484 Hits in 12.6 sec

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation [article]

Özgün Çiçek, Ahmed Abdulkadir, Soeren S. Lienkamp, Thomas Brox, Olaf Ronneberger
2016 arXiv   pre-print
This paper introduces a network for volumetric segmentation that learns from sparsely annotated volumetric images.  ...  The network learns from these sparse annotations and provides a dense 3D segmentation. (2) In a fully-automated setup, we assume that a representative, sparsely annotated training set exists.  ...  Lienkamp acknowledges funding from DFG (Emmy Noether-Programm). We also thank Elitsa Goykovka for the useful annotations and Alena Sammarco for the excellent technical assistance in imaging.  ... 
arXiv:1606.06650v1 fatcat:syngj6glhjeabcntvhu2mwhkgy

Fully Automatic Intervertebral Disc Segmentation Using Multimodal 3D U-Net [article]

Chuanbo Wang, Ye Guo, Wei Chen, Zeyun Yu
2020 arXiv   pre-print
This paper proposes a novel convolutional framework based on 3D U-Net to segment IVDs from multi-modality MRI images.  ...  Furthermore, experiments conducted on 2D and 3D U-Nets with augmented and non-augmented datasets are demonstrated and compared in terms of Dice coefficient and Hausdorff distance.  ...  For the 3D framework, we apply 3D convolutional kernels directly on the volume and generate a volumetric mask using a modified multimodal 3D U-Net.  ... 
arXiv:2009.13583v1 fatcat:hj2hzplc5zb47nlys2qgo76bgu

Whole Heart Segmentation from CT images Using 3D U-Net architecture

Marija Habijan, Hrvoje Leventic, Irena Galic, Danilo Babin
2019 2019 International Conference on Systems, Signals and Image Processing (IWSSIP)  
We propose a convolutional neural network approach for the whole heart segmentation which is based upon the 3D U-Net architecture and incorporates principle component analysis as an additional data augmentation  ...  Evaluation of the proposed approach is performed on 20 3D CT images from MICCAI 2017 Multi-Modality Whole Heart Segmentation Challenge dataset, divided into 15 training and 5 validation images.  ...  The learning process involves the generation of the dense volumetric segmentations while only requiring two-dimensional annotated slices for training.  ... 
doi:10.1109/iwssip.2019.8787253 dblp:conf/iwssip/HabijanLGB19 fatcat:wahk2qibejcx5jntyxvltaqecy

A Novel Brain Image Segmentation Method Using an Improved 3D U-Net Model

Zhuqing Yang, Chenxi Huang
2021 Scientific Programming  
From the evaluation indicators, it can be analyzed that the improved 3D U-Net model used can greatly reduce the amount of data while achieving better segmentation results, and the model has better robustness  ...  Therefore, this study introduces the self-excited compressed dilated convolution (SECDC) module on the basis of the 3D U-Net network and proposes an improved 3D U-Net network model.  ...  [24] proposed a 3D U-Net network structure for learning 3D segmentation from sparsely annotated stereo data. e 3D U-Net model structure is shown in Figure 1 .  ... 
doi:10.1155/2021/4801077 fatcat:l7alvqaawfdgjo3nhzlchcdywa

Video Summarization through Reinforcement Learning with a 3D Spatio-Temporal U-Net [article]

Tianrui Liu, Qingjie Meng, Jun-Jie Huang, Athanasios Vlontzos, Daniel Rueckert, Bernhard Kainz
2021 arXiv   pre-print
A 3D spatio-temporal U-Net is used to efficiently encode spatio-temporal information of the input videos for downstream reinforcement learning (RL).  ...  We investigate if real/inflated 3D spatio-temporal CNN features are better suited to learn representations from videos than commonly used 2D image features.  ...  ACKNOWLEDGMENT We thank the volunteers and sonographers from routine fetal screening at St. Thomas' Hospital London. This work was supported by the Wellcome Trust IEH Award  ... 
arXiv:2106.10528v1 fatcat:6q3wnioqtrdktkfl5w5n3pjthi

