Metraipolis › archive › dc_5087ed45fcc5
Anatomical Prior-Guided Routing for 3D Lung Tumor Segmentation — arXiv:2610.39414
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39414
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:41:57.902Z
- SHA-256 of the archived text
3799165e813381352888a858d5005c7cba8e491ac0f08905ad81bba70ea3b7c0- Stable URL of this page
https://metraipolis.com/documento/dc_5087ed45fcc5
How to cite
Anatomical Prior-Guided Routing for 3D Lung Tumor Segmentation — arXiv:2610.39414 — arXiv (en), https://arxiv.org/abs/2610.39414 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5087ed45fcc5 (Metraipolis archive dc_5087ed45fcc5, sha256 3799165e813381352888a858d5005c7cba8e491ac0f08905ad81bba70ea3b7c0)
BibTeX
@misc{dc5087ed45fcc5,
title = {Anatomical Prior-Guided Routing for 3D Lung Tumor Segmentation — arXiv:2610.39414},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39414},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5087ed45fcc5; sha256 3799165e813381352888a858d5005c7cba8e491ac0f08905ad81bba70ea3b7c0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39414. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Accurate lung tumor segmentation in computed tomography (CT) is essential for treatment planning, response assessment, and quantitative imaging analysis. However, 3D lung tumor segmentation remains challenging because tumors occupy only a small portion of the whole volume and exhibit heterogeneous appearances across anatomical locations. In patch-based training and sliding-window inference for 3D medical image segmentation, location-dependent heterogeneity is further amplified because cropped image patches provide limited global anatomical context, making it difficult for a model to adapt its feature processing according to the anatomical region from which each patch is extracted. To address this limitation, we propose an Anatomical Prior-guided Routing Module (APRM) for lung tumor segmentation. For each image patch, we obtain anatomical prior information of regional occupancy and deterministically select an anatomical routing gate. The selected gate then performs sparse feature routing over a shared expert adapter pool, enabling anatomy-specific feature adaptation while sharing expert capacity across regions. We evaluate APRM on two datasets with various backbone networks and demonstrate consistent improvements over baseline models. Furthermore, feature visualizations show that APRM produces different feature responses depending on patch location, indicating that the proposed routing mechanism effectively adapts feature processing according to anatomical context. 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/2610.39414 — 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 2026-11-01T02:16:43.927Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).