Filters








2,145 Hits in 7.6 sec

Automatic Brain Structures Segmentation Using Deep Residual Dilated U-Net [article]

Hongwei Li, Andrii Zhygallo, Bjoern Menze
2018 arXiv   pre-print
We present an automated ap-proach using 2D deep residual dilated networks which captures rich context information of different tissues for the segmentation of eight brain structures.  ...  Brain image segmentation is used for visualizing and quantifying anatomical structures of the brain.  ...  Deep dilated residual U-Net was adopted to learn context and texture information of different brain tissues.  ... 
arXiv:1811.04312v1 fatcat:qqwlpycmtfbcbhobjzxdf4awfi

Dilated deeply supervised networks for hippocampus segmentation in MRI [article]

Lukas Folle, Sulaiman Vesal, Nishant Ravikumar, Andreas Maier
2019 arXiv   pre-print
We propose an alternative form of the 3D U-Net, which uses dilated convolutions and deep supervision to incorporate multi-scale information into the model.  ...  In this paper, we investigate variants of the well known 3D U-Net, a type of convolution neural network (CNN) for semantic segmentation tasks.  ...  Several automatic and semi-automatic segmentation approaches have been proposed, which utilize T1-weighted structural MRIs, to segment the hippocampus.  ... 
arXiv:1903.09097v1 fatcat:p5zgl3vmrfgonlvx3h6yueyuqe

Dilated Deeply Supervised Networks for Hippocampus Segmentation in MRI [chapter]

Lukas Folle, Sulaiman Vesal, Nishant Ravikumar, Andreas Maier
2019 Handbook of Experimental Pharmacology  
We propose an alternative form of the 3D U-Net, which uses dilated convolutions and deep supervision to incorporate multi-scale information into the model.  ...  In this paper, we investigate variants of the well known 3D U-Net, a type of convolution neural network (CNN) for semantic segmentation tasks.  ...  Several automatic and semi-automatic segmentation approaches have been proposed, which utilize T1-weighted structural MRIs, to segment the hippocampus.  ... 
doi:10.1007/978-3-658-25326-4_18 fatcat:r36furosvragxcvypc3h66cnpe

Automatic segmentation of the femur and tibia bones from X-ray images based on pure dilated residual U-Net

Weihao Shen, ,School of Artificial Intelligence, Hebei University of Technology, Tianjin 300401, China, Wenbo Xu, Hongyang Zhang, Zexin Sun, Jianxiong Ma, Xinlong Ma, Shoujun Zhou, Shijie Guo, Yuanquan Wang, ,Tianjin Institute of Orthopaedics, Tianjin Hospital, Tianjin University, Tianjin 300211, China, ,Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China (+1 others)
2020 Inverse Problems and Imaging  
In this paper, we propose a new approach based on pure dilated residual U-Net for the segmentation of the femur and tibia bones.  ...  The proposed approach employs dilated convolution completely to increase the receptive field, in this way, we can make full use of the advantages of dilated convolution.  ...  [17] have achieved automatic brain structures segmentation using deep residual dilated U-net.  ... 
doi:10.3934/ipi.2020057 fatcat:lwkyipldrfcmrliqbmiatmh3ga

Semantic Segmentation of Cerebellum in 2D Fetal Ultrasound Brain Images using Convolutional Neural Networks

Vishal Singh, Pradeeba Sridar, Jinman Kim, Ralph Nanan, N. Poornima, Shanmuga Priya, G. Sameera, Sathyabama Chandrasekaran, Ramarathnam Krishnakumar
2021 IEEE Access  
We leverage U-Net as a base model with the integration of residual blocks (Res) and introduce dilation convolution in the last two layers to segment the cerebellum (c) from noisy US images.  ...  We propose ResU-Net-c a semantic segmentation model optimized for fetal cerebellum structure.  ...  segmentation network, where it leverages the strength of both deep residual learning and U-Net architecture.  ... 
doi:10.1109/access.2021.3088946 fatcat:rbxybu4lgjfxbb4po4uano6rg4