Spider U-Net: Incorporating Inter-Slice Connectivity Using LSTM for 3D Blood Vessel Segmentation

Kyeorye Lee, Leonard Sunwoo, Tackeun Kim, Kyong Joon Lee
2021 Applied Sciences  
Automation of 3D BVS using deep supervised learning is being researched, and U-Net-based approaches, which are considered as standard for medical image segmentation, are proposed a lot.  ...  We propose a novel U-Net-based model named Spider U-Net for 3D BVS that considers the connectivity of the blood vessels between the axial slices.  ...  Next, the 3D U-Net family, which extracts volumetric features instantly using a 3D convolutional operation, is commonly adopted [13] [14] [15] [16] .  ... 
doi:10.3390/app11052014 fatcat:hjfnwrx5jzeexjmqj3kj5ucnj4

U-Net-Based Medical Image Segmentation

Xiao-Xia Yin, Le Sun, Yuhan Fu, Ruiliang Lu, Yanchun Zhang, Hangjun Che
2022 Journal of Healthcare Engineering  
Deep learning has been extensively applied to segmentation in medical imaging.  ...  U-Net proposed in 2015 shows the advantages of accurate segmentation of small targets and its scalable network architecture.  ...  strategy could use semiautomatic and completely automatic methods to segment 3D targets from sparse annotations. e structure and data enhancement of this network allow it to learn from a small number  ... 
doi:10.1155/2022/4189781 pmid:35463660 pmcid:PMC9033381 fatcat:juxw7yh2j5f5le3kjl4tkacxju

Modality specific U-Net variants for biomedical image segmentation: A survey [article]

Narinder Singh Punn, Sonali Agarwal
2022 arXiv   pre-print
With the advent of advancements in deep learning approaches, such as deep convolution neural network, residual neural network, adversarial network; U-Net architectures are most widely utilized in biomedical  ...  Finally, the strengths and similarities of these U-Net variants are analysed along with the challenges involved in biomedical image segmentation to uncover promising future research directions in this  ...  Recently, Punn and Agarwal (2020d) proposed a 3D U-Net based framework for volumetric brain tumor segmentation.  ... 
arXiv:2107.04537v4 fatcat:m5oqea5q6vhbhkerjmejder3hu

3D U-Net Improves Automatic Brain Extraction for Isotropic Rat Brain Magnetic Resonance Imaging Data

Li-Ming Hsu, Shuai Wang, Lindsay Walton, Tzu-Wen Winnie Wang, Sung-Ho Lee, Yen-Yu Ian Shih
2021 Frontiers in Neuroscience  
However, such an approach cannot make use of the rich 3D spatial-context information from volumetric MRI data.  ...  In this study, we advanced our previously proposed U-Net architecture by replacing all 2D operations with their 3D counterparts and created a 3D U-Net framework.  ...  S., Brox, T., and Ronneberger, O. (2016). “3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation,” in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, Lecture  ... 
doi:10.3389/fnins.2021.801008 pmid:34975392 pmcid:PMC8716693 fatcat:i4aprltpa5do5f42k52kkwvi34

RAR-U-Net: a Residual Encoder to Attention Decoder by Residual Connections Framework for Spine Segmentation under Noisy Labels [article]

Ziyang Wang, Zhengdong Zhang, Irina Voiculescu
2021 arXiv   pre-print
Finally, an adaptive denoising learning strategy (ADL) is introduced into the training process to avoid too much influence from the noisy labels.  ...  In this paper, we propose a new and efficient method for medical image segmentation under noisy labels. The method operates under a deep learning paradigm, incorporating four novel contributions.  ...  In 2016, Ronneberger proposed a 3D U-Net which carried out volumetric segmentation through extracting sparsely annotated volumetric images [2] .  ... 
arXiv:2009.12873v4 fatcat:hylniojevreerpebninvyjqmsa

Automatic Semicircular Canal Segmentation of CT Volumes Using Improved 3D U-Net with Attention Mechanism

