Metraipolis › archive › dc_7d775dd484fc

Healthy Counterfactual Generation via Diffusion Inpainting for Mammography Classification — arXiv:2610.12147

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.12147
License (as archived): CC0-1.0
Archived: 2026-10-09T06:30:48.909Z
SHA-256 of the archived text: 68d3edef382225d83352eb76429dd4a5b545bbc2a4b9cdb984a87ceb25790661
Stable URL of this page: https://metraipolis.com/documento/dc_7d775dd484fc

How to cite

Healthy Counterfactual Generation via Diffusion Inpainting for Mammography Classification — arXiv:2610.12147 — arXiv (en), https://arxiv.org/abs/2610.12147 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7d775dd484fc (Metraipolis archive dc_7d775dd484fc, sha256 68d3edef382225d83352eb76429dd4a5b545bbc2a4b9cdb984a87ceb25790661)

BibTeX

@misc{dc7d775dd484fc,
  title = {Healthy Counterfactual Generation via Diffusion Inpainting for Mammography Classification — arXiv:2610.12147},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12147},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7d775dd484fc; sha256 68d3edef382225d83352eb76429dd4a5b545bbc2a4b9cdb984a87ceb25790661},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12147. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

False negatives remain a critical limitation of computer-aided diagnosis (CAD) systems for breast cancer screening due to delayed detection and treatment. To address this issue, we propose a counterfactual data augmentation strategy that generates healthy mammograms by "erasing" lesions from anomalous images, thereby enriching the training distribution. We train a Denoising Diffusion Probabilistic Model on BI-RADS 1 (healthy) mammograms and use a RePaint-based sampling strategy to inpaint realistic normal tissue within annotated lesion bounding boxes. The resulting healthy counterfactuals replace annotated lesion regions with realistic healthy tissue while preserving patient-specific anatomical structure, as supported by similarity metrics between real and generated images. Image realism was further assessed by radiologists and found to be consistent with the original dataset quality. We evaluate counterfactual augmentation across four representative classifier architectures: a convolutional neural network (ConvNeXt), a vision transformer (ViT), a vision-language model pre-trained on mammogram-report pairs (Mammo-CLIP) and a multi-scale attention-based multiple-instance learning framework (FPN-MIL). Experiments conducted on the VinDr-Mammo dataset show improvements in sensitivity across all architectures, particularly at 80\% fixed specificity, contributing towards more reliable CAD systems for breast cancer. Code is available at: this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.12147 — 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 2026-10-09T05:55:07.611Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).