arXiv：cs.AI· Yuan Liang, Sourav Bhattacharjee, Abraham Campbell·· 18 小时前
超越门控权重：肾细胞癌分类中影像组学-图像特征融合的决策级解释
Beyond Gate Weights: Decision-Level Interpretation of Radiomics-Image Feature Fusion for RCC Classification
AI 导读
研究在固定的 3D MedVAE--radiomics 模型上区分门控系数与决策级分支贡献，用于增强 CT 的透明细胞与非透明细胞肾细胞癌分类。平均结构 radiomics 权重为 0.823，而平均有效 radiomics 主导度为 0.148，两者仅有较弱关联（ρ = 0.290）。门控图像项保留的判别排序信息明显强于直接 radiomics 项，结构权重与决策级贡献应分开解读。
正文
Abstract:Gate coefficients describe how a fusion layer weights intermediate features, but they do not necessarily reflect the magnitude of branch contributions at the classifier output. We investigate this distinction in a fixed 3D MedVAE--radiomics model for clear cell versus non-clear cell renal cell carcinoma classification from contrast-enhanced CT. Because the model uses a linear classification head, the binary decision logit can be decomposed exactly into a gated image term, a direct radiomics term, and a bias. We define effective radiomics dominance as the direct radiomics term's share of the summed absolute non-bias branch contributions and compare it with structural radiomics weighting. Internally, mean structural radiomics weighting was 0.823, whereas mean effective radiomics dominance was 0.148, with a modest case-wise association (\r{ho} = 0.290). The gated image term retained substantially stronger discriminative ranking information than the direct radiomics term. The same structural-to-effective discrepancy was observed in exploratory external evaluation. Branch-targeted permutation, integrated-gradient, and Shapley-style analyses further identified radiomics descriptors influencing the direct radiomics term. Because radiomics also generates the gate, the gated image term remains radiomics-dependent, so additive branch contribution should not be interpreted as total input influence. These findings show that structural gate weighting and decision-level branch contribution represent distinct aspects of gated feature fusion and should be interpreted separately.
| Comments: | 12 pages, 1 figure. Accepted at the 2026 Irish Conference on Artificial Intelligence and Cognitive Science (AICS 2026). Proceedings forthcoming |
| Subjects: | Image and Video Processing (eess.IV); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.14152 [eess.IV] |
| (or arXiv:2610.14152v1 [eess.IV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14152 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuan Liang [view email]
[v1]
Fri, 9 Oct 2026 15:57:04 UTC (287 KB)
来源：arXiv：cs.AI · arxiv.org