Metraipolis › archive › dc_6c3bfba33422

A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generation — arXiv:2608.02805

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.02805
License (as archived)
CC0-1.0
Archived
2026-10-31T12:18:15.468Z
SHA-256 of the archived text
b78df4efa3e786ed87ff5527c01b5336cd62374f61c16bb1e741b0ccaa538448
Stable URL of this page
https://metraipolis.com/documento/dc_6c3bfba33422

How to cite

A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generation — arXiv:2608.02805 — arXiv (en), https://arxiv.org/abs/2608.02805 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6c3bfba33422 (Metraipolis archive dc_6c3bfba33422, sha256 b78df4efa3e786ed87ff5527c01b5336cd62374f61c16bb1e741b0ccaa538448)
BibTeX
@misc{dc6c3bfba33422,
  title = {A Unified 2D Framework for DeepLesion Detection, Segmentation and Short Report Generation — arXiv:2608.02805},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.02805},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6c3bfba33422; sha256 b78df4efa3e786ed87ff5527c01b5336cd62374f61c16bb1e741b0ccaa538448},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.02805. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In previous work, we integrated large language models (LLMs) into the lesion segmentation model based on the ULS23 DeepLesion dataset, using short-form findings from the reports. In this study, we developed a unified 2D lesion analysis framework that integrates LLM-based reasoning, lesion bounding box detection, segmentation, and radiology report generation from the original DeepLesion dataset. In the testing phase, we achieved relatively high lesion bounding box detection accuracy with mAP50 of 70.1%, mAP50-95 of 46.4%; Lesion segmentation performance with a Dice score of 62.6%; short report generation accuracy with BLEU_1 score of 64.3%, BLEU_4 score of 49.6%, METEOR of 34.7%, and ROUGE_L of 60.1%. In this work, we address the challenging issue of segmentation in the original DeepLesion dataset and achieve a 28.5% Dice score improvement over the nnUNet lesion segmentation model. We also integrated spatial and anatomical context into the DeepLesion short report generation. We released the implementation, dataset, and models on Github. this https URL

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.02805 — 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 2026-10-31T12:05:52.953Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).