Rethinking Multi-view Mammogram Representation Learning via Counterfactual Reasoning with Kolmogorov-Arnold Theorem
Abstract
Cross-view interference caused by impure shared information for multiview mammogram representation. Existing methods are accustomed to assuming that purely complementary shared information are provided between multiple views, ignoring the negative side of the shared information. To address this issue, we propose the first Dual-view Mammography Causal Graph (DMCG) to model multi-view representation by capturing direct and mediation effects. Based on DMCG, we propose MammoCRKAN, the first counterfactual reasoning paradigm integrating the Kolmogorov-Arnold theorem for decoupling interfering information. MammoCRKAN comprises two key modules: the Spherical Sample Module (SSM), which enhances the direct effect of tumor features by aligning consistent geometric representations, and the Kolmogorov–Arnold Aggregate Module (KAAM), which decomposes complex joint causality into univariate effects to mitigate negative side of mediation effects. Moreover, We find that heterogeneous channel allocations across views outperform fixed matching channels. Extensive experiments on four publicly available mammogram datasets demonstrate the effectiveness of MammoCRKAN.
MammoCRKAN consists of SSM and KAAM. SSM strengthening direct effect. KAAM promoting positive side of mediation effect.
MammoCRKAN achieves the best classification results on four mainstream datasets.
(a) Heterogeneous channel allocations for MLO and CC views outperform fixed matching channels.
(b)MammoCRKAN demonstrates superior representation both within and across classes.
BibTeX
@InProceedings{ Wan_MammoKAN_MICCAI2025,
author = { Wang, Guoli and Benzheng Wei and Shuo Li },
title = { { Rethinking Multi-view Mammogram Representation Learning via Counterfactual Reasoning with Kolmogorov-Arnold Theorem } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2024},
year = {2025},
publisher = {Springer Nature Switzerland},
volume = { LNCS ***** },
month = {October},
pages = { * -- * },
}