# MedUniSeg: 2D and 3D Medical Image Segmentation via a Prompt-driven Universal Model

arXiv: https://arxiv.org/abs/2410.05905 · HTML: https://mlsanity.com/paper/2410.05905/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 87 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Builds on (most cited first, 30 of 57)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Kvasir-SEG: A Segmented Polyp Dataset](https://mlsanity.com/paper/1911.07069/) (2019)
- [The RSNA-ASNR-MICCAI BraTS 2021 Benchmark on Brain Tumor Segmentation and Radiogenomic Classification](https://mlsanity.com/paper/2107.02314/) (2021)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [PraNet: Parallel Reverse Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2006.11392/) (2020)
- [Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis](https://mlsanity.com/paper/2111.14791/) (2021)
- [U-Mamba: Enhancing Long-range Dependency for Biomedical Image Segmentation](https://mlsanity.com/paper/2401.04722/) (2024)
- [What Makes Training Multi-Modal Classification Networks Hard?](https://mlsanity.com/paper/1905.12681/) (2019)
- [Med3D: Transfer Learning for 3D Medical Image Analysis](https://mlsanity.com/paper/1904.00625/) (2019)
- [CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.03024/) (2021)
- [CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection](https://mlsanity.com/paper/2301.00785/) (2023)
- [Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest](https://mlsanity.com/paper/1603.00275/) (2016)
- [The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge](https://mlsanity.com/paper/1912.01054/) (2019)
- [nnFormer: Interleaved Transformer for Volumetric Segmentation](https://mlsanity.com/paper/2109.03201/) (2021)
- [U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation](https://mlsanity.com/paper/2406.02918/) (2024)
- [Benchmarking Self-Supervised Learning on Diverse Pathology Datasets](https://mlsanity.com/paper/2212.04690/) (2022)
- [MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology](https://mlsanity.com/paper/2301.02228/) (2023)
- [Domain Adaptation via Prompt Learning](https://mlsanity.com/paper/2202.06687/) (2022)
- [Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images](https://mlsanity.com/paper/2302.14042/) (2023)
- [Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)](https://mlsanity.com/paper/2203.12221/) (2022)
- [VerSe: A Vertebrae Labelling and Segmentation Benchmark for Multi-detector CT Images](https://mlsanity.com/paper/2001.09193/) (2020)
- [DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets](https://mlsanity.com/paper/2011.10217/) (2020)
- [3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2209.15076/) (2022)
- [Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation](https://mlsanity.com/paper/1904.06346/) (2019)

## Built on by (most cited first, 7 of 7)

- [Large-Scale 3D Medical Image Pre-training with Geometric Context Priors](https://mlsanity.com/paper/2410.09890/) (2024)
- [Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation](https://mlsanity.com/paper/2601.10880/) (2026)
- [Show and Segment: Universal Medical Image Segmentation via In-Context Learning](https://mlsanity.com/paper/2503.19359/) (2025)
- [COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets](https://mlsanity.com/paper/2508.09886/) (2025)
- [MedSeqFT: Sequential Fine-tuning Foundation Models for 3D Medical Image Segmentation](https://mlsanity.com/paper/2509.06096/) (2025)
- [Prompt Mechanisms in Medical Imaging: A Comprehensive Survey](https://mlsanity.com/paper/2507.01055/) (2025)
- [DpDNet: An Dual-Prompt-Driven Network for Universal PET-CT Segmentation](https://mlsanity.com/paper/2507.07126/) (2025)

## Abstract (arXiv)

Universal segmentation models offer significant potential in addressing a wide range of tasks by effectively leveraging discrete annotations. As the scope of tasks and modalities expands, it becomes increasingly important to generate and strategically position task- and modal-specific priors within the universal model. However, existing universal models often overlook the correlations between different priors, and the optimal placement and frequency of these priors remain underexplored. In this paper, we introduce MedUniSeg, a prompt-driven universal segmentation model designed for 2D and 3D multi-task segmentation across diverse modalities and domains. MedUniSeg employs multiple modal-specific prompts alongside a universal task prompt to accurately characterize the modalities and tasks. To generate the related priors, we propose the modal map (MMap) and the fusion and selection (FUSE) modules, which transform modal and task prompts into corresponding priors. These modal and task priors are systematically introduced at the start and end of the encoding process. We evaluate MedUniSeg on a comprehensive multi-modal upstream dataset consisting of 17 sub-datasets. The results demonstrate that MedUniSeg achieves superior multi-task segmentation performance, attaining a 1.2% improvement in the mean Dice score across the 17 upstream tasks compared to nnUNet baselines, while using less than 1/10 of the parameters. For tasks that underperform during the initial multi-task joint training, we freeze MedUniSeg and introduce new modules to re-learn these tasks. This approach yields an enhanced version, MedUniSeg*, which consistently outperforms MedUniSeg across all tasks. Moreover, MedUniSeg surpasses advanced self-supervised and supervised pre-trained models on six downstream tasks, establishing itself as a high-quality, highly generalizable pre-trained segmentation model.