3,855 Hits in 4.5 sec

Graph Convolutional Networks for Multi-modality Medical Imaging: Methods, Architectures, and Clinical Applications [article]

Kexin Ding, Mu Zhou, Zichen Wang, Qiao Liu, Corey W. Arnold, Shaoting Zhang, Dimitri N. Metaxas
2022 arXiv   pre-print
The development of graph convolutional networks (GCNs) has created the opportunity to address this information complexity via graph-driven architectures, since GCNs can perform feature aggregation, interaction  ...  We discuss the fast-growing use of graph network architectures in medical image analysis to improve disease diagnosis and patient outcomes in clinical practice.  ...  developed a group quadratic graph convolutional network for breast tissue and grade classification on pixel-based graph representation.  ... 
arXiv:2202.08916v3 fatcat:zskcqvgjpnb6vdklmyy5rozswq

A Graphical Approach For Brain Haemorrhage Segmentation [article]

Dr. Ninad Mehendale, Pragya Gupta, Nishant Rajadhyaksha, Ansh Dagha, Mihir Hundiwala, Aditi Paretkar, Sakshi Chavan, Tanmay Mishra
2022 arXiv   pre-print
In this paper, we propose a novel implementation of an architecture consisting of traditional Convolutional Neural Networks(CNN) along with Graph Neural Networks(GNN) to produce a holistic model for the  ...  task of brain haemorrhage segmentation.GNNs work on the principle of neighbourhood aggregation thus providing a reliable estimate of global structures present in images.  ...  A = (A + Υ • diag(A)) (8) GCN Layer The general idea of GCN is to apply convolution over a graph. Convolution on a graph is defined on its neighbouring nodes.  ... 
arXiv:2202.06876v1 fatcat:ydqrth4yqbexpmmxgh3rss44rm

3D Randomized Connection Network With Graph-Based Label Inference

Siqi Bao, Pei Wang, Tony C. W. Mok, Albert C. S. Chung
2018 IEEE Transactions on Image Processing  
In this paper, a novel 3D deep learning network is proposed for brain MR image segmentation with randomized connection, which can decrease the dependency between layers and increase the network capacity  ...  The convolutional LSTM and 3D convolution are employed as network units to capture the long-term and short-term 3D properties respectively.  ...  As such, it is necessary to design effective graph-based inference method for 3D brain image segmentation.  ... 
doi:10.1109/tip.2018.2829263 pmid:29993687 fatcat:ibrbql5imzdgjhxeziusenw72e

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future

David Ahmedt-Aristizabal, Mohammad Ali Armin, Simon Denman, Clinton Fookes, Lars Petersson
2021 Sensors  
As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interacting nodes connected by edges whose weights can be  ...  In this survey, we thoroughly review the different types of graph architectures and their applications in healthcare.  ...  • Isomorphism graph-based model [16] . • Synergic GCN [37, 38] . • Simple graph convolution network [39, 40] .  ... 
doi:10.3390/s21144758 fatcat:jytyt4u2pjgvhnhcto3vcvd3a4

MRI Brain Abnormality Detection Using Conventional Neural Network (CNN) [chapter]

Jeevitha R, Selvaraj D
2021 Advances in Parallel Computing  
In this paper, MRI brain tumor detection is performed from a brain images using Fuzzy C-means(FCM) algorithm and sebsequently Convolutional Neural Network(CNN) algorithm is employed.  ...  Brain tumours has huge heterogeneity and there is always a familiarity between normal and abnormal tissues and hence the extraction of tumour portions from normal images becomes persistent.  ...  The below graphs are plotted based on the values calculated from the feature formulas.  ... 
doi:10.3233/apc210080 fatcat:2uw5lymrbvcdnlfzeyhje6ugd4

Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future [article]

David Ahmedt-Aristizabal, Mohammad Ali Armin, Simon Denman, Clinton Fookes, Lars Petersson
2021 arXiv   pre-print
As such, graph neural networks have attracted significant attention by exploiting implicit information that resides in a biological system, with interactive nodes connected by edges whose weights can be  ...  In this survey, we thoroughly review the different types of graph architectures and their applications in healthcare.  ...  convolutional network [45] . • Graph domain adaptation [28] . • Isomorphism graph-based model [22] , [46] . • Synergic GCN [47] , [48] . • Simple graph convolution network [49] - [51] . • Graph-based  ... 
arXiv:2105.13137v1 fatcat:gm7d2ziagba7bj3g34u4t3k43y

3D Segmentation of Brain Tumor Imaging

M. Sumithra, P. Madhumitha, S. Madhumitha, D. Malini, B. Poorni Vinayaa
2020 International Journal of Advanced engineering Management and Science  
In this project, we have proposed a system to detect, segment, and classify the tumors present in the brain.  ...  A brain tumor is a collection of anomalous cells that grow in or around the brain. Brain tumors affect the humans badly, it can disrupt proper brain function and be life-threatening.  ...  LITERATURE SURVEY Brain Tumor Segmentation Using Convolutional Neural Network In MRI Brain tumor segmentation methodology is based on Convolutional Neural Networks (CNN), by exploring into small 3x3  ... 
doi:10.22161/ijaems.66.5 fatcat:l54ukkwa4vh3vmftntpeat4neu

A Joint Graph and Image Convolution Network for Automatic Brain Tumor Segmentation [article]

