Metraipolis › archive › dc_4321250efdc2

Multimodal Prompt Learning with Dual-Granularity Contrastive Alignment for Preoperative Prediction of Lung Adenocarcinoma Invasiveness Using 3D CT — arXiv:2611.03109

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03109
License (as archived)
CC0-1.0
Archived
2026-11-03T10:38:07.641Z
SHA-256 of the archived text
7bd8ab5abdadc610202177a176b6e2dccbc9b2fa8ad01f61ee35291add9a3217
Stable URL of this page
https://metraipolis.com/documento/dc_4321250efdc2

How to cite

Multimodal Prompt Learning with Dual-Granularity Contrastive Alignment for Preoperative Prediction of Lung Adenocarcinoma Invasiveness Using 3D CT — arXiv:2611.03109 — arXiv (en), https://arxiv.org/abs/2611.03109 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4321250efdc2 (Metraipolis archive dc_4321250efdc2, sha256 7bd8ab5abdadc610202177a176b6e2dccbc9b2fa8ad01f61ee35291add9a3217)
BibTeX
@misc{dc4321250efdc2,
  title = {Multimodal Prompt Learning with Dual-Granularity Contrastive Alignment for Preoperative Prediction of Lung Adenocarcinoma Invasiveness Using 3D CT — arXiv:2611.03109},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03109},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4321250efdc2; sha256 7bd8ab5abdadc610202177a176b6e2dccbc9b2fa8ad01f61ee35291add9a3217},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03109. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate preoperative prediction of lung adenocarcinoma invasiveness is important for surgical planning and individualized treatment. However, overlapping CT appearances make it challenging to distinguish invasive adenocarcinoma (IAD) from Pre-IAD lesions. We propose a multimodal prompt-learning framework with dual-granularity image-text alignment for 3D CT-based IAD classification. A 3D ResNet-CBAM encoder extracts global and spatial visual features. A frozen RadBERT backbone is adapted with separate learnable prompts for report-level and keyword-level text encoding. These prompts are initialized using semantic representations derived from real-world clinical reports. Global contrastive alignment connects whole-volume CT representations with reports generated from clinician-annotated radiological attributes to provide overall semantic supervision. A multiple instance learning-based local alignment module associates spatial CT features with vascular-focused radiological keywords, to capture local imaging characteristics potentially associated with tumor invasion. The framework jointly optimizes classification and alignment objectives, while inference requires only CT images. Experiments included 1,593 pathologically confirmed nodules. On the test set, the proposed method achieved an accuracy of 87.92%, F1-score of 87.78%, and AUC of 0.9499. Its AUC significantly exceeded that of the image-only Res-CBAM baseline with the same visual backbone (0.9297; DeLong test, p = 0.0078). Ablation analyses supported the complementary contributions of global and local alignment and the benefit of report-based prompt initialization. Qualitative visualizations showed activation within nodules and adjacent vascular structures. These findings suggest that dual-granularity radiological supervision can enhance CT-based invasiveness prediction while preserving a CT-only inference workflow.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.03109 — 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 2026-11-03T10:29:48.930Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).