Zeus: Zero-shot LLM Instruction for Union Segmentation in Multimodal Medical Imaging
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915235729768448 |
|---|---|
| author | Dai, Siyuan Ye, Kai Liu, Guodong Tang, Haoteng Zhan, Liang |
| author_facet | Dai, Siyuan Ye, Kai Liu, Guodong Tang, Haoteng Zhan, Liang |
| contents | Medical image segmentation has achieved remarkable success through the continuous advancement of UNet-based and Transformer-based foundation backbones. However, clinical diagnosis in the real world often requires integrating domain knowledge, especially textual information. Conducting multimodal learning involves visual and text modalities shown as a solution, but collecting paired vision-language datasets is expensive and time-consuming, posing significant challenges. Inspired by the superior ability in numerous cross-modal tasks for Large Language Models (LLMs), we proposed a novel Vision-LLM union framework to address the issues. Specifically, we introduce frozen LLMs for zero-shot instruction generation based on corresponding medical images, imitating the radiology scanning and report generation process. {To better approximate real-world diagnostic processes}, we generate more precise text instruction from multimodal radiology images (e.g., T1-w or T2-w MRI and CT). Based on the impressive ability of semantic understanding and rich knowledge of LLMs. This process emphasizes extracting special features from different modalities and reunion the information for the ultimate clinical diagnostic. With generated text instruction, our proposed union segmentation framework can handle multimodal segmentation without prior collected vision-language datasets. To evaluate our proposed method, we conduct comprehensive experiments with influential baselines, the statistical results and the visualized case study demonstrate the superiority of our novel method.} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07336 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Zeus: Zero-shot LLM Instruction for Union Segmentation in Multimodal Medical Imaging Dai, Siyuan Ye, Kai Liu, Guodong Tang, Haoteng Zhan, Liang Computer Vision and Pattern Recognition Artificial Intelligence Medical image segmentation has achieved remarkable success through the continuous advancement of UNet-based and Transformer-based foundation backbones. However, clinical diagnosis in the real world often requires integrating domain knowledge, especially textual information. Conducting multimodal learning involves visual and text modalities shown as a solution, but collecting paired vision-language datasets is expensive and time-consuming, posing significant challenges. Inspired by the superior ability in numerous cross-modal tasks for Large Language Models (LLMs), we proposed a novel Vision-LLM union framework to address the issues. Specifically, we introduce frozen LLMs for zero-shot instruction generation based on corresponding medical images, imitating the radiology scanning and report generation process. {To better approximate real-world diagnostic processes}, we generate more precise text instruction from multimodal radiology images (e.g., T1-w or T2-w MRI and CT). Based on the impressive ability of semantic understanding and rich knowledge of LLMs. This process emphasizes extracting special features from different modalities and reunion the information for the ultimate clinical diagnostic. With generated text instruction, our proposed union segmentation framework can handle multimodal segmentation without prior collected vision-language datasets. To evaluate our proposed method, we conduct comprehensive experiments with influential baselines, the statistical results and the visualized case study demonstrate the superiority of our novel method.} |
| title | Zeus: Zero-shot LLM Instruction for Union Segmentation in Multimodal Medical Imaging |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2504.07336 |