发表机构
Research Ireland Centre for Research Training in Machine Learning; University College Dublin（爱尔兰研究机器学习研究中心; 都柏林大学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究比较放射组学与2D/3D MedVAE基础表示及其融合方法，用于肾细胞癌CT亚型分类，发现3D门控融合（AUC 82.7%）最佳，证明放射组学与基础表示互补有效。
AI 中文摘要
基于对比增强计算机断层扫描的肾细胞癌（RCC）术前亚型分类在临床上仍具挑战性。放射组学提供结构化的肿瘤描述符，而基础表示则提供可迁移的图像特征。然而，尚不清楚在预训练表示存在的情况下，放射组学是否仍能增加价值，以及2D和3D MedVAE编码器在此场景中的表现如何。我们在统一预处理流程下，对KiTS23数据集上的透明细胞RCC与非透明细胞RCC二分类任务，比较了手工放射组学、2D MedVAE、3D MedVAE及其融合方法。评估了拼接、交叉注意力和门控融合作为代表性集成策略，并分析了放射组学特征重要性以支持决策中心的解释性。融合方法在判别性能上持续优于仅基于图像的MedVAE分支。最佳整体性能由3D门控融合实现，AUC为82.7%，优于最佳2D融合模型（79.6%）、放射组学基线（74.4%）和单模态MedVAE分支。消融分析进一步显示，完整融合模型相对于仅图像和仅放射组学变体均有明显提升，表明放射组学与图像表示存在互补贡献。这些发现表明，在基础表示存在的情况下，放射组学对RCC CT分类仍具相关性，且其与MedVAE的集成在3D设置中更为有效。更广泛地，该研究支持放射组学与基础表示在临床有意义的影像决策支持中的互补作用。
英文摘要
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.
CommentsAccepted at Medical Image Understanding and Analysis (MIUA 2026). 15 pages, 2 figures
