Metraipolis › archive › dc_2ee5a78efebb

Confidence-Aware Teacher-Student Distillation for 3D Medical Segmentation — arXiv:2609.23815

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.23815
License (as archived): CC0-1.0
Archived: 2026-10-09T22:04:37.748Z
SHA-256 of the archived text: 967eb2556398d81f9fb77f9d954c03b1718acc9d8bd3bad9837efbfc8617a98f
Stable URL of this page: https://metraipolis.com/documento/dc_2ee5a78efebb

How to cite

Confidence-Aware Teacher-Student Distillation for 3D Medical Segmentation — arXiv:2609.23815 — arXiv (en), https://arxiv.org/abs/2609.23815 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2ee5a78efebb (Metraipolis archive dc_2ee5a78efebb, sha256 967eb2556398d81f9fb77f9d954c03b1718acc9d8bd3bad9837efbfc8617a98f)

BibTeX

@misc{dc2ee5a78efebb,
  title = {Confidence-Aware Teacher-Student Distillation for 3D Medical Segmentation — arXiv:2609.23815},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23815},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2ee5a78efebb; sha256 967eb2556398d81f9fb77f9d954c03b1718acc9d8bd3bad9837efbfc8617a98f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23815. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Medical image segmentation models typically rely on large amounts of densely annotated volumetric data, limiting their scalability across tasks and imaging modalities. This work addresses the challenge of predicting entire 3D anatomical structures from extreme annotation sparsity. An annotation-efficient student-teacher framework is proposed for automatic 3D medical segmentation that requires only a set of point prompts on a single 2D slice per volume, as input. A foundation model serves as an offline teacher, utilizing the provided point prompts from the selected slice to full-volume pseudo-annotations alongside their corresponding spatial confidence scores prior to student training. To mitigate the error propagation of noisy pseudo-annotations, a task-specific 3D student network is trained using a confidence-aware optimization strategy. By leveraging the teacher's pre-computed confidence scores, this strategy explicitly excludes statically uncertain regions of the pseudo-annotations from the loss calculation, while simultaneously emphasizing regions with higher confidence. Evaluated on 3D cardiac MRI datasets, our framework outperforms state-of-the-art semi-supervised methods, improving segmentation performance by up to 43.6%. Furthermore, it drastically reduces the manual annotation burden to just a few positive point prompts per volume, while improving surface boundary precision by up to 14.7% over the teacher and successfully recovering up to 34.1% of the performance gap toward the fully supervised upper bound.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.23815 — 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 2026-10-09T21:45:20.955Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).