Hongcheng Wu, Juanxiu Liu, Gui Chen, Weixing Liu, Ruqian Hao, Lin Liu, Guangming Ni, Yong Liu, Xiaowen Zhang, Jing Zhang, Thippa Reddy G
2021 Computational Intelligence and Neuroscience  
To solve this problem, we propose a novel 3D convolutional neural network based on 3D U-Net to automatically segment the semicircular canal.  ...  Doctors have to annotate the image in a slice-by-slice manner, which is time-consuming and labor-intensive.  ...  corresponding 3D operations. is network can learn from sparsely annotated volumetric images and achieves good results for Xenopus kidney segmentation.  ... 
doi:10.1155/2021/9654059 pmid:34545284 pmcid:PMC8448990 fatcat:clu23sqjyvg4zgogeese4xs2y4

Medical Image Segmentation with 3D Convolutional Neural Networks: A Survey [article]

S Niyas, S J Pawan, M Anand Kumar, Jeny Rajan
2022 arXiv   pre-print
Here, we present an extensive review of the recently evolved 3D deep learning methods in medical image segmentation.  ...  Furthermore, the research gaps and future directions in 3D medical image segmentation are discussed.  ...  Semi-supervised Learning Çiçek et al.[88] Xenopus kidney dataset [89] 3D U-Net with sparsely annotated volumes.  ... 
arXiv:2108.08467v3 fatcat:s2rzghycjbczpparmrflsdzujq

VoxSegNet: Volumetric CNNs for Semantic Part Segmentation of 3D Shapes [article]

Zongji Wang, Feng Lu
2018 arXiv   pre-print
In this paper, we propose a novel volumetric convolutional neural network, which could extract discriminative features encoding detailed information from voxelized 3D data under a limited resolution.  ...  Voxel is an important format to represent geometric data, which has been widely used for 3D deep learning in shape analysis due to its generalization ability and regular data format.  ...  Different from 2D images which contain dense and smooth signals, 3D volumetric shapes are sparse, making it harder to extract discriminative features using sparse kernels.  ... 
arXiv:1809.00226v1 fatcat:rlxoahgzdvdcbbdmv3j453tp2q

Bottleneck Supervised U-Net for Pixel-wise Liver and Tumor Segmentation [article]

Song Li, Geoffrey Kwok Fai Tso
2019 arXiv   pre-print
supervised (BS) U-Net that contains an encoding U-Net and a segmentation U-Net.  ...  In this paper, we propose a bottleneck supervised (BS) U-Net model for liver and tumor segmentation.  ...  Li et al. (2017) proposed a hybrid densely connected U-Net (H-DenseUNet), which uses a 2D Dense UNet to extract intra-slice features and a 3D counterpart to aggregate volumetric contexts under the spirit  ... 
arXiv:1810.10331v2 fatcat:jrcpd3yuund6hnkvaqzp6lwz2u

Towards dense volumetric pancreas segmentation in CT using 3D fully convolutional networks

Masahiro Oda, Natsuki Shimizu, Hirohisa Oda, Yuichiro Hayashi, Takayuki Kitasaka, Michitaka Fujiwara, Kazunari Misawa, Kensaku Mori, Holger R. Roth, Elsa D. Angelini, Bennett A. Landman
2018 Medical Imaging 2018: Image Processing  
In this work, we describe a custom-build 3D fully convolutional network (FCN) that can process a 3D image including the whole pancreas and produce an automatic segmentation.  ...  We evaluate our methods on a dataset from a clinical trial with gastric cancer patients, including 147 contrast enhanced abdominal CT scans acquired in the portal venous phase.  ...  One such example is the recently proposed 3D U-Net, 5 which applies a 3D FCN with skip connections to sparsely annotated biomedical images.  ... 
doi:10.1117/12.2293499 dblp:conf/miip/RothOSOHKFMM18 fatcat:gzxovm2yb5hdnihxvdqjjkenay
« Previous Showing results 1 — 15 out of 484 results