Metraipolis › archive › dc_964de6ca5367
Beyond In-Distribution Metrics: A Systematic Out-of-Distribution Evaluation of Congenital Heart Disease Segmentation — arXiv:2609.17068
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.17068
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T18:38:48.678Z
- SHA-256 of the archived text
f6832e8f48714aa5f250aa8703817b4e8cb67a83caef3803cf37baab695a4cdc- Stable URL of this page
https://metraipolis.com/documento/dc_964de6ca5367
How to cite
Beyond In-Distribution Metrics: A Systematic Out-of-Distribution Evaluation of Congenital Heart Disease Segmentation — arXiv:2609.17068 — arXiv (en), https://arxiv.org/abs/2609.17068 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_964de6ca5367 (Metraipolis archive dc_964de6ca5367, sha256 f6832e8f48714aa5f250aa8703817b4e8cb67a83caef3803cf37baab695a4cdc)
BibTeX
@misc{dc964de6ca5367,
title = {Beyond In-Distribution Metrics: A Systematic Out-of-Distribution Evaluation of Congenital Heart Disease Segmentation — arXiv:2609.17068},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.17068},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_964de6ca5367; sha256 f6832e8f48714aa5f250aa8703817b4e8cb67a83caef3803cf37baab695a4cdc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17068. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Congenital heart disease (CHD) diagnosis and surgical planning often require patient-specific 3D anatomical models, but manual segmentation is labor-intensive, particularly in complex anatomies. Although deep-learning methods can automate this process, they are typically evaluated in-distribution, despite clinically relevant shifts in scanner, protocol, institution, population, and imaging modality. We present, to our knowledge, the first systematic evaluation of out-of-distribution (OOD) generalization in CHD segmentation, using ImageCHD as a held-out target cohort. We compare representative segmentation architectures under combined CT and CMR training, CT-only training, self-supervised pretraining, and limited target-domain adaptation. In-distribution performance proves to be a poor indicator of cross-cohort robustness: nnU-Net achieves the highest validation Dice (0.77) but falls to 0.51 on ImageCHD, while SwinUNETR generalizes substantially better, reaching 0.67 Dice. MAE and JEPA pretraining provide only modest additional benefit, suggesting that architecture contributes more to robustness than the tested pretraining strategies in this setting. When limited target-domain supervision is introduced, all SwinUNETR variants exceed 0.76 Dice with only 11 labeled ImageCHD cases. These findings demonstrate that conventional in-distribution evaluation can obscure clinically important generalization failures and support explicit cross-dataset testing as a key component of CHD segmentation evaluation. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.17068 — 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 2026-10-15T18:03:09.723Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).