Filters








3,499 Hits in 5.2 sec

Table of Contents

2021 2021 5th International Conference on Pattern Recognition and Image Analysis (IPRIA)  
SkinXNet: A DoG-based Model for Automatic Detection of Skin Lesion using Deep Learning 19. Automatic Image Annotation using Tag Relations and Graph Convolutional Networks 20.  ...  Fast Drivable Area Detection for Autonomous Driving with Deep Learning 28. Auto-Driving Policies in Highway based on Distributional Deep Reinforcement Learning 29.  ... 
doi:10.1109/ipria53572.2021.9483452 fatcat:drscmcfa5vhnjadd7k2vcb3nma

Semi-supervised Auto-encoder Graph Network for Diabetic Retinopathy Grading

YuJie Li, Zhang Song, SunKyoung Kang, SungTae Jung, Wenpei Kang
2021 IEEE Access  
We propose a Semisupervised Auto-encoder Graph Network (SAGN) for the challenging DR diagnosis to relax this constraint.  ...  Finally, we operate Graph Convolutional Neural Network (GCN) to grade retinal samples from extracted features and their correlations.  ...  RELATED WORK This section discusses recently proposed retinal image classification methods based on supervised learning and then introduces many applications of the semi-supervised framework on medical  ... 
doi:10.1109/access.2021.3119434 fatcat:pf465hyztjflhkglxs7lycmd3m

Hybrid Graph Convolutional Network for Semi-supervised Retinal Image Classification

Guanghua Zhang, Jing Pan, Zhaoxia Zhang, Heng Zhang, Changyuan Xing, Bin Sun, Ming Li
2021 IEEE Access  
This HGCN network designs a modularity-based graph learning module and integrates Convolutional Neural Network (CNN) features into the graph representation by graph convolutional network.  ...  INDEX TERMS Retinal image classification, semi-supervised, graph convolutional network, modularitybased graph learning.  ...  FIGURE 2 . 2 The scheme of Hybrid Graph Convolutional Network (HGCN). There contains three modules of feature extraction, modularity-based graph learning, and hybrid graph convolutional network.  ... 
doi:10.1109/access.2021.3061690 fatcat:mod2mr3kt5a6fn5iwguocplnjq

A Survey on the Recent Advances of Deep Community Detection

Stavros Souravlas, Sofia Anastasiadou, Stefanos Katsavounis
2021 Applied Sciences  
Communities are represented as clusters of an entire network. Most of the community detection techniques are based on graph structures.  ...  In this paper, we present the recent advances of deep learning techniques for community detection.  ...  The Adaptive Graph Encoder (AGE) is another filter-related graph embedding model for community detection. Cui et al. [42] proposed a two-part model for auto-encoder based community detection.  ... 
doi:10.3390/app11167179 fatcat:lzff6bskjrfgfo5ho7dalltke4

A Framework for Medical Data Analysis using Deep Learning based on Conventional Neural Network (CNN) and Variable Auto-Encoder

2019 International journal of recent technology and engineering  
Hybrid AE-CNN (auto encoder based Convolutional neural network). Here the performance of proposed mechanism with respect to baseline methods will be assessed.  ...  Here Auto encoder uses to get the prime features and CNN is there to extract detailed features. Combination of these two mechanisms are more suitable for medical data classification.  ...  In order to substantiate that machine learning based auto encoder and convolution neural network (CNN) [3] [4] have been used in combination.  ... 
doi:10.35940/ijrte.c4038.098319 fatcat:b4a5d72kqjdr3a2tcpasscrx7m

MRI based genomic analysis of glioma using three pathway deep convolutional neural network for IDH classification

2021 Turkish Journal of Electrical Engineering and Computer Sciences  
Our aim is to train a deep convolutional neural network for 6 isocitrate dehydrogenase (IDH) genotyping of glioma by auto-extracting the most discriminative features from magnetic 7 resonance imaging (  ...  The multipath neural network, consisting of one shallow and two deep neural network paths, is used 10 to auto-extract the significant imaging features for successful IDH discrimination into IDH mutant  ...  Our deep neural network-based work proposes multipath convolutional neural 29 network with the capability to auto-discriminate IDH types of glioma.  ... 
doi:10.3906/elk-2104-180 fatcat:gzolynp6vfgu3gtel6sg5bsxae

A Survey on Deep Learning for Neuroimaging-based Brain Disorder Analysis [article]

Li Zhang and Mingliang Wang and Mingxia Liu and Daoqiang Zhang
2020 arXiv   pre-print
This paper reviews the applications of deep learning methods for neuroimaging-based brain disorder analysis.  ...  We first provide a comprehensive overview of deep learning techniques and popular network architectures, by introducing various types of deep neural networks and recent developments.  ...  These models include feed-forward neural networks, stacked auto-encoders, deep belief network, deep Boltzmann machine, generative adversarial networks, convolutional neural networks, graph convolutional  ... 
arXiv:2005.04573v1 fatcat:64ze55onzfemhgpebvsewe3fki

An Efficient Image Based Feature Extraction and Feature Selection Model for Medical Data Clustering Using Deep Neural Networks

