U-Net: Convolutional Networks for Biomedical Image Segmentation

Abstract

There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. 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 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net .

conditionally accepted at MICCAI 2015

References in corpus (2)

• Fully Convolutional Multi-Class Multiple Instance Learning
• Hypercolumns for Object Segmentation and Fine-grained Localization

Cited by in corpus (32)

• TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentation
• Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
• GAP-net for Snapshot Compressive Imaging
• Estimation of the volume of the left ventricle from MRI images using deep neural networks
• Detection of Tooth caries in Bitewing Radiographs using Deep Learning
• Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis
• Optimizing Sparse RFI Prediction using Deep Learning
• CARPool: fast, accurate computation of large-scale structure statistics by pairing costly and cheap cosmological simulations
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• Deep Learning Convolutional Networks for Multiphoton Microscopy Vasculature Segmentation
• A global method to identify trees outside of closed-canopy forests with medium-resolution satellite imagery
• Deep learning approach for identification of HII regions during reionization in 21-cm observations
• Interpretability of a Deep Learning Model in the Application of Cardiac MRI Segmentation with an ACDC Challenge Dataset
• Cleaning our own Dust: Simulating and Separating Galactic Dust Foregrounds with Neural Networks
• SAN: Scale-Aware Network for Semantic Segmentation of High-Resolution Aerial Images
• Image Deconvolution via Noise-Tolerant Self-Supervised Inversion
• Predicting 21cm-line map from Lyman $\alpha$ emitter distribution with Generative Adversarial Networks
• Scalable, End-to-End, Deep-Learning-Based Data Reconstruction Chain for Particle Imaging Detectors
• Self-Adaptive 2D-3D Ensemble of Fully Convolutional Networks for Medical Image Segmentation
• A Multiscale Patch Based Convolutional Network for Brain Tumor Segmentation
• Cardiac MRI Image Segmentation for Left Ventricle and Right Ventricle using Deep Learning
• Cosmic-CoNN: A Cosmic Ray Detection Deep-Learning Framework, Dataset, and Toolkit
• Predicting Localized Primordial Star Formation with Deep Convolutional Neural Networks
• Air, bone and soft-tissue Segmentation on 3D brain MRI Using Semantic Classification Random Forest with Auto-Context Model
• Recurrent U-net: Deep learning to predict daily summertime ozone in the United States
• Approximated Orthonormal Normalisation in Training Neural Networks
• Discovering Hidden Physics Behind Transport Dynamics
• Identification of images of COVID-19 from Chest Computed Tomography (CT) images using Deep learning: Comparing COGNEX VisionPro Deep Learning 1.0 Software with Open Source Convolutional Neural Networks
• On-the-fly Prediction of Protein Hydration Densities and Free Energies using Deep Learning
• Investigations of the Influences of a CNN's Receptive Field on Segmentation of Subnuclei of Bilateral Amygdalae
• Gaussian Filter in CRF Based Semantic Segmentation
• Using constraint structure and an improved object detection network to detect the 12^{th} Vertebra from CT images with a limited field of view for image-guided radiotherapy