paper-with-me

홈 › Papers

Utilizing Synthetic Data for Medical Vision-Language Pre-training: Bypassing the Need for Real Images

2023-10-10 · Che Liu, Anand Shah, Wenjia Bai, Rossella Arcucci

Medical Vision-Language Pre-training (VLP) learns representations jointly from medical images and paired radiology reports. It typically requires large-scale paired image-text datasets to achieve effective pre-training for both the image encoder and text encoder. The advent of text-guided generative models raises a compelling question: Can VLP be implemented solely with synthetic images generated from genuine radiology reports, thereby mitigating the need for extensively pairing and curating image-text datasets? In this work, we scrutinize this very question by examining the feasibility and effectiveness of employing synthetic images for medical VLP. We replace real medical images with their synthetic equivalents, generated from authentic medical reports. Utilizing three state-of-the-art VLP algorithms, we exclusively train on these synthetic samples. Our empirical evaluation across three subsequent tasks, namely image classification, semantic segmentation and object detection, reveals that the performance achieved through synthetic data is on par with or even exceeds that obtained with real images. As a pioneering contribution to this domain, we introduce a large-scale synthetic medical image dataset, paired with anonymized real radiology reports. This alleviates the need of sharing medical images, which are not easy to curate and share in practice. The code and the dataset can be found in \href{https://github.com/cheliu-computation/MedSyn-RepLearn/tree/main}{https://github.com/cheliu-computation/MedSyn-RepLearn/tree/main}.

📄 PDF Abstract BibTeX arXiv:2310.07027

Code (1)

cheliu-computation/medsyn-replearn 공식 구현

Tasks

image-classificationImage Classificationobject-detectionObject DetectionSemantic Segmentation

Similar Papers 제목 키워드 기반

An Early Investigation into the Utility of Multimodal Large Language Models in Medical Imaging

2024-06-02 · Sulaiman Khan, Md. Rafiul Biswas, Alina Murad, Hazrat Ali 외

Recent developments in multimodal large language models (MLLMs) have spurred significant interest in their potential applications across various medical imaging domains. On the one hand, there is a temptation to use thes…

Medical Image Analysis

MoME: Mixture of Visual Language Medical Experts for Medical Imaging Segmentation

2025-10-30 · Arghavan Rezvani, Xiangyi Yan, Anthony T. Wu, Kun Han 외 arxiv

In this study, we propose MoME, a Mixture of Visual Language Medical Experts, for Medical Image Segmentation. MoME adapts the successful Mixture of Experts (MoE) paradigm, widely used in Large Language Models (LLMs), for…

Medical Image Segmentation

Multi-modal Pre-training for Medical Vision-language Understanding and Generation: An Empirical Study with A New Benchmark

2023-06-10 · Li Xu, Bo Liu, Ameer Hamza Khan, Lu Fan 외

With the availability of large-scale, comprehensive, and general-purpose vision-language (VL) datasets such as MSCOCO, vision-language pre-training (VLP) has become an active area of research and proven to be effective f…

Image-text RetrievalMedical Report GenerationQuestion AnsweringRetrieval+2

Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?

2024-10-17 · Che Liu, Zhongwei Wan, Haozhe Wang, Yinda Chen 외

Medical Vision-Language Pre-training (MedVLP) has made significant progress in enabling zero-shot tasks for medical image understanding. However, training MedVLP models typically requires large-scale datasets with paired…

zero-shot-classificationZero-Shot Learning

Utilizing Large Language Models to Generate Synthetic Data to Increase the Performance of BERT-Based Neural Networks

2024-05-08 · Chancellor R. Woolsey, Prakash Bisht, Joshua Rothman, Gondy Leroy

An important issue impacting healthcare is a lack of available experts. Machine learning (ML) models could resolve this by aiding in diagnosing patients. However, creating datasets large enough to train these models is e…