CNN-based Segmentation of Medical Imaging Data

Abstract

Convolutional neural networks have been applied to a wide variety of computer vision tasks. Recent advances in semantic segmentation have enabled their application to medical image segmentation. While most CNNs use two-dimensional kernels, recent CNN-based publications on medical image segmentation featured three-dimensional kernels, allowing full access to the three-dimensional structure of medical images. Though closely related to semantic segmentation, medical image segmentation includes specific challenges that need to be addressed, such as the scarcity of labelled data, the high class imbalance found in the ground truth and the high memory demand of three-dimensional images. In this work, a CNN-based method with three-dimensional filters is demonstrated and applied to hand and brain MRI. Two modifications to an existing CNN architecture are discussed, along with methods on addressing the aforementioned challenges. While most of the existing literature on medical image segmentation focuses on soft tissue and the major organs, this work is validated on data both from the central nervous system as well as the bones of the hand.

arXiv comment24 pages, Code available on https://github.com/BRML/CNNbasedMedicalSegmentation

References in corpus (20)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Brain Tumor Segmentation with Deep Neural Networks
• Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
• Striving for Simplicity: The All Convolutional Net
• Deeply-Supervised Nets
• Fully Convolutional Networks for Semantic Segmentation
• Learning Deconvolution Network for Semantic Segmentation
• 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
• Visualizing and Understanding Convolutional Networks
• Identity Mappings in Deep Residual Networks
• DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation
• VoxResNet: Deep Voxelwise Residual Networks for Volumetric Brain Segmentation
• The Importance of Skip Connections in Biomedical Image Segmentation
• 3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes
• Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Classification
• Accurate Image Super-Resolution Using Very Deep Convolutional Networks
• Closed-Form Training of Conditional Random Fields for Large Scale Image Segmentation
• Superpixel Convolutional Networks using Bilateral Inceptions

Cited by in corpus (28)

• Automated brain extraction of multi-sequence MRI using artificial neural networks
• Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image Segmentation
• Deep and Statistical Learning in Biomedical Imaging: State of the Art in 3D MRI Brain Tumor Segmentation
• Scalable Neural Architecture Search for 3D Medical Image Segmentation
• Automatic Cardiac Disease Assessment on cine-MRI via Time-Series Segmentation and Domain Specific Features
• DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks
• Deep Learning for Lung Cancer Detection: Tackling the Kaggle Data Science Bowl 2017 Challenge
• Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis
• Low-Memory Neural Network Training: A Technical Report
• COVID-19 Screening Using Residual Attention Network an Artificial Intelligence Approach
• Multi-level Context Gating of Embedded Collective Knowledge for Medical Image Segmentation
• Reconstructing Patchy Reionization with Deep Learning
• Domain specific cues improve robustness of deep learning based segmentation of ct volumes
• Autofocus Layer for Semantic Segmentation
• Reconstructing Cosmic Polarization Rotation with ResUNet-CMB
• Responsible AI: Gender bias assessment in emotion recognition
• 3D U${}^2$-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation
• Few Labeled Atlases are Necessary for Deep-Learning-Based Segmentation
• Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data
• Multiclass Spinal Cord Tumor Segmentation on MRI with Deep Learning
• 3D Consistent & Robust Segmentation of Cardiac Images by Deep Learning with Spatial Propagation
• CU-Net: Cascaded U-Net with Loss Weighted Sampling for Brain Tumor Segmentation
• Segmentation of Head and Neck Organs at Risk Using CNN with Batch Dice Loss
• Convolutional Recurrent Residual U-Net Embedded with Attention Mechanism and Focal Tversky Loss Function for Cancerous Nuclei Detection
• Automated Human Claustrum Segmentation using Deep Learning Technologies
• Self-supervised Lesion Change Detection and Localisation in Longitudinal Multiple Sclerosis Brain Imaging
• An Automatic Cardiac Segmentation Framework based on Multi-sequence MR Image
• Morphological Operation Residual Blocks: Enhancing 3D Morphological Feature Representation in Convolutional Neural Networks for Semantic Segmentation of Medical Images