analiza aiqbench
This study demonstrates that handcrafted radiomics features provide complementary value alongside foundation models like MedVAE for classifying renal cell carcinoma subtypes on CT scans. The research confirms that integrating structured descriptors with deep image representations, particularly using 3D gated fusion strategies, yields superior diagnostic performance compared to either modality alone. These findings are significant for medical AI applications where combining domain-specific knowledge with transferable learning features enhances clinical decision support.
Complementary Roles of Radiomics and Foundation Representations in Renal Cell Carcinoma Classification: A Comparative Study of 2D and 3D CT Encodings
arXiv:2609.26463v1 Announce Type: cross Abstract: Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced computed tomography remains clinically challenging. Radiomics provides structured tumour descriptors, whereas foundation representations offer transferable image features. However, it remains unclear whether radiomics still adds value beyond pretrained representations, and how 2D and 3D MedVAE encoders compare in this setting. We compared handcrafted radiomics, 2D MedVAE, 3D MedVAE, and their fusion for binary clear-cell RCC versus non-clear-cell RCC classification on KiTS23 under a unified preprocessing pipeline. Concatenation, cross-attention, and gated fusion were evaluated as representative integration strategies, and radiomics feature importance was analysed to support decision-centric interpretability. Fusion consistently improved discrimination over image-only MedVAE branches. The best overall performance was achieved by 3D gated fusion, with an AUC of 82.7\%, outperforming the best 2D fusion model (79.6%), the radiomics baseline (74.4%), and the single-modality MedVAE branches. Ablation analysis further showed clear gains of the full fusion model over both image-only and radiomics-only variants, indicating complementary contributions from radiomics and image representations. These findings suggest that radiomics remains relevant for RCC CT classification in the presence of foundation representations, and that its integration with MedVAE is more effective in the 3D setting. More broadly, the study supports a complementary role for radiomics and foundation representations in clinically meaningful imaging decision support.
Abstract:Accurate preoperative subtype classification of renal cell carcinoma (RCC) from contrast-enhanced computed tomography remains clinically challenging. Radiomics provides structured tumour descriptors, whereas foundation representations offer transferable image features. However, it remains unclear whether radiomics still adds value beyond pretrained representations, and how 2D and 3D MedVAE encoders compare in this setting. We compared handcrafted radiomics, 2D MedVAE, 3D MedVAE, and their fusion for binary clear-cell RCC versus non-clear-cell RCC classification on KiTS23 under a unified preprocessing pipeline. Concatenation, cross-attention, and gated fusion were evaluated as representative integration strategies, and radiomics feature importance was analysed to support decision-centric interpretability. Fusion consistently improved discrimination over image-only MedVAE branches. The best overall performance was achieved by 3D gated fusion, with an AUC of 82.7\%, outperforming the best 2D fusion model (79.6%), the radiomics baseline (74.4%), and the single-modality MedVAE branches. Ablation analysis further showed clear gains of the full fusion model over both image-only and radiomics-only variants, indicating complementary contributions from radiomics and image representations. These findings suggest that radiomics remains relevant for RCC CT classification in the presence of foundation representations, and that its integration with MedVAE is more effective in the 3D setting. More broadly, the study supports a complementary role for radiomics and foundation representations in clinically meaningful imaging decision support.
Accepted at Medical Image Understanding and Analysis (MIUA 2026). 15 pages, 2 figures
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2609.26463 [cs.CV]
(or arXiv:2609.26463v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.26463 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
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.
Text integral sub licența deschisă a publicației · 324 cuvinte
Subiecte conexe
Radiomics-Conditioned Modulation of RenalCLIP Features for Clear Cell Renal Cell Carcinoma Classification
arXiv · 24 sept. 2026
Foundation-model-guided radiogenomic discovery linking cancer genomes to cancer scans
arXiv · 24 iul. 2026
Beyond Gene Reconstruction: Learning Cell Representations through Complementary Transcriptomic Views
arXiv · 5 aug. 2026
ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders
arXiv · 31 iul. 2026