U-Net: Convolutional Networks for Biomedical Image Segmentation

@article{Ronneberger2015UNetCN,
  title={U-Net: Convolutional Networks for Biomedical Image Segmentation},
  author={Olaf Ronneberger and Philipp Fischer and Thomas Brox},
  journal={ArXiv},
  year={2015},
  volume={abs/1505.04597}
}
There is large consent that successful training of deep networks requires many thousand annotated training samples. [] Key Method We show 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. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge…
View PDF on arXiv
42,689 Citations
Highly Influential Citations
8,120
Background Citations
11,093
Methods Citations
19,786
Results Citations
545

42,689 Citations

KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation

A new architecture for im- age segmentation- KiU-Net is designed which has two branches: an overcomplete convolutional network Kite-Net which learns to capture fine details and accurate edges of the input, and (2) U- net which learns high level features.

A Learning-Guided Hierarchical Approach for Biomedical Image Segmentation

This paper proposes and experimentally evaluates a more efficient framework, especially suited for image segmentation on embedded systems, that involves first “tiling” the target image, followed by processing the tiles that only contain an object of interest in a hierarchical fashion.

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.

O-Net: An Overall Convolutional Network for Segmentation Tasks

This work introduces a novel architecture, namely the Overall Convolutional Network (O-Net), which takes advantage of different pooling levels and convolutional layers to extract more deeper local and containing global context.

KUnet: Microscopy Image Segmentation With Deep Unet Based Convolutional Networks

The most powerful structure for encoder of Unet is discovered through plentiful experiments and comparison of multiple deep learning models and it is successfully enable the best model to perform spatiotemporal encoding.

DoubleU-Net: A Deep Convolutional Neural Network for Medical Image Segmentation

Encouraging results show that DoubleU-Net can be used as a strong baseline for both medical image segmentation and cross-dataset evaluation testing to measure the generalizability of Deep Learning (DL) models.

Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation

Dense Dilated Deep Multiscale Supervised U-Network for biomedical image segmentation

An Auto-Encoder Strategy for Adaptive Image Segmentation

A novel perspective of segmentation as a discrete representation learning problem is proposed, and a variational autoencoder segmentation strategy that is flexible and adaptive is presented, which can be a single unpaired segmentation image.

Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding

...

References

SHOWING 1-10 OF 16 REFERENCES

Fully convolutional networks for semantic segmentation

The key insight is to build “fully convolutional” networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning.

Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images

This work addresses a central problem of neuroanatomy, namely, the automatic segmentation of neuronal structures depicted in stacks of electron microscopy images, using a special type of deep artificial neural network as a pixel classifier to segment biological neuron membranes.

Very Deep Convolutional Networks for Large-Scale Image Recognition

This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.

ImageNet classification with deep convolutional neural networks

A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.

Caffe: Convolutional Architecture for Fast Feature Embedding

Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures.

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.

Hypercolumns for object segmentation and fine-grained localization

Using hypercolumns as pixel descriptors, this work defines the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel, and shows results on three fine-grained localization tasks: simultaneous detection and segmentation, and keypoint localization.

Image Segmentation with Cascaded Hierarchical Models and Logistic Disjunctive Normal Networks

This work proposes a multi-resolution contextual framework, called cascaded hierarchical model (CHM), which learns contextual information in a hierarchical framework for image segmentation, and introduces a novel classification scheme, called logistic disjunctive normal networks (LDNN), which outperforms state-of-the-art classifiers and can be used in the CHM to improve object segmentation performance.

Fully Convolutional Multi-Class Multiple Instance Learning

This work proposes a novel MIL formulation of multi-class semantic segmentation learning by a fully convolutional network that exploits the further supervision given by images with multiple labels.

A benchmark for comparison of cell tracking algorithms

Six algorithms covering a variety of segmentation and tracking paradigms have been compared and ranked based on their performance on both synthetic and real datasets in the Cell Tracking Challenge.