cs.CVMay 8, 2025

CAG-VLM: Fine-Tuning of a Large-Scale Model to Recognize Angiographic Images for Next-Generation Diagnostic Systems

Authors: Yuto Nakamura, Satoshi Kodera, Haruki Settai, Hiroki Shinohara, Masatsugu Tamura, Tomohiro Noguchi, Tatsuki Furusawa, Ryo Takizawa, 

Organizations: The University of Tokyo · The University of Tokyo Hospital

Abstract

Coronary angiography (CAG) is the gold-standard imaging modality for evaluating coronary artery disease, but its interpretation and subsequent treatment planning rely heavily on expert cardiologists. To enable AI-based decision support, we introduce a two-stage, physician-curated pipeline and a bilingual (Japanese/English) CAG image-report dataset. First, we sample 14,686 frames from 539 exams and annotate them for key-frame detection and left/right laterality; a ConvNeXt-Base CNN trained on this data achieves 0.96 F1 on laterality classification, even on low-contrast frames. Second, we apply the CNN to 243 independent exams, extract 1,114 key frames, and pair each with its pre-procedure report and expert-validated diagnostic and treatment summary, yielding a parallel corpus. We then fine-tune three open-source VLMs (PaliGemma2, Gemma3, and ConceptCLIP-enhanced Gemma3) via LoRA and evaluate them using VLScore and cardiologist review. Although PaliGemma2 w/LoRA attains the highest VLScore, Gemma3 w/LoRA achieves the top clinician rating (mean 7.20/10); we designate this best-performing model as CAG-VLM. These results demonstrate that specialized, fine-tuned VLMs can effectively assist cardiologists in generating clinical reports and treatment recommendations from CAG images.

Figures & tables

Explore similar work

CardsList
  1. CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography Interpretation

    Sep 7, 2026Jia-Jen Lee, Shih-Yen Hou, Kee Koon Ng +2Coronary AngiographyMedical VLMs

  2. Can Large Language Models Reliably Extract Physiology Index Values from Coronary Angiography Reports?

    Mar 21, 2026Sofia Morgado, Filipa Valdeira, Niklas Sander +4Clinical Information ExtractionLLM Information Extraction

  3. CARDIAG: A Dense Segment Classification Benchmark of Deep Learning Architectures for Coronary Angiography

    Jul 24, 2026Dominik Bernard Lau, Hubert Malinowski, Jerzy Szyjut +5Coronary AngiographyMedical Image Segmentation