Nested Dilation Networks for Brain Tumor Segmentation Based on Magnetic Resonance Imaging

Liansheng Wang, Shuxin Wang, Rongzhen Chen, Xiaobo Qu, Yiping Chen, Shaohui Huang, Changhua Liu
2019 Frontiers in Neuroscience  
Conclusion: Experiments show that the proposed deep learning algorithm outperforms other U-Net transmutation networks for brain tumor segmentation.  ...  To prove the reliability of the network structure, we compare our results with those of the standard U-Net and its transmutation networks.  ...  We developed a new deep learning framework based on U-Net, NDNs, for segmenting brain tumors.  ... 
doi:10.3389/fnins.2019.00285 pmid:31024229 pmcid:PMC6460997 fatcat:rpiwvyjcqja37m4kolrweylopq

AIU-Net: An Efficient Deep Convolutional Neural Network for Brain Tumor Segmentation

Yongchao Jiang, Mingquan Ye, Daobin Huang, Xiaojie Lu, Shianghau Wu
2021 Mathematical Problems in Engineering  
In order to improve the accuracy of brain tumor segmentation, an improved multimodal MRI brain tumor segmentation algorithm based on U-net is proposed in this paper.  ...  Automatic and accurate segmentation of brain tumors plays an important role in the diagnosis and treatment of brain tumors.  ...  U-net is also encoder-decoder structure and has been widely used in medical image segmentation.  ... 
doi:10.1155/2021/7915706 fatcat:dp2rtfjltvaw7f2wap3oetxtaa

Morphological Operation Residual Blocks: Enhancing 3D Morphological Feature Representation in Convolutional Neural Networks for Semantic Segmentation of Medical Images [article]

Chentian Li, Chi Ma, William W. Lu
2021 arXiv   pre-print
Here, we introduced a 3D morphological operation residual block to extract morphological features in end-to-end deep learning models for semantic segmentation.  ...  Several 3D deep learning models with the proposed morphological operation block were built and compared in different medical imaging segmentation tasks.  ...  [11] used a combination of res-net and deep-supervision techniques in the 3D U-net in image segmentation. Then Isensee et al.  ... 
arXiv:2103.04026v1 fatcat:uhvqvvcbfncvpgyfhifbjdc2ma

Residual Convolutional Neural Network for Cardiac Image Segmentation and Heart Disease Diagnosis

Tao Liu, Yun Tian, Shifeng Zhao, Xiaoying Huang, Qingjun Wang
2020 IEEE Access  
Deep learning (DL) has been widely used in biomedical image segmentation and automatic disease diagnosis, leading to state-of-the-art performance.  ...  Moreover, automatic disease diagnosis has been conducted using the segmentation maps.  ...  (ii) U-Net + CLSTM and (iii) U-Net + Bi-CLSTM were used to prove the segmentation method of 2D combined temporal information.  ... 
doi:10.1109/access.2020.2991424 fatcat:rk5x6jenojb3fg5slelxfgpdoa

A Deep-Learning Model with Learnable Group Convolution and Deep Supervision for Brain Tumor Segmentation

Hengxin Liu, Qiang Li, I-Chi Wang, Kim-Hua Tan
2021 Mathematical Problems in Engineering  
The experiment results revealed that the proposed model is superior to 3D U-Net and DMFNet and has better segmentation results for tumor cores than No New-Net and NVDLMED, the winning methods in the BraTS  ...  The segmentation of brain tumors in medical images is a crucial step of clinical treatment.  ...  Models based on U-Net include the 3D U-Net structure used by Sherman [34] , in which residual structures were added between convolutions in the same layer.  ... 
doi:10.1155/2021/6661083 fatcat:h75t2gqg3bdxlh6ytwyaikorwq

Using Convolutional Neural Network with Taguchi Parametric Optimization for Knee Segmentation from X-Ray Images