Mohammed Zaheer Ahmed, Chitraivel Mahesh
2021 Traitement du signal  
A medical textual learning model based on a convolution neural network is proposed for the aspect of medical textual functional education.  ...  In the framework for risk evaluation, the convolution neural network information retrieval methodology is applied. The deep learning approach is used for medical data representation.  ...  In the framework for risk evaluation, the convolution neural network text analysis methodology is applied. The deep learning approach is used for medical data representation.  ... 
doi:10.18280/ts.380425 fatcat:dccwngfx4nfznjkphwgkjshkhi

A Survey on Deep Learning for Neuroimaging-Based Brain Disorder Analysis

Li Zhang, Mingliang Wang, Mingxia Liu, Daoqiang Zhang
2020 Frontiers in Neuroscience  
This paper reviews the applications of deep learning methods for neuroimaging-based brain disorder analysis.  ...  We first provide a comprehensive overview of deep learning techniques and popular network architectures by introducing various types of deep neural networks and recent developments.  ...  Spatial-based methods defined graph convolution directly on the graph, which operates on spatial close neighbors FIGURE 5 | Architecture of convolutional neural networks.  ... 
doi:10.3389/fnins.2020.00779 pmid:33117114 pmcid:PMC7578242 fatcat:tzdcq3kyyrefvn7vxgdj5lnhju

Weakly Supervised Prostate TMA Classification via Graph Convolutional Networks [article]

Jingwen Wang, Richard J. Chen, Ming Y. Lu, Alexander Baras, Faisal Mahmood
2019 arXiv   pre-print
In this work, we propose a weakly-supervised approach for grade classification in tissue micro-arrays (TMA) using graph convolutional networks (GCNs), in which we model the spatial organization of cells  ...  As node-level features in our graph representation, we learn the morphometry of each cell using a contrastive predictive coding (CPC)-based self-supervised approach.  ...  Graph Convolution Networks We train a CPC encoder on extracted TMA patches of size While CNNs remain a powerful deep learning tool for med- 256 × 256 and a stride of 128.  ... 
arXiv:1910.13328v2 fatcat:cxhdf6ipjzahphg2p66mkj3aqe

ElixirNet: Relation-aware Network Architecture Adaptation for Medical Lesion Detection [article]

Chenhan Jiang, Shaoju Wang, Hang Xu, Xiaodan Liang, Nong Xiao
2020 arXiv   pre-print
Most advances in medical lesion detection network are limited to subtle modification on the conventional detection network designed for natural images.  ...  for medical images to incorporate relation-aware operations among region proposals, and leads to more suitable and efficient classification and localization. 3) Relation transfer module incorporates the  ...  Our method is more accurate than the 3DCE and baseline FPN due to relation-aware architecture adaptation for medical images. The graph structure learned from ALB is in Figure 5 .  ... 
arXiv:2003.08770v1 fatcat:hshaxuev6fbk3fooncmq74umcq

Auto-context Convolutional Neural Network (Auto-Net) for Brain Extraction in Magnetic Resonance Imaging [article]

Seyed Sadegh Mohseni Salehi, Deniz Erdogmus, Ali Gholipour
2017 arXiv   pre-print
With the aim of designing a learning-based, geometry-independent and registration-free brain extraction tool in this study, we present a technique based on an auto-context convolutional neural network  ...  In this architecture three parallel 2D convolutional pathways for three different directions (axial, coronal, and sagittal) implicitly learn 3D image information without the need for computationally expensive  ...  With the aim of designing an accurate, learning-based, geometry-independent and registrationfree brain extraction tool in this study, we present a technique based on an auto-context convolutional neural  ... 
arXiv:1703.02083v2 fatcat:ygwwjqinqzefpn5pnk6dtdl4au

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  ...  We also outline the limitations of existing techniques and discuss potential directions for future research.  ...  Why graph-based deep learning for medical diagnosis and analysis?  ... 
arXiv:2105.13137v1 fatcat:gm7d2ziagba7bj3g34u4t3k43y

Efficient Document Image Classification Using Region-Based Graph Neural Network [article]

Jaya Krishna Mandivarapu, Eric Bunch, Qian You, Glenn Fung
2021 arXiv   pre-print
In the paper we propose an efficient document image classification framework that uses graph convolution neural networks and incorporates textual, visual and layout information of the document.  ...  Recent advancements in large pre-trained computer vision and language models and graph neural networks has lent document image classification many tools.  ...  Convolutional neural networks for doc- ument image classification.  ... 
arXiv:2106.13802v1 fatcat:f4yjygge5vgzjdiyitc2zeynqa

Transfer Learning with Deep Convolutional Neural Network for SAR Target Classification with Limited Labeled Data

Zhongling Huang, Zongxu Pan, Bin Lei
2017 Remote Sensing  
Instead of training a deep network with limited dataset from scratch, a large number of unlabeled SAR scene images are used to train the reconstruction pathway with stacked convolutional auto-encoders  ...  To solve this problem, we propose a transfer learning based method, making knowledge learned from sufficient unlabeled SAR scene images transferrable to labeled SAR target data.  ...  The mechanisms of deep transfer learning for medical images are analyzed in [36] .  ... 
doi:10.3390/rs9090907 fatcat:vsbekc5p5vew5gcjcstoluvcay
« Previous Showing results 1 — 15 out of 3,499 results