Metraipolis › archive › dc_0db77d03e38f

Measurement-Aware Multimodal LLM for No-Reference Low-Dose CT Quality Assessment — arXiv:2611.08754

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08754
License (as archived)
CC0-1.0
Archived
2026-11-09T22:45:31.984Z
SHA-256 of the archived text
21dbfb978a3cf45d074afd95e336cc51803420199154cae367360ed23f9f2252
Stable URL of this page
https://metraipolis.com/documento/dc_0db77d03e38f

How to cite

Measurement-Aware Multimodal LLM for No-Reference Low-Dose CT Quality Assessment — arXiv:2611.08754 — arXiv (en), https://arxiv.org/abs/2611.08754 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0db77d03e38f (Metraipolis archive dc_0db77d03e38f, sha256 21dbfb978a3cf45d074afd95e336cc51803420199154cae367360ed23f9f2252)
BibTeX
@misc{dc0db77d03e38f,
  title = {Measurement-Aware Multimodal LLM for No-Reference Low-Dose CT Quality Assessment — arXiv:2611.08754},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08754},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0db77d03e38f; sha256 21dbfb978a3cf45d074afd95e336cc51803420199154cae367360ed23f9f2252},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08754. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

No-reference image quality assessment (IQA) of low-dose CT predicts the score that radiologists would assign to a slice without a full-dose reference, as needed to compare dose protocols and denoisers. Trained CT IQA networks agree well with radiologists but output only a score, whereas multimodal large language models (MLLMs) can explain a score but perform poorly on CT when only prompted. We propose a measurement-aware MLLM, built on Qwen3.8-27B, that rates a slice from its image together with six image-domain measurements of noise, sharpness, high-frequency content and streaks, given to the language model as percentiles in text. On the LDCT-IQA 2023 test set, it reaches an Overall score of 2.735, on par with the retrained challenge winner (2.735) and MedSigLIP-FiLM (2.713), and substantially above its base MLLM used as a zero-shot agent. Shuffling the measurements at test time reduces the score by 0.048, mostly through noise, but the same measurements also lead the model to assign higher scores to over-smoothed denoised images.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Image and Video Processing (eess.IV) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.08754 — 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 2026-11-09T22:37:47.237Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).