# TV-SAM: Increasing Zero-Shot Segmentation Performance on Multimodal Medical Images Using GPT-4 Generated Descriptive Prompts Without Human Annotation

arXiv: https://arxiv.org/abs/2402.15759 · HTML: https://mlsanity.com/paper/2402.15759/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 47 references that are in the map.
- First posted on arXiv 24 Feb 2024.

## Builds on (most cited first, 25 of 25)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [PraNet: Parallel Reverse Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2006.11392/) (2020)
- [A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications](https://mlsanity.com/paper/2402.07927/) (2024)
- [CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation](https://mlsanity.com/paper/2001.06535/) (2020)
- [Segment Anything Model for Medical Image Analysis: an Experimental Study](https://mlsanity.com/paper/2304.10517/) (2023)
- [Segment Anything in Medical Images](https://mlsanity.com/paper/2304.12306/) (2023)
- [Can AI help in screening Viral and COVID-19 pneumonia?](https://mlsanity.com/paper/2003.13145/) (2020)
- [Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imaging](https://mlsanity.com/paper/2304.04155/) (2023)
- [SAM-Med2D](https://mlsanity.com/paper/2308.16184/) (2023)
- [Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applications](https://mlsanity.com/paper/2304.05750/) (2023)
- [SAM-Med3D: Towards General-purpose Segmentation Models for Volumetric Medical Images](https://mlsanity.com/paper/2310.15161/) (2023)
- [Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection](https://mlsanity.com/paper/2304.04709/) (2023)
- [SAM on Medical Images: A Comprehensive Study on Three Prompt Modes](https://mlsanity.com/paper/2305.00035/) (2023)
- [Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study](https://mlsanity.com/paper/2209.15517/) (2022)
- [Radiology-GPT: A Large Language Model for Radiology](https://mlsanity.com/paper/2306.08666/) (2023)
- [Multimodal ChatGPT for Medical Applications: an Experimental Study of GPT-4V](https://mlsanity.com/paper/2310.19061/) (2023)
- [DCSAU-Net: A Deeper and More Compact Split-Attention U-Net for Medical Image Segmentation](https://mlsanity.com/paper/2202.00972/) (2022)

## Built on by (most cited first, 5 of 5)

- [Taming Vision-Language Models for Medical Image Analysis: A Comprehensive Review](https://mlsanity.com/paper/2506.18378/) (2025)
- [Zero-shot Emotion Annotation in Facial Images Using Large Multimodal Models: Benchmarking and Prospects for Multi-Class, Multi-Frame Approaches](https://mlsanity.com/paper/2502.12454/) (2025)
- [Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges](https://mlsanity.com/paper/2507.09562/) (2025)
- [AutoMiSeg: Automatic Medical Image Segmentation via Test-Time Adaptation of Foundation Models](https://mlsanity.com/paper/2505.17931/) (2025)
- [CT Radiomics-Based Explainable Machine Learning Model for Accurate Differentiation of Malignant and Benign Endometrial Tumors: A Two-Center Study](https://mlsanity.com/paper/2506.18106/) (2025)

## Abstract (arXiv)

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.