Saved in:
Bibliographic Details
Main Authors: Nakamura, Yuto, Kodera, Satoshi, Settai, Haruki, Shinohara, Hiroki, Tamura, Masatsugu, Noguchi, Tomohiro, Furusawa, Tatsuki, Takizawa, Ryo, Kabayama, Tempei, Takeda, Norihiko
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.04964
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909642276208640
author Nakamura, Yuto
Kodera, Satoshi
Settai, Haruki
Shinohara, Hiroki
Tamura, Masatsugu
Noguchi, Tomohiro
Furusawa, Tatsuki
Takizawa, Ryo
Kabayama, Tempei
Takeda, Norihiko
author_facet Nakamura, Yuto
Kodera, Satoshi
Settai, Haruki
Shinohara, Hiroki
Tamura, Masatsugu
Noguchi, Tomohiro
Furusawa, Tatsuki
Takizawa, Ryo
Kabayama, Tempei
Takeda, Norihiko
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_04964
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CAG-VLM: Fine-Tuning of a Large-Scale Model to Recognize Angiographic Images for Next-Generation Diagnostic Systems
Nakamura, Yuto
Kodera, Satoshi
Settai, Haruki
Shinohara, Hiroki
Tamura, Masatsugu
Noguchi, Tomohiro
Furusawa, Tatsuki
Takizawa, Ryo
Kabayama, Tempei
Takeda, Norihiko
Computer Vision and Pattern Recognition
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.
title CAG-VLM: Fine-Tuning of a Large-Scale Model to Recognize Angiographic Images for Next-Generation Diagnostic Systems
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2505.04964