Saved in:
Bibliographic Details
Main Authors: Jiang, Zekun, Cheng, Dongjie, Qin, Ziyuan, Gao, Jun, Lao, Qicheng, Ismoilovich, Abdullaev Bakhrom, Gayrat, Urazboev, Elyorbek, Yuldashov, Habibullo, Bekchanov, Tang, Defu, Wei, LinJing, Li, Kang, Zhang, Le
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.15759
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910647311138816
author Jiang, Zekun
Cheng, Dongjie
Qin, Ziyuan
Gao, Jun
Lao, Qicheng
Ismoilovich, Abdullaev Bakhrom
Gayrat, Urazboev
Elyorbek, Yuldashov
Habibullo, Bekchanov
Tang, Defu
Wei, LinJing
Li, Kang
Zhang, Le
author_facet Jiang, Zekun
Cheng, Dongjie
Qin, Ziyuan
Gao, Jun
Lao, Qicheng
Ismoilovich, Abdullaev Bakhrom
Gayrat, Urazboev
Elyorbek, Yuldashov
Habibullo, Bekchanov
Tang, Defu
Wei, LinJing
Li, Kang
Zhang, Le
contents This study presents a novel multimodal medical image zero-shot segmentation algorithm named the text-visual-prompt segment anything model (TV-SAM) without any manual annotations. The TV-SAM incorporates and integrates the large language model GPT-4, the vision language model GLIP, and the SAM to autonomously generate descriptive text prompts and visual bounding box prompts from medical images, thereby enhancing the SAM's capability for zero-shot segmentation. Comprehensive evaluations are implemented on seven public datasets encompassing eight imaging modalities to demonstrate that TV-SAM can effectively segment unseen targets across various modalities without additional training. TV-SAM significantly outperforms SAM AUTO and GSAM, closely matching the performance of SAM BBOX with gold standard bounding box prompts and surpasses the state-of-the-art methods on specific datasets such as ISIC and WBC. The study indicates that TV-SAM serves as an effective multimodal medical image zero-shot segmentation algorithm, highlighting the significant contribution of GPT-4 to zero-shot segmentation. By integrating foundational models such as GPT-4, GLIP, and SAM, the ability to address complex problems in specialized domains can be enhanced.
format Preprint
id arxiv_https___arxiv_org_abs_2402_15759
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TV-SAM: Increasing Zero-Shot Segmentation Performance on Multimodal Medical Images Using GPT-4 Generated Descriptive Prompts Without Human Annotation
Jiang, Zekun
Cheng, Dongjie
Qin, Ziyuan
Gao, Jun
Lao, Qicheng
Ismoilovich, Abdullaev Bakhrom
Gayrat, Urazboev
Elyorbek, Yuldashov
Habibullo, Bekchanov
Tang, Defu
Wei, LinJing
Li, Kang
Zhang, Le
Computer Vision and Pattern Recognition
Artificial Intelligence
This study presents a novel multimodal medical image zero-shot segmentation algorithm named the text-visual-prompt segment anything model (TV-SAM) without any manual annotations. The TV-SAM incorporates and integrates the large language model GPT-4, the vision language model GLIP, and the SAM to autonomously generate descriptive text prompts and visual bounding box prompts from medical images, thereby enhancing the SAM's capability for zero-shot segmentation. Comprehensive evaluations are implemented on seven public datasets encompassing eight imaging modalities to demonstrate that TV-SAM can effectively segment unseen targets across various modalities without additional training. TV-SAM significantly outperforms SAM AUTO and GSAM, closely matching the performance of SAM BBOX with gold standard bounding box prompts and surpasses the state-of-the-art methods on specific datasets such as ISIC and WBC. The study indicates that TV-SAM serves as an effective multimodal medical image zero-shot segmentation algorithm, highlighting the significant contribution of GPT-4 to zero-shot segmentation. By integrating foundational models such as GPT-4, GLIP, and SAM, the ability to address complex problems in specialized domains can be enhanced.
title TV-SAM: Increasing Zero-Shot Segmentation Performance on Multimodal Medical Images Using GPT-4 Generated Descriptive Prompts Without Human Annotation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2402.15759