U-Net and its variants for medical image segmentation: theory and applications

2020/11/02 by Nahian Siddique, Paheding Sidike, Sidike Paheding +2 · 34 citations
Computer Science · Engineering · #AI in cancer detection #Advanced Neural Network Applications #Medical Image Segmentation Techniques #cs.CV #cs.LG #eess.IV

paper · pdf · doi:10.1109/access.2021.3086020

42 pages, in IEEE Access

arxiv created 2020/11/02 · openalex created_date 2020/11/09 · openalex publication_date 2021/01/01 · arxiv updated 2021/06/10 · openalex updated_date 2026/08/03

Abstract

U-net is an image segmentation technique developed primarily for medical image analysis that can precisely segment images using a scarce amount of training data. These traits provide U-net with a very high utility within the medical imaging community and have resulted in extensive adoption of U-net as the primary tool for segmentation tasks in medical imaging. The success of U-net is evident in its widespread use in all major image modalities from CT scans and MRI to X-rays and microscopy. Furthermore, while U-net is largely a segmentation tool, there have been instances of the use of U-net in other applications. As the potential of U-net is still increasing, in this review we look at the various developments that have been made in the U-net architecture and provide observations on recent trends. We examine the various innovations that have been made in deep learning and discuss how these tools facilitate U-net. Furthermore, we look at image modalities and application areas where U-net has been applied.

Citations

• The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)
• THE DISTRIBUTION OF THE FLORA IN THE ALPINE ZONE.1
• Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response
• An introduction to ROC analysis
• DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
• W-Net: A Deep Model for Fully Unsupervised Image Segmentation
• Attention U-Net: Learning Where to Look for the Pancreas
• Dual-force convolutional neural networks for accurate brain tumor segmentation
• Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)
• H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT Volumes
• MSU-Net: Multiscale Statistical U-Net for Real-time 3D Cardiac MRI Video Segmentation
• A neural network approach to segment brain blood vessels in digital subtraction angiography
• Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation
• Attention U-Net Based Adversarial Architectures for Chest X-ray Lung Segmentation
• PanNuke Dataset Extension, Insights and Baselines
• COVID-19 Chest CT Image Segmentation -- A Deep Convolutional Neural Network Solution
• Fully Convolutional Networks for Semantic Segmentation
• H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes
• Generative Adversarial Nets
• Exploiting Generative AI to Scale up Intelligent Tutoring Systems

Cited by

• Comparing YOLOv8 and Mask R-CNN for instance segmentation in complex orchard environments
• Material combination optimization for brazed ceramic-metal composites using Artificial Intelligence
• Conditional Denoising Diffusion Model-Based Robust MR Image Reconstruction from Highly Undersampled Data
• Advances in Medical Image Segmentation: A Comprehensive Survey with a Focus on Lumbar Spine Applications
• Real‐Time MRI With Deep Learning for Efficient Evaluation of Neuromuscular Breathing Impairment
• Brain Tumor Detection Through Diverse CNN Architectures in IoT Healthcare Industries: Fast R-CNN, U-Net, Transfer Learning-Based CNN, and Fully Connected CNN
• Medical Image Segmentation Review: The Success of U-Net
• Filling MIDI Velocity using U-Net Image Colorizer
• Transfer Learning U-Net Deep Learning for Lung Ultrasound Segmentation
• Stereo Video Reconstruction Without Explicit Depth Maps for Endoscopic Surgery
• Improving U-Net Confidence on TEM Image Data with L2-Regularization, Transfer Learning, and Deep Fine-Tuning
• Chimeric U-Net – Modifying the standard U-Net towards explainability
• Alleviating Textual Reliance in Medical Language-guided Segmentation via Prototype-driven Semantic Approximation
• PRISM: Pointcloud Reintegrated Inference via Segmentation and Cross-attention for Manipulation
• OsteoCAD: A Human-in-the-Loop Cloud-Edge Framework for Bone Tumor Segmentation
• Cancer cytoplasm segmentation in hyperspectral cell image with data augmentation
• PDFNet: Pointwise Dense Flow Network for Urban-Scene Segmentation
• Magnetic resonance imaging–based radiation treatment plans for dogs may be feasible with the use of generative adversarial networks
• PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation
• Self-attention U-Net decoder for toric codes
• U-Net-and-a-half: Convolutional network for biomedical image segmentation using multiple expert-driven annotations
• Towards Operational Automated Greenhouse Gas Plume Detection
• Improving regional weather forecasts with neural interpolation
• NnU-Net versus mesh growing algorithm as a tool for the robust and timely segmentation of neurosurgical 3D images in contrast-enhanced T1 MRI scans
• Recent Advances in Medical Imaging Segmentation: A Survey
• How to build the best medical image segmentation algorithm using foundation models: a comprehensive empirical study with Segment Anything Model
• AI Alignment in Medical Imaging: Unveiling Hidden Biases Through Counterfactual Analysis
• Characterizing snow roughness: A novel low-cost portable tool based on ChArUco board and digital photography
• Dimension Scaling SR-Net for Super-Resolution Radar Range Profiles
• Transforming Hyperspectral Images Into Chemical Maps: A Novel End-to-End Deep Learning Approach
• Putting the Segment Anything Model to the Test with 3D Knee MRI - A Comparison with State-of-the-Art Performance
• TextDiffSeg: Text-guided Latent Diffusion Model for 3d Medical Images Segmentation
• Computationally Efficient Signal Detection with Unknown Bandwidths
• WoundAmbit: Bridging State-of-the-Art Semantic Segmentation and Real-World Wound Care
• Dynamic hysteresis model of grain-oriented ferromagnetic material using neural operators

Related

• U-Net and its variants for Medical Image Segmentation : A short review
• U-Net in Medical Image Segmentation: A Review of Its Applications Across Modalities
• Medical Image Segmentation Review: The Success of U-Net
• Medical Image Segmentation Review: The success of U-Net
• A Comprehensive Review of U-Net and Its Variants: Advances and Applications in Medical Image Segmentation