PRIMA: Pre-training with Risk-integrated Image-Metadata Alignment for Medical Diagnosis via LLM

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Yiqing, He, Chunming, Lu, Ming-Chen, Pawar, Mercy, Niziol, Leslie, Woodward, Maria, Farsiu, Sina
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912928561627136
author Wang, Yiqing
He, Chunming
Lu, Ming-Chen
Pawar, Mercy
Niziol, Leslie
Woodward, Maria
Farsiu, Sina
author_facet Wang, Yiqing
He, Chunming
Lu, Ming-Chen
Pawar, Mercy
Niziol, Leslie
Woodward, Maria
Farsiu, Sina
contents Medical diagnosis requires the effective synthesis of visual manifestations and clinical metadata. However, existing methods often treat metadata as isolated tags, failing to exploit the rich semantic knowledge embedded in clinical descriptions. We propose PRIMA (Pre-training with Risk-integrated Image-Metadata Alignment), a framework that integrates domain-specific knowledge into multi-modal representation learning. We first curate an expert corpus of risk-disease correlations via Retrieval-Augmented Generation (RAG) to refine Clinical ModernBERT, embedding diagnostic priors into the text encoder. To bridge the modality gap, we introduce a dual-encoder pre-training strategy utilizing DINOv3 and our refined BERT, optimized by a suite of four complementary loss functions. These losses are designed to capture multi-granular semantic alignment and handle the ambiguity of clinical correlations through soft labels. Finally, we leverage Qwen-3 to fuse these aligned features for precise disease classification. Extensive experiments demonstrate that PRIMA effectively harmonizes pixel-level features with abstract clinical expertise, significantly outperforming other state-of-the-art methods. Notably, our framework achieves superior robustness without the need for massive data collection or exhaustive computational resources. Our code will be made public upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2602_23297
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PRIMA: Pre-training with Risk-integrated Image-Metadata Alignment for Medical Diagnosis via LLM
Wang, Yiqing
He, Chunming
Lu, Ming-Chen
Pawar, Mercy
Niziol, Leslie
Woodward, Maria
Farsiu, Sina
Computer Vision and Pattern Recognition
Medical diagnosis requires the effective synthesis of visual manifestations and clinical metadata. However, existing methods often treat metadata as isolated tags, failing to exploit the rich semantic knowledge embedded in clinical descriptions. We propose PRIMA (Pre-training with Risk-integrated Image-Metadata Alignment), a framework that integrates domain-specific knowledge into multi-modal representation learning. We first curate an expert corpus of risk-disease correlations via Retrieval-Augmented Generation (RAG) to refine Clinical ModernBERT, embedding diagnostic priors into the text encoder. To bridge the modality gap, we introduce a dual-encoder pre-training strategy utilizing DINOv3 and our refined BERT, optimized by a suite of four complementary loss functions. These losses are designed to capture multi-granular semantic alignment and handle the ambiguity of clinical correlations through soft labels. Finally, we leverage Qwen-3 to fuse these aligned features for precise disease classification. Extensive experiments demonstrate that PRIMA effectively harmonizes pixel-level features with abstract clinical expertise, significantly outperforming other state-of-the-art methods. Notably, our framework achieves superior robustness without the need for massive data collection or exhaustive computational resources. Our code will be made public upon acceptance.
title PRIMA: Pre-training with Risk-integrated Image-Metadata Alignment for Medical Diagnosis via LLM
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.23297