Metraipolis › archive › dc_7421efcb74e5

FCA-Guided Counterfactual Explanations for Multi-Modal Breast Cancer Diagnosis: A Framework Achieving Perfect Validity with Emergent Sparsity — arXiv:2609.20067

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.20067
License (as archived)
CC0-1.0
Archived
2026-10-10T03:21:25.831Z
SHA-256 of the archived text
a78f4fe63f7d7cd26e4c2ec4604a2ac98079871ff393a4b2e3d6a19971b56418
Stable URL of this page
https://metraipolis.com/documento/dc_7421efcb74e5

How to cite

FCA-Guided Counterfactual Explanations for Multi-Modal Breast Cancer Diagnosis: A Framework Achieving Perfect Validity with Emergent Sparsity — arXiv:2609.20067 — arXiv (en), https://arxiv.org/abs/2609.20067 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7421efcb74e5 (Metraipolis archive dc_7421efcb74e5, sha256 a78f4fe63f7d7cd26e4c2ec4604a2ac98079871ff393a4b2e3d6a19971b56418)
BibTeX
@misc{dc7421efcb74e5,
  title = {FCA-Guided Counterfactual Explanations for Multi-Modal Breast Cancer Diagnosis: A Framework Achieving Perfect Validity with Emergent Sparsity — arXiv:2609.20067},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.20067},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7421efcb74e5; sha256 a78f4fe63f7d7cd26e4c2ec4604a2ac98079871ff393a4b2e3d6a19971b56418},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20067. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.20067 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T03:04:13.697Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).