Metraipolis › archive › dc_3f291ca83bb3

Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting — arXiv:2608.12590

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.12590
License (as archived): CC0-1.0
Archived: 2026-10-19T04:17:14.942Z
SHA-256 of the archived text: efba547ca1893debb2ff6efe4e4cdf2e17ae2ce433958dfffc6608dff7ab2e25
Stable URL of this page: https://metraipolis.com/documento/dc_3f291ca83bb3

How to cite

Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting — arXiv:2608.12590 — arXiv (en), https://arxiv.org/abs/2608.12590 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3f291ca83bb3 (Metraipolis archive dc_3f291ca83bb3, sha256 efba547ca1893debb2ff6efe4e4cdf2e17ae2ce433958dfffc6608dff7ab2e25)

BibTeX

@misc{dc3f291ca83bb3,
  title = {Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting — arXiv:2608.12590},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12590},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3f291ca83bb3; sha256 efba547ca1893debb2ff6efe4e4cdf2e17ae2ce433958dfffc6608dff7ab2e25},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12590. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Thyroid ultrasound diagnosis requires coordinated lesion localization, measurement, risk stratification and reporting, yet most AI systems address these tasks in isolation and provide limited support for clinical review. We present ThyroidXAgent, a clinician-interactive agentic AI system that coordinates specialized diagnostic tools and stores their outputs as an auditable case-level evidence record. The system was developed using OpenThyroidDB, a multicentre, multitask resource integrating approximately 0.3 million ultrasound images and 24,000 paired reports, and was evaluated on 28,458 non-overlapping test cases, including 8,721 cases from 35 centres in the private NHC-MISD-TUS cohort. Across heterogeneous datasets, ThyroidXAgent achieved a mean Dice score of 87.21 percent for nodule segmentation and a mean AUROC of 0.9466 for benign-malignant classification. The same workflow supported lymph-node metastasis prediction and follicular versus papillary thyroid carcinoma classification, with AUROCs of 0.864 and 0.805, respectively. For report generation, evidence-grounded assembly outperformed multimodal language-model baselines across three cohorts. ThyClinScore, a lesion-level clinical semantic metric introduced here, showed the strongest correlation with a location-aware language-model judge. ThyroidXAgent improved physician classification accuracy, increased report diagnostic consistency from 70.3 percent to 86.2 percent, and reduced segmentation and reporting time by 35.9 percent and 27.4 percent, respectively. These findings support auditable, clinician-correctable agentic AI for thyroid ultrasound diagnosis and reporting.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.12590 — 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 2026-10-19T04:13:06.529Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).