scholarly journals A Modified U-Net Convolutional Network Featuring a Nearest-neighbor Re-sampling-based Elastic-Transformation for Brain Tissue Characterization and Segmentation

2018 ◽  
Author(s):  
S. M. Kamrul Hasan ◽  
Cristian A. Linte
Keyword(s):  
Brain Tissue ◽  
Tissue Characterization ◽  
Nearest Neighbor ◽  
Convolutional Network

scholarly journals KVGCN: A KNN Searching and VLAD Combined Graph Convolutional Network for Point Cloud Segmentation

2021 ◽  
Vol 13 (5) ◽  
pp. 1003
Author(s):  
Nan Luo ◽  
Hongquan Yu ◽  
Zhenfeng Huo ◽  
Jinhui Liu ◽  
Quan Wang ◽  
...  
Keyword(s):  
Point Cloud ◽  
Nearest Neighbor ◽  
Semantic Segmentation ◽  
K Nearest Neighbor ◽  
Topological Graph ◽  
Convolutional Network ◽  
Cloud Data ◽  
Nearest Neighbor Searching ◽  
Point Cloud Segmentation ◽  
Local Feature Extraction

Semantic segmentation of the sensed point cloud data plays a significant role in scene understanding and reconstruction, robot navigation, etc. This work presents a Graph Convolutional Network integrating K-Nearest Neighbor searching (KNN) and Vector of Locally Aggregated Descriptors (VLAD). KNN searching is utilized to construct the topological graph of each point and its neighbors. Then, we perform convolution on the edges of constructed graph to extract representative local features by multiple Multilayer Perceptions (MLPs). Afterwards, a trainable VLAD layer, NetVLAD, is embedded in the feature encoder to aggregate the local and global contextual features. The designed feature encoder is repeated for multiple times, and the extracted features are concatenated in a jump-connection style to strengthen the distinctiveness of features and thereby improve the segmentation. Experimental results on two datasets show that the proposed work settles the shortcoming of insufficient local feature extraction and promotes the accuracy (mIoU 60.9% and oAcc 87.4% for S3DIS) of semantic segmentation comparing to existing models.

Graph Convolutional Networks for Exercise Motion Classification

2021 ◽  
Vol 65 (1) ◽  
pp. 685-689
Author(s):  
Parian Haghighat ◽  
Aden Prince ◽  
Heejin Jeong
Keyword(s):  
Nearest Neighbor ◽  
Current Model ◽  
Model Performance ◽  
Classification Performance ◽  
Great Promise ◽  
Graph Classification ◽  
Convolutional Network ◽  
Motion Data ◽  
Convolutional Networks ◽  
Personal Fitness

The growth in self-fitness mobile applications has encouraged people to turn to personal fitness, which entails integrating self-tracking applications with exercise motion data to reduce fatigue and mitigate the risk of injury. The advancements in computer vision and motion capture technologies hold great promise to improve exercise classification performance. This study investigates a supervised deep learning model performance, Graph Convolutional Network (GCN) to classify three workouts using the Azure Kinect device’s motion data. The model defines the skeleton as a graph and combines GCN layers, a readout layer, and multi-layer perceptrons to build an end-to-end framework for graph classification. The model achieves an accuracy of 95.86% in classifying 19,442 frames. The current model exchanges feature information between each joint and its 1-nearest neighbor, which impact fades in graph-level classification. Therefore, a future study on improved feature utilization can enhance the model performance in classifying inter-user exercise variation.

Myocardial Tissue Characterization Using Pattern Recognition Procedures on Backscattered Ultrasonic Signals

1986 ◽  
Vol 8 (3) ◽  
pp. 181-195
Author(s):  
R.A.G. Dyer ◽  
S.A. Dyer ◽  
P.K. Bhagat
Keyword(s):  
Pattern Recognition ◽  
Minimum Distance ◽  
Tissue Characterization ◽  
Nearest Neighbor ◽  
Myocardial Tissue ◽  
Ultrasonic Signals ◽  
Pattern Recognition Techniques ◽  
Myocardial Tissue Characterization ◽  
Backscattered Signals

Pattern recognition techniques were applied to backscattered signals obtained in vitro from normal and abnormal canine and human heart samples. Orthogonal transforms, in conjunction with the variance criterion, comprised the feature extractors. The minimum-distance (MD) and nearest-neighbor (NN) rules were used as classifiers. When the MD rule was used, the magnitude of the DFT gave the best performance for both canine and human samples. When the NN rule was used, all the transforms performed comparably. The classification performances were improved for both species when the NN rule was used with feature extractors containing phase information.

Optical imaging for brain tissue characterization using relative fluorescence lifetime imaging

2013 ◽  
Vol 18 (6) ◽  
pp. 060504 ◽  
Author(s):  
Asael Papour ◽  
Zach Taylor ◽  
Adria Sherman ◽  
Desiree Sanchez ◽  
Gregory Lucey ◽  
...  
Keyword(s):  
Optical Imaging ◽  
Brain Tissue ◽  
Fluorescence Lifetime ◽  
Tissue Characterization ◽  
Fluorescence Lifetime Imaging ◽  
Lifetime Imaging

Fetal brain tissue characterization at 1.5 T using STrategically Acquired Gradient Echo (STAGE) imaging

2021 ◽  
Author(s):  
Feifei Qu ◽  
Taotao Sun ◽  
Yongsheng Chen ◽  
Brijesh Kumar Yadav ◽  
Ling Jiang ◽  
...  
Keyword(s):  
Brain Tissue ◽  
Tissue Characterization ◽  
Fetal Brain ◽  
Gradient Echo

scholarly journals Auto-kNN: Brain Tissue Segmentation using Automatically Trained k-Nearest-Neighbor Classification

2013 ◽  
Author(s):  
Henri Vrooman ◽  
Fedde Van der Lijn ◽  
Wiro Niessen
Keyword(s):  
White Matter ◽  
Brain Tissue ◽  
Nearest Neighbor ◽  
White Matter Lesion ◽  
Lesion Detection ◽  
K Nearest Neighbor ◽  
Tissue Segmentation ◽  
Rigid Registration ◽  
Brain Tissue Segmentation ◽  
Skull Stripping

In this paper we applied one of our regularly used processing pipelines for fully automated brain tissue segmentation. Brain tissue was segmented in cerebrospinal fluid (CSF), gray matter (GM) and white matter (WM). Our algorithms for skull stripping, tissue segmentation and white matter lesion (WML) detection were slightly adapted and applied to twelve data sets within the MRBrainS13 brain tissue segmentation challenge. Skull stripping is performed using non-rigid registration of 5 atlas masks. Our tissue segmentation is based on an automatically trained kNN-classifier. Training samples were obtained by non-rigid registration of 5 manually labeled scans followed by a pruning step in feature space to remove any residual erroneously sampled tissue voxels. The kNN-classification incorporates voxel intensities from a T1-weighted scan and a FLAIR scan. The white matter lesion detection is based on an automatically determined threshold on the FLAIR scan. The application of the algorithms on the data from the MRBrainS13 Challenge showed that our pipeline produces acceptable segmentations. Average resulting Dice scores were 77.86 (CSF), 81.22 (GM), 87.27 (WM), 93.78 (total parenchyma), and 96.26 (all intracranial structures). Total processing time was about 2 hours per subject.

Sign in / Sign up

Export Citation Format

Share Document