# Zeus: Zero-shot LLM Instruction for Union Segmentation in Multimodal Medical Imaging

arXiv: https://arxiv.org/abs/2504.07336 · HTML: https://mlsanity.com/paper/2504.07336/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 66 references that are in the map.
- First posted on arXiv 9 Apr 2025.

## Builds on (most cited first, 30 of 38)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Galactica: A Large Language Model for Science](https://mlsanity.com/paper/2211.09085/) (2022)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation](https://mlsanity.com/paper/1912.05074/) (2019)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks](https://mlsanity.com/paper/2305.11175/) (2023)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)
- [VirTex: Learning Visual Representations from Textual Annotations](https://mlsanity.com/paper/2006.06666/) (2020)
- [ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge](https://mlsanity.com/paper/2303.14070/) (2023)
- [CHAOS Challenge -- Combined (CT-MR) Healthy Abdominal Organ Segmentation](https://mlsanity.com/paper/2001.06535/) (2020)
- [A Survey on Multimodal Large Language Models for Autonomous Driving](https://mlsanity.com/paper/2311.12320/) (2023)
- [Multimodal Deep Learning](https://mlsanity.com/paper/2301.04856/) (2023)
- [Medical Image Segmentation Review: The success of U-Net](https://mlsanity.com/paper/2211.14830/) (2022)
- [UNeXt: MLP-based Rapid Medical Image Segmentation Network](https://mlsanity.com/paper/2203.04967/) (2022)
- [ResViT: Residual vision transformers for multi-modal medical image synthesis](https://mlsanity.com/paper/2106.16031/) (2021)
- [Learning Visual Features from Large Weakly Supervised Data](https://mlsanity.com/paper/1511.02251/) (2015)

## Built on by (most cited first, 4 of 4)

- [Why Text Prevails: Vision May Undermine Multimodal Medical Decision Making](https://mlsanity.com/paper/2512.13747/) (2025)
- [MedPrompt: LLM-CNN Fusion with Weight Routing for Medical Image Segmentation and Classification](https://mlsanity.com/paper/2506.21199/) (2025)
- [ChiMed 2.0: Advancing Chinese Medical Dataset in Facilitating Large Language Modeling](https://mlsanity.com/paper/2507.15275/) (2025)
- [FigEx2: Visual-Conditioned Panel Detection and Captioning for Scientific Compound Figures](https://mlsanity.com/paper/2601.08026/) (2026)

## Abstract (arXiv)

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.}