Filters








187 Hits in 6.7 sec

Efficient Liver Segmentation from Computed Tomography Images Using Deep Learning

Mubashir Ahmad, Syed Furqan Qadri, M. Usman Ashraf, Khalid Subhi, Salabat Khan, Syeda Shamaila Zareen, Salman Qadri, Rahim Khan
2022 Computational Intelligence and Neuroscience  
To overcome the difficulties that come across the liver segmentation that are affected by fuzzy boundaries, stacked autoencoder (SAE) is applied to learn the most discriminative features of the liver among  ...  In this paper, we propose a patch-based deep learning method for the segmentation of a liver from CT images using SAE.  ...  Acknowledgments is project was funded by the Deanship of Scientific Research (DSR) at King Abdulaziz University, Jeddah, under Grant no. (D63-611-1442).  ... 
doi:10.1155/2022/2665283 pmid:35634046 pmcid:PMC9132625 fatcat:n4uqij6sf5hklcddv4owx7wjyy

Alzheimer rsquo s disease diagnostics by a 3D deeply supervised adaptable convolutional network

Mohammed Ghazal
2018 Frontiers in Bioscience  
Brain sMRI of CADDementia dataset (a) before and (b) after preprocessing depicted in axial, coronal, and sagittal view, by spatially normalizing and removing skull based on mutual information-based rigid  ...  Note that the image intensity is normalized to (0,1) after removing the skull, and the image looks more bright than before preprocessing.  ...  Comparing to the known diagnostic systems outlines below in Section 2, the proposed system employs a deep 3D Convolutional Neural Network (3D-CNN) pretrained by 3D Convolutional Autoencoder (3D-CAE) to  ... 
doi:10.2741/4606 pmid:28930562 fatcat:rynaau7vrba7zgq4yzhwpu5e6m

Machine learning based hyperspectral image analysis: A survey [article]

Utsav B. Gewali, Sildomar T. Monteiro, Eli Saber
2019 arXiv   pre-print
The image analysis tasks considered are land cover classification, target detection, unmixing, and physical parameter estimation.  ...  We organize the methods by the image analysis task and by the type of machine learning algorithm, and present a two-way mapping between the image analysis tasks and the types of machine learning algorithms  ...  In [262] , features generated by sparse unsupervised convolutional neural network, trained using Enforcing Population and Lifetime Sparsity (EPLS) [263] algorithm, showed better performance for classification  ... 
arXiv:1802.08701v2 fatcat:bfi6qkpx2bf6bowhyloj2duugu

Deep Learning for Health Informatics

Daniele Ravi, Charence Wong, Fani Deligianni, Melissa Berthelot, Javier Andreu-Perez, Benny Lo, Guang-Zhong Yang
2017 IEEE journal of biomedical and health informatics  
Deep learning, a technique with its foundation in artificial neural networks, is emerging in recent years as a powerful tool for machine learning, promising to reshape the future of artificial intelligence  ...  For example, the sparse autoencoder [6] that forces the representation to be sparse is usually used to make the classes more separable.  ...  NNs with many layers as deep neural networks (DNNs), or with directed cycles as recurrent neural networks (RNNs).  ... 
doi:10.1109/jbhi.2016.2636665 pmid:28055930 fatcat:24hfhfasljhehb2phndoyu5rnm

A Survey of Surface Defect Detection of Industrial Products Based on A Small Number of Labeled Data [article]

Qifan Jin
2022 arXiv   pre-print
The surface defect detection method based on visual perception has been widely used in industrial quality inspection.  ...  Because defect data are not easy to obtain and the annotation of a large number of defect data will waste a lot of manpower and material resources.  ...  JING [54] proposed a fabric surface defect classification method based on convolutional neural network.  ... 
arXiv:2203.05733v1 fatcat:7imwu76dqzglvms4fivggd6r3y

Deep Learning for Radio-based Human Sensing: Recent Advances and Future Directions [article]

Isura Nirmal, Abdelwahed Khamis, Mahbub Hassan, Wen Hu, Xiaoqing Zhu
2021 arXiv   pre-print
[87, 91, 92] also demonstrated positive outcomes when using layer-by-layer pretraining with sparse autoencoders, 13 [85] Gait Recognition CW Radar GRU 2 Avg.  ...  [93] combines the merits of convolutional spatial learning of CNNs with the unsupervised pretraining capability of autoencoders to design a so called convolutional autoencoder (CAE) to localize a user  ... 
arXiv:2010.12717v2 fatcat:pb6xt445tneijjohfwxizxr7he

A survey on generative adversarial networks for imbalance problems in computer vision tasks

Vignesh Sampath, Iñaki Maurtua, Juan José Aguilar Martín, Aitor Gutierrez
2021 Journal of Big Data  
In recent years, Generative Adversarial Neural Networks (GANs) have gained immense attention by researchers across a variety of application domains due to their capability to model complex real-world image  ...  Any computer vision application development starts off by acquiring images and data, then preprocessing and pