Metraipolis › archive › dc_a0045264dd33

RepConTUR: A Report-Conditioned Volumetric Multimodal Model for Abdominal Tumor Segmentation — arXiv:2610.40094

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40094
License (as archived)
CC0-1.0
Archived
2026-11-01T02:42:17.835Z
SHA-256 of the archived text
90d920db596e7fa554b56fbb8cd132d7a9f5bdb2041f946dadff40ca309ea210
Stable URL of this page
https://metraipolis.com/documento/dc_a0045264dd33

How to cite

RepConTUR: A Report-Conditioned Volumetric Multimodal Model for Abdominal Tumor Segmentation — arXiv:2610.40094 — arXiv (en), https://arxiv.org/abs/2610.40094 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a0045264dd33 (Metraipolis archive dc_a0045264dd33, sha256 90d920db596e7fa554b56fbb8cd132d7a9f5bdb2041f946dadff40ca309ea210)
BibTeX
@misc{dca0045264dd33,
  title = {RepConTUR: A Report-Conditioned Volumetric Multimodal Model for Abdominal Tumor Segmentation — arXiv:2610.40094},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40094},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a0045264dd33; sha256 90d920db596e7fa554b56fbb8cd132d7a9f5bdb2041f946dadff40ca309ea210},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40094. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tumor delineation is required for radiotherapy planning, yet automatic segmentation is limited by errors, predominantly false positives, that distort dose and increase editing time. The radiology report accompanies the scan and localizes disease at the suborgan level, but existing text-promptable models condition on short referring phrases, and most operate in 2D. We present RepConTUR, a single native-3D early-fusion multimodal model that conditions volumetric abdominal tumor segmentation on the narrative report. We extend AbdomenAtlas 3.0 to a suborgan-level promptable segmentation dataset and generate report-based VQA pairs, yielding four report-derived tasks on the same annotations: referring segmentation (RES), report-grounded segmentation (GSEG), report generation (RRG), and visual question answering (VQA). We train RepConTUR, comprising a 3D CT encoder, an early-fusion language model, and a native-3D segmentation module, jointly on the four tasks. Across liver, kidney and pancreas, RepConTUR attains the highest Dice similarity coefficient (DSC), instance-wise precision, and detection F1 among the text-promptable baselines, and adding the report raises mean precision while leaving recall comparable. Against two vision-only specialists, nnU-Net and the report-supervised R-Super, RepConTUR attains the highest value on every in-domain metric for liver and pancreas and the highest mean DSC, recall, precision, and detection F1 over the four out-of-distribution public cohorts. Ablations indicate that conditioning on the narrative report raises detection F1 from 0.499 to 0.528 within the same model, that joint GSEG training raises RES F1 from 0.450 to 0.482, and that the native-3D segmentation module raises GSEG F1 from 0.139 to 0.528 over its 2D counterpart. 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/2610.40094 — 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 2026-11-01T02:16:43.969Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).