Camillo Saueressig, Adam Berkley, Reshma Munbodh, Ritambhara Singh
2021 arXiv   pre-print
We present a joint graph convolution-image convolution neural network as our submission to the Brain Tumor Segmentation (BraTS) 2021 challenge.  ...  We model each brain as a graph composed of distinct image regions, which is initially segmented by a graph neural network (GNN).  ...  Our submission to the BraTS 2021 challenge is a joint graph neural network (GNN) -convolutional neural network (CNN) model (summarized in Figure 1 ).  ... 
arXiv:2109.05580v1 fatcat:3526q2s7rbdmlkazu4i4w4mmmu

DMCNN: A Deep Multiscale Convolutional Neural Network Model for Medical Image Segmentation

Lin Teng, Hang Li, Shahid Karim
2019 Journal of Healthcare Engineering  
Therefore, we propose a novelty model for medical image segmentation based on deep multiscale convolutional neural network (CNN) in this article.  ...  Medical image segmentation is one of the hot issues in the related area of image processing. Precise segmentation for medical images is a vital guarantee for follow-up treatment.  ...  To solve the problem of image segmentation, many researchers have come up with many approaches based on the fully convolutional network (FCN) model to remedy limitations of image segmentation.  ... 
doi:10.1155/2019/8597606 pmid:31949890 pmcid:PMC6948302 fatcat:awee42wswbey7gbdj7kvaptkzi

Front Matter: Volume 12032

Ivana Išgum, Olivier Colliot
2022 Medical Imaging 2022: Image Processing  
.  The last two digits indicate publication order within the volume using a Base 36 numbering system employing both numerals and letters. These two-number sets start with 00,  ...  and one-shot learning [12032-14] 0H Evaluating the impact of MR image harmonization on thalamus deep network segmentation [12032-15] 0I Evaluating the impact of MR image contrast on whole brain segmentation  ...  -103] 2Z Automated fractured femur segmentation using CNN [12032-104] 30 BDG- Net: boundary distribution guided network for accurate polyp segmentation 36 Deep learning-based breast tissue segmentation  ... 
doi:10.1117/12.2638192 fatcat:ikfgnjefaba2tpiamxoftyi6sa

Brain Tumor Segmentation in MRI Images using Convolution Neural Networks

2019 International journal of recent technology and engineering  
The proposed algorithm makes use of deep learning concepts for automatic segmentation of the tumor from the MRI brain images.  ...  Brain tumor (BT) is one of the problems that is increasing at a rapid rate and its early detection is important in increasing the survival rate of humans.  ...  Keywords: Brain Tumor, Segmentation, Data Augmentation, Convolution Neural Networks, Deep Learning I. INTRODUCTION A mass of cells which grow without any control results in a brain tumor.  ... 
doi:10.35940/ijrte.b3817.118419 fatcat:esb4xzi4szaytdv7yzsxs3arpy

Segmentation of brain tumor on magnetic resonance imaging using a convolutional architecture [article]

Miriam Zulema Jacobo, Jose Mejia
2020 arXiv   pre-print
MRI scans provides detailed images of the body being one of the most common tests to diagnose brain tumors.  ...  Here we consider the problem brain tumor segmentation using a Deep learning architecture for use in tumor segmentation.  ...  There are several works that study brain tumor segmentation, for example in [2] an automatic method of segmentation of brain tumors based on deep neural networks, two types of architectures are described  ... 
arXiv:2003.07934v1 fatcat:hutqagnv3zdi5dryywdyyy77lu

Residual Block Based Nested U-Type Architecture for Multi-Modal Brain Tumor Image Segmentation

Sirui Chen, Shengjie Zhao, Quan Lan
2022 Frontiers in Neuroscience  
Based on this, Dense-ResUNet, a multi-modal MRI image segmentation model for brain tumors is created.  ...  In this article, convolutional neural networks (CNN) is used as a tool to improve the efficiency and effectiveness of segmentation.  ...  Based on this modular design, our model can train the network by adding a small number of convolutional layers to extract good medical image features.  ... 
doi:10.3389/fnins.2022.832824 pmid:35356052 pmcid:PMC8959850 fatcat:wcgz6kxgmfa6rkwozu5oimdr3u

3D CNN based Alzheimer's diseases classification using segmented Grey matter extracted from whole-brain MRI

Bijen Khagi, Goo-Rak Kwon
2021 JOIV: International Journal on Informatics Visualization  
This image file is then fed into 3D convolutional neural network (CNN) with necessary pre-processing so that it can train the network, to produce a classifying model.  ...  Using the whole brain MRI as the feature is an on-going approach among machine learning researchers, however, we are interested only in grey matter content.  ...  The goal of this paper is to prove that the tissue segmented MRI can be effective than a normal MRI with diverse pixel value for CNN-based.  ... 
doi:10.30630/joiv.5.2.572 fatcat:eu3wqi2c2fhsvmd6slqtbpusgy

Registration of Histopathogy Images Using Structural Information From Fine Grained Feature Maps [article]

Dwarikanath Mahapatra
2020 arXiv   pre-print
We propose a novel approach of combining segmentation information in a registration framework using self supervised segmentation feature maps extracted using a pre-trained segmentation network followed  ...  segmentation maps are unavailable.  ...  Table 1 summarizes the performance of SR−N et (our prposed Segmentation based Registration NETwork) and the top 2 methods on different tissue types.  ... 
arXiv:2007.02078v1 fatcat:3tpxzwvm5bcmplk5vvetirgad4
« Previous Showing results 1 — 15 out of 3,855 results