Metraipolis › archive › dc_f453bfa75dcc

Learning Where to Look: Anatomical Grounding and Guided Attention for Cardiac MRI Vision-Language Models — arXiv:2609.39899

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39899
License (as archived)
CC0-1.0
Archived
2026-10-07T14:46:30.510Z
SHA-256 of the archived text
55a37b6206d735d9d0f3dd0822efb0e763b238d660bb109d64e192bc720081dc
Stable URL of this page
https://metraipolis.com/documento/dc_f453bfa75dcc

How to cite

Learning Where to Look: Anatomical Grounding and Guided Attention for Cardiac MRI Vision-Language Models — arXiv:2609.39899 — arXiv (en), https://arxiv.org/abs/2609.39899 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f453bfa75dcc (Metraipolis archive dc_f453bfa75dcc, sha256 55a37b6206d735d9d0f3dd0822efb0e763b238d660bb109d64e192bc720081dc)
BibTeX
@misc{dcf453bfa75dcc,
  title = {Learning Where to Look: Anatomical Grounding and Guided Attention for Cardiac MRI Vision-Language Models — arXiv:2609.39899},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39899},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f453bfa75dcc; sha256 55a37b6206d735d9d0f3dd0822efb0e763b238d660bb109d64e192bc720081dc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39899. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cardiac magnetic resonance imaging (CMR) enables assessment of cardiac anatomy, ventricular function, and myocardial tissue characteristics. Clinicians interpret these images by identifying cardiac structures and focusing on the regions relevant to each clinical question, motivating anatomically guided vision-language models (VLMs). Yet CMR-specific supervision for anatomical localisation and clinical question answering remains limited. To address this gap, we investigate fine-grained CMR visual question answering through anatomical grounding and guided attention. We construct 128,915 anatomical-grounding and 42,799 clinical QA pairs across short-axis cine, late gadolinium enhancement, and long-axis cine. These datasets support anatomical recognition, localisation, and clinical assessment without requiring paired reports for individual training images. To help the model learn where to look, we introduce Cardiac Anatomy-Routed Attention (CARA), which selects predicted anatomical priors according to the question and guides decoder attention with learned task-specific strengths. Combining anatomical grounding pretraining with CARA yields our model, CARA-VL. Experiments demonstrate CARA-VL's strengths in clinical assessment and regional localisation across CMR imaging settings, with promising generalization to an external clinical cohort. Together, our data and method provide a practical framework for studying and advancing cardiac visual understanding in VLMs. We will release the QA data derived from public datasets upon publication.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.39899 — 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 2026-10-07T14:19:00.823Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).