3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
Explore this paper's citation graph
Summary
The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts and performs on-the-fly elastic deformations for efficient data augmentation during training.
- Type
- preprint
- Published
- 2016-06-21
- Cited by
- 8,358
- References
- 16
- Access
- Open access
- OpenAlex
- https://openalex.org/W2951839332
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:2164893
Keywords
Computer science, Segmentation, Artificial intelligence, Annotation, Volume (thermodynamics)
References
- Deep MRI brain extraction: A 3D convolutional neural network for skull stripping
- Fully convolutional networks for semantic segmentation
- Hypercolumns for object segmentation and fine-grained localization
- Inversin relays Frizzled-8 signals to promote proximal pronephros development
- 3D Slicer as an Image Computing Platform for the Quantitative Imaging Network
- Renovascular imaging in the NSF Era
- XuvTools: free, fast and reliable stitching of large 3D datasets
- Image Segmentation with Cascaded Hierarchical Models and Logistic Disjunctive Normal Networks
- Caffe: Convolutional Architecture for Fast Feature Embedding
- Rethinking the Inception Architecture for Computer Vision
- Deep End2End Voxel2Voxel Prediction
- Hough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound
- Normal Table of Xenopus Laevis (Daudin)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- U-Net: Convolutional Networks for Biomedical Image Segmentation
Cited by
- A deep 3D residual CNN for false-positive reduction in pulmonary nodule detection.
- Learning U-Net Based Multi-Scale Features in Encoding-Decoding for MR Image Brain Tissue Segmentation
- RefineNet‐based 2D and 3D automatic segmentations for clinical target volume and organs at risks for patients with cervical cancer in postoperative radiotherapy
- VoteNet: A Deep Learning Label Fusion Method for Multi-Atlas Segmentation
- Automatic Lung Cancer Segmentation in [^18F]FDG PET/CT Using a Two-Stage Deep Learning Approach
- V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
- VoxResNet: Deep Voxelwise Residual Networks for Volumetric Brain Segmentation
- Multilevel Contextual 3-D CNNs for False Positive Reduction in Pulmonary Nodule Detection
- A Combinatorial Solution to Non-Rigid 3D Shape-to-Image Matching
- Automatic abdominal multi-organ segmentation using deep convolutional neural network and time-implicit level sets
- OctNet: Learning Deep 3D Representations at High Resolutions
- End-to-end learning of brain tissue segmentation from imperfect labeling
- Filter sharing: Efficient learning of parameters for volumetric convolutions
- CNN-based Segmentation of Medical Imaging Data
- FusionNet: A Deep Fully Residual Convolutional Neural Network for Image Segmentation in Connectomics
- Spatial aggregation of holistically‐nested convolutional neural networks for automated pancreas localization and segmentation☆
- 3D skeletal uptake of 18F sodium fluoride in PET/CT images is associated with overall survival in patients with prostate cancer
- Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach
- Automatic Liver and Tumor Segmentation of CT and MRI Volumes using Cascaded Fully Convolutional Neural Networks
- fastER: a user‐friendly tool for ultrafast and robust cell segmentation in large‐scale microscopy
Related papers
- A survey on deep learning in medical image analysis
- V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation
- DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
- Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
- Deep Residual Learning for Image Recognition
- ImageNet classification with deep convolutional neural networks
- Going deeper with convolutions