FCA引导的多模态乳腺癌诊断反事实解释：一个实现完美有效性与涌现稀疏性的框架

中文摘要 AI 辅助

用于多模态乳腺癌诊断的深度学习模型达到了较高的预测准确率，但若缺乏可操作的反事实解释，在临床上仍不可接受。基于归因的方法（LIME、SHAP）在类别上不适用于此目的，因为它们不生成替代实例，因此无法在反事实质量指标上进行评估。本研究提供了实证证据，证明FCA引导反事实（FCA-CF）框架使用形式概念分析（FCA）概念格作为反事实搜索的硬结构约束，在多模态TCGA-BRCA数据集上运行。我们与四种真正的反事实方法进行基准比较：Wachter式CF、DiCE、FACE和NICE，在60个良性预测的TCGA-BRCA实例上进行评估。FCA-CF框架实现了Validity = 1.0000（100%的反事实成功翻转预测），Sparsity = 2.37个特征改变（在所有有效方法中最佳），Proximity = 0.900（归一化L2距离，与NICE并列最佳）。分类器实现了Accuracy = 0.980，F1 = 0.976，ROC-AUC = 0.9947。消融分析证实，FCA格约束是稀疏性的主要驱动因素（移除它会使稀疏性增加+40%，p < 0.001，Cohen's d = 0.78），而C阶段贪婪细化贡献了最大的个体贡献（禁用时稀疏性增加+113%，p < 0.001，d = 5.01）。FCA引导的反事实生成实现了临床上重要的帕累托主导结果；它同时是所有有效方法中最稀疏且最接近的方法之一，并具有完美有效性。由格拓扑而非数值惩罚项产生的涌现稀疏性属性，构成了对反事实解释文献的结构性新颖贡献。

英文摘要

Deep learning models for multi-modal breast cancer diagnosis achieve high predictive accuracy but remain clinically unacceptable without actionable, counterfactual explanations. Attribution-based methods (LIME, SHAP) are categorically inapplicable to this purpose, as they generate no alternative instances and thus cannot be evaluated on counterfactual quality metrics. This investigation provides empirical evidence that FCA-Guided Counterfactual (FCA-CF) framework that uses a Formal Concept Analysis (FCA) concept lattice as a hard structural constraint on counterfactual search, operating over a multi-modal TCGA-BRCA dataset. We benchmark against four genuine counterfactual methods: Wachter-style CF, DiCE, FACE, and NICE, evaluated on 60 benign-predicted TCGA-BRCA instances. The FCA-CF framework achieves Validity = 1.0000 (100% of counterfactuals successfully flip the prediction), Sparsity = 2.37 features changed (best among all valid methods), and Proximity = 0.900 (normalised L2-based, matching NICE as joint best). The classifier achieves Accuracy = 0.980, F1 = 0.976, ROC-AUC = 0.9947. Ablation analysis confirms that the FCA lattice constraint is the primary sparsity driver (removing it increases sparsity by +40%, p < 0.001, Cohen's d = 0.78), while Phase C greedy refinement accounts for the largest individual contribution (+113% sparsity increase when disabled, p < 0.001, d = 5.01). FCA-guided counterfactual generation achieves a clinically important Pareto-dominant outcome; it is simultaneously the sparsest and among the most proximate of all valid methods, with perfect validity. The emergent sparsity property arising from lattice topology rather than numerical penalty terms constitutes a structurally novel contribution to the counterfactual explanation literature.

发表机构

• Abubakar Tafawa Balewa University（阿布巴卡尔·塔法瓦·巴莱瓦大学）

机构由 AI 辅助整理，请以论文原文为准。