# Beyond Gate Weights: Decision-Level Interpretation of Radiomics-Image Feature Fusion for RCC Classification

arXiv: https://arxiv.org/abs/2610.14152 · HTML: https://mlsanity.com/paper/2610.14152/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 24 references that are in the map.
- First posted on arXiv 9 Oct 2026.

## Builds on (most cited first, 8 of 8)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Attention is not not Explanation](https://mlsanity.com/paper/1908.04626/) (2019)
- [All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously](https://mlsanity.com/paper/1801.01489/) (2018)
- [Gated Multimodal Units for Information Fusion](https://mlsanity.com/paper/1702.01992/) (2017)
- [Image biomarker standardisation initiative](https://mlsanity.com/paper/1612.07003/) (2016)
- [AI-Generated Annotations Dataset for Diverse Cancer Radiology Collections in NCI Image Data Commons](https://mlsanity.com/paper/2310.14897/) (2023)
- [Borrowing From the Future: Enhancing Early Risk Assessment through Contrastive Learning](https://mlsanity.com/paper/2508.11210/) (2025)

## Abstract (arXiv)

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 (rho = 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.