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）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出用影像组学通过FiLM调制RenalCLIP特征，提升透明细胞肾细胞癌CT分类性能，内外验证AUC达0.804和0.854，证明其互补有效性。
AI 中文摘要
影像组学提供肿瘤外观的定量描述，可在小标注队列中补充疾病特异性基础模型。我们研究了这种互补性在基于计算机断层扫描的透明细胞肾细胞癌分类中的应用。我们的框架通过特征级线性调制（FiLM）使用影像组学调制 RenalCLIP 特征，同时保留直接的影像组学贡献。内部测试和外部验证将其与传统的融合策略和参考分类器进行比较。FiLM 模型在内部达到 0.804 的受试者工作特征曲线下面积（AUC），在外部达到 0.854，在两个队列中评估的 RenalCLIP 融合策略中具有最高的平均 AUC。通路消融实验考察了条件调制和直接影像组学残差的贡献，而特征排列突出了肿瘤纹理的作用。这些发现支持影像组学在小标注队列中作为 RenalCLIP 的有用补充，并确定 FiLM 是整合其表示以实现稳健肾肿瘤分类的有效方法。
英文摘要
Radiomics provides quantitative descriptions of tumour appearance that may complement disease-specific foundation models in small labelled cohorts. We investigate this complementarity for computed tomography-based classification of clear cell renal cell carcinoma. Our framework uses radiomics to modulate RenalCLIP features through feature-wise linear modulation (FiLM), while retaining a direct radiomics contribution. Internal testing and external validation compare it with conventional fusion strategies and reference classifiers. The FiLM model achieves an area under the receiver operating characteristic curve (AUC) of 0.804 internally and 0.854 externally, with the highest mean AUC among the evaluated RenalCLIP fusion strategies in both cohorts. Pathway ablations examine the contributions of conditional modulation and the direct radiomics residual, while feature permutation highlights the role of tumour texture. These findings support radiomics as a useful complement to RenalCLIP in a small labelled cohort and identify FiLM as an effective approach to integrating their representations for robust renal tumour classification.
CommentsAccepted at the 7th International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2026). 10 pages, 2 figures
