medical AI necessitates rigorous benchmarking to understand their practical utility in clinical settings.
This research provides critical insights into the performance and robustness of AI techniques for medical imaging, influencing clinical diagnostics and treatment pathways.
The systematic comparison of AI components in medical imaging allows for more informed development and adoption of AI-driven diagnostic tools.
- · AI developers in healthcare
- · Healthcare providers adopting AI
- · Patients receiving AI-assisted diagnoses
- · Traditional radiomics-only approaches
- · AI models lacking cross-cohort robustness
Improved reliability and accuracy of AI for lung cancer detection and prediction.
Accelerated integration of AI foundation models into clinical workflows and diagnostic software.
Potential for early and more personalized interventions, leading to better patient outcomes and resource allocation in healthcare.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG