# DFGET: Displacement-Field Assisted Graph Energy Transmitter for Gland Instance Segmentation

arXiv: https://arxiv.org/abs/2312.07584 · HTML: https://mlsanity.com/paper/2312.07584/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 11 Dec 2023.

## Builds on (most cited first, 28 of 28)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation](https://mlsanity.com/paper/2004.08790/) (2020)
- [GRAND: Graph Neural Diffusion](https://mlsanity.com/paper/2106.10934/) (2021)
- [A Note on Over-Smoothing for Graph Neural Networks](https://mlsanity.com/paper/2006.13318/) (2020)
- [Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest](https://mlsanity.com/paper/1603.00275/) (2016)
- [Directional Graph Networks](https://mlsanity.com/paper/2010.02863/) (2020)
- [Graph-Coupled Oscillator Networks](https://mlsanity.com/paper/2202.02296/) (2022)
- [Instance-aware Semantic Segmentation via Multi-task Network Cascades](https://mlsanity.com/paper/1512.04412/) (2015)
- [UTNet: A Hybrid Transformer Architecture for Medical Image Segmentation](https://mlsanity.com/paper/2107.00781/) (2021)
- [MILD-Net: Minimal Information Loss Dilated Network for Gland Instance Segmentation in Colon Histology Images](https://mlsanity.com/paper/1806.01963/) (2018)
- [DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion](https://mlsanity.com/paper/2301.09474/) (2023)
- [DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation](https://mlsanity.com/paper/1604.02677/) (2016)
- [Micro-Net: A unified model for segmentation of various objects in microscopy images](https://mlsanity.com/paper/1804.08145/) (2018)
- [ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks](https://mlsanity.com/paper/2206.05437/) (2022)
- [TA-Net: Topology-Aware Network for Gland Segmentation](https://mlsanity.com/paper/2110.14593/) (2021)
- [Pairwise Relation Learning for Semi-supervised Gland Segmentation](https://mlsanity.com/paper/2008.02699/) (2020)
- [Gland Instance Segmentation Using Deep Multichannel Neural Networks](https://mlsanity.com/paper/1611.06661/) (2016)
- [The nonlinear heat equation on dense graphs and graph limits](https://mlsanity.com/paper/1302.5804/) (2013)
- [Two-Stream Graph Convolutional Network for Intra-oral Scanner Image Segmentation](https://mlsanity.com/paper/2204.08797/) (2022)

## Abstract (arXiv)

Gland instance segmentation is an essential but challenging task in the diagnosis and treatment of adenocarcinoma. The existing models usually achieve gland instance segmentation through multi-task learning and boundary loss constraint. However, how to deal with the problems of gland adhesion and inaccurate boundary in segmenting the complex samples remains a challenge. In this work, we propose a displacement-field assisted graph energy transmitter (DFGET) framework to solve these problems. Specifically, a novel message passing manner based on anisotropic diffusion is developed to update the node features, which can distinguish the isomorphic graphs and improve the expressivity of graph nodes for complex samples. Using such graph framework, the gland semantic segmentation map and the displacement field (DF) of the graph nodes are estimated with two graph network branches. With the constraint of DF, a graph cluster module based on diffusion theory is presented to improve the intra-class feature consistency and inter-class feature discrepancy, as well as to separate the adherent glands from the semantic segmentation maps. Extensive comparison and ablation experiments on the GlaS dataset demonstrate the superiority of DFGET and effectiveness of the proposed anisotropic message passing manner and clustering method. Compared to the best comparative model, DFGET increases the object-Dice and object-F1 score by 2.5% and 3.4% respectively, while decreases the object-HD by 32.4%, achieving state-of-the-art performance.