Young Jae Kim, Seung Ro Lee, Ja-Young Choi, Kwang Gi Kim, Tsutomu Gomi
2021 BioMed Research International  
When the Dilated-Resnet architecture is used with the Adam optimizer and a learning rate of 0.001, dice coefficients of 0.964 and 0.942 are obtained for the femur and tibia for knee segmentation.  ...  Several studies have investigated the use of automatic knee segmentation to assist in the calculation process, but the results are of limited value owing to the complexity of the knee.  ...  All Drop U-Net model shows the highest dice coefficient of 0.988 [12] . In 2018, Kolařík et al. used Dense U-Net, Res-U-Net, and U-Net models for brain image segmentation.  ... 
doi:10.1155/2021/5521009 pmid:34476259 pmcid:PMC8408001 fatcat:j376fqejqbf7rlhj3a7qlcmor4

Multi-Task Deep Supervision on Attention R2U-Net for Brain Tumor Segmentation

Shiqiang Ma, Jijun Tang, Fei Guo
2021 Frontiers in Oncology  
Accurate automatic medical image segmentation technology plays an important role for the diagnosis and treatment of brain tumor.  ...  In order to solve the problems above, we propose a 2D end-to-end model of attention R2U-Net with multi-task deep supervision (MTDS).  ...  improved the stability of the network for a feature extraction of small batches. nnU-Net ( 16 ) used 2D U-Net, 3D U-Net, and cascaded 3D U-Net to adaptively segment inputs of different resolutions.  ... 
doi:10.3389/fonc.2021.704850 pmid:34604039 pmcid:PMC8484917 fatcat:ajjjhte4tfes7clnwxv3zstd4u

Automatic Ultrasound Image Segmentation of Supraclavicular Nerve Using Dilated U-Net Deep Learning Architecture [article]

Mizuki Miyatake, Subhash Nerella, David Simpson, Natalia Pawlowicz, Sarah Stern, Patrick Tighe, Parisa Rashidi
2022 arXiv   pre-print
We developed a model to capture features of nerves by training two deep neural networks with skip connections: two extended U-Net architectures with and without dilated convolutions.  ...  In this paper, we automatically segmented supraclavicular nerves in ultrasound images to assist in injecting peripheral nerve blocks.  ...  We compared models that recognizes target nerves automatically from ultrasound images using two different network architectures; U-Net; dilated U-Net (Dilated convolutions are introduced to U-Net.  ... 
arXiv:2208.05050v1 fatcat:w7jh2b5imrbx5mngcykb4jya6q

Dilated Dense U-Net for Infant Hippocampus Subfield Segmentation

Hancan Zhu, Feng Shi, Li Wang, Sheng-Che Hung, Meng-Hsiang Chen, Shuai Wang, Weili Lin, Dinggang Shen
2019 Frontiers in Neuroinformatics  
3D U-net.  ...  In this paper, we propose a new fully convolutional network (FCN) for infant hippocampal subfield segmentation by embedding the dilated dense network in the U-net, namely DUnet.  ...  To overcome the limitation of U-net structure, we propose a novel network by embedding a dilated dense network in the U-net, namely DUnet.  ... 
doi:10.3389/fninf.2019.00030 pmid:31068797 pmcid:PMC6491864 fatcat:e7cnqfplbjhj3itzbkcwii7fvy

Volumetric Segmentation of Brain Regions from MRI Scans using 3D Convolutional Neural Networks

Farheen Ramzan, Muhammad Usman Ghani Khan, Sajid Iqbal, Tanzila Saba, Amjad Rehman
2020 IEEE Access  
In this work, a network for the segmentation of multiple brain regions has been proposed that is based on 3D convolutional neural networks and utilizes residual learning and dilated convolution operations  ...  Consequently, deep learning has been extensively employed as a tool for precise segmentation of brain regions because of its capability to learn the intricate features of the high-dimensional data.  ...  [34] for the segmentation of 132 brain regions. This network was made of two assemblies of U-Nets that shared knowledge among the neighboring U-Nets.  ... 
doi:10.1109/access.2020.2998901 fatcat:c6rmsdqsnbe23cm42pebc5nhum
« Previous Showing results 1 — 15 out of 2,145 results