# NexToU: Efficient Topology-Aware U-Net for Medical Image Segmentation

arXiv: https://arxiv.org/abs/2305.15911 · HTML: https://mlsanity.com/paper/2305.15911/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 26 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 17 of 17)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation](https://mlsanity.com/paper/2105.05537/) (2021)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [DeepGCNs: Can GCNs Go as Deep as CNNs?](https://mlsanity.com/paper/1904.03751/) (2019)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [Vision GNN: An Image is Worth Graph of Nodes](https://mlsanity.com/paper/2206.00272/) (2022)
- [UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation](https://mlsanity.com/paper/2212.04497/) (2022)
- [Deep Vessel Segmentation By Learning Graphical Connectivity](https://mlsanity.com/paper/1806.02279/) (2018)
- [Learning Topological Interactions for Multi-Class Medical Image Segmentation](https://mlsanity.com/paper/2207.09654/) (2022)
- [Vox2Cortex: Fast Explicit Reconstruction of Cortical Surfaces from 3D MRI Scans with Geometric Deep Neural Networks](https://mlsanity.com/paper/2203.09446/) (2022)
- [CPR-GCN: Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary Arteries](https://mlsanity.com/paper/2003.08560/) (2020)
- [PHTrans: Parallelly Aggregating Global and Local Representations for Medical Image Segmentation](https://mlsanity.com/paper/2203.04568/) (2022)
- [RAVIR: A Dataset and Methodology for the Semantic Segmentation and Quantitative Analysis of Retinal Arteries and Veins in Infrared Reflectance Imaging](https://mlsanity.com/paper/2203.14928/) (2022)
- [Automated Intracranial Artery Labeling using a Graph Neural Network and Hierarchical Refinement](https://mlsanity.com/paper/2007.14472/) (2020)

## Built on by (most cited first, 10 of 10)

- [The TopCoW Challenge -- Topology-Aware Circle of Willis Segmentation for CT and MR Angiography](https://mlsanity.com/paper/2312.17670/) (2023)
- [Centerline Boundary Dice Loss for Vascular Segmentation](https://mlsanity.com/paper/2407.01517/) (2024)
- [Auditing Significance, Metric Choice, and Demographic Fairness in Medical AI Challenges](https://mlsanity.com/paper/2512.19091/) (2025)
- [Topology-Aware Exploration of Circle of Willis for CTA and MRA: Segmentation, Detection, and Classification](https://mlsanity.com/paper/2410.15614/) (2024)
- [Topology-Aware Wavelet Mamba for Airway Structure Segmentation in Postoperative Recurrent Nasopharyngeal Carcinoma CT Scans](https://mlsanity.com/paper/2502.14363/) (2025)
- [A Systematic Review on the Generative AI Applications in Human Medical Genomics](https://mlsanity.com/paper/2508.20275/) (2025)
- [Anatomy Aware Cascade Network: Bridging Epistemic Uncertainty and Geometric Manifold for 3D Tooth Segmentation](https://mlsanity.com/paper/2601.07499/) (2026)
- [CoralLite: μCT Reconstruction of Coral Colonies from Individual Corallites](https://mlsanity.com/paper/2605.15093/) (2026)
- [Beyond Volume Overlap: Surface Matching for Topology-Aware Coronary Artery Segmentation](https://mlsanity.com/paper/2609.31740/) (2026)
- [Topology-Informed Prompt-Conditioned Universal Segmentation of Uterine Structures from Ultrasound and MRI](https://mlsanity.com/paper/2610.06494/) (2026)

## Abstract (arXiv)

Convolutional neural networks (CNN) and Transformer variants have emerged as the leading medical image segmentation backbones. Nonetheless, due to their limitations in either preserving global image context or efficiently processing irregular shapes in visual objects, these backbones struggle to effectively integrate information from diverse anatomical regions and reduce inter-individual variability, particularly for the vasculature. Motivated by the successful breakthroughs of graph neural networks (GNN) in capturing topological properties and non-Euclidean relationships across various fields, we propose NexToU, a novel hybrid architecture for medical image segmentation. NexToU comprises improved Pool GNN and Swin GNN modules from Vision GNN (ViG) for learning both global and local topological representations while minimizing computational costs. To address the containment and exclusion relationships among various anatomical structures, we reformulate the topological interaction (TI) module based on the nature of binary trees, rapidly encoding the topological constraints into NexToU. Extensive experiments conducted on three datasets (including distinct imaging dimensions, disease types, and imaging modalities) demonstrate that our method consistently outperforms other state-of-the-art (SOTA) architectures. All the code is publicly available at https://github.com/PengchengShi1220/NexToU.