Point-Unet: A Context-Aware Point-Based Neural Network for Volumetric Segmentation

  title={Point-Unet: A Context-Aware Point-Based Neural Network for Volumetric Segmentation},
  author={Ngoc-Vuong Ho and Tan H. Nguyen and Gia-Han Diep and Ngan T. H. Le and Binh-Son Hua},
Medical image analysis using deep learning has recently been prevalent, showing great performance for various downstream tasks including medical image segmentation and its sibling, volumetric image segmentation. Particularly, a typical volumetric segmentation network strongly relies on a voxel grid representation which treats volumetric data as a stack of individual voxel ‘slices’, which allows learning to segment a voxel grid to be as straightforward as extending existing image-based… 

PointNeuron: 3D Neuron Reconstruction via Geometry and Topology Learning of Point Clouds

A novel framework for 3D neuron reconstruction that adopts one graph convolutional network to predict the neural skeleton points and another to produce the connectivity of these points to achieve competitive neuron reconstruction performance.

Super-Resolution Based Patch-Free 3D Medical Image Segmentation with Self-Supervised Guidance

A super-resolution (SR) guided patch-free 3D medical image segmentation framework that can realize HR segmentation with global information of low- resolution (LR) input and has a four times higher inference speed compared to traditional patch-based methods.

3DConvCaps: 3DUnet with Convolutional Capsule Encoder for Medical Image Segmentation

This paper proposes a 3D encoder-decoder network with Convolutional Capsule Encoder (called 3DConvCaps) to learn lower-level features (short-range attention) with convolutional layers while modeling the higher- level features (long-range dependence) with capsule layers.

ImplicitAtlas: Learning Deformable Shape Templates in Medical Imaging

The proposed framework, named ImplicitAtlas, represents a shape as a deformation field from a learned template field, where multiple templates could be integrated to improve the shape representation at negligible computational cost.

EmbryosFormer: Deformable Transformer and Collaborative Encoding-Decoding for Embryos Stage Development Classification

EmbryosFormer, a computational model to automatically de-tect and classify cell divisions from original time-lapse images, is proposed, designed as an encoder-decoder deformable transformer with collaborative heads.

SS-3DCAPSNET: Self-Supervised 3d Capsule Networks for Medical Segmentation on Less Labeled Data

This work extends capsule networks for volumetric medical image segmentation with self-supervised learning for capsule networks pre-training to improve on the problem of weight initialization compared to previous capsule networks.



V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once.

3D Dilated Multi-Fiber Network for Real-time Brain Tumor Segmentation in MRI

This work proposes a highly efficient 3D CNN to achieve real-time dense volumetric segmentation of brain MRI volumes that leverages the 3D multi-fiber unit which consists of an ensemble of lightweight 3D convolutional networks to significantly reduce the computational cost.

A 3D Coarse-to-Fine Framework for Volumetric Medical Image Segmentation

3D Convolutional Neural Networks are adopted to segment volumetric medical images and outperforms the 2D counterpart to a large margin since it can leverage the rich spatial information along all three axes.

A Fixed-Point Model for Pancreas Segmentation in Abdominal CT Scans

This paper forms a fixed-point model which uses a predicted segmentation mask to shrink the input region and outperform the state-of-the-art by more than \(4\%\), measured by the average Dice-Sorensen Coefficient (DSC).

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

Brain Tumor Segmentation Using an Ensemble of 3D U-Nets and Overall Survival Prediction Using Radiomic Features

A linear model based on the radiomics features extracted from segmentation and other clinical features are developed to predict patient overall survival and show high prediction accuracy in both low-grade glioma and glioblastoma patients.

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation

This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.

Dynamic Graph CNN for Learning on Point Clouds

This work proposes a new neural network module suitable for CNN-based high-level tasks on point clouds, including classification and segmentation called EdgeConv, which acts on graphs dynamically computed in each layer of the network.

Learning High-Resolution and Efficient Non-local Features for Brain Glioma Segmentation in MR Images

A 3D High-resolution and Non-local Feature Network for brain glioma segmentation using multi-parametric MR imaging based on the parallel multi-scale fusion (PMF) module and the expectation-maximization attention (EMA) module is introduced, aiming to capture the long-range dependent contextual information and reduce the feature redundancy in a lightweight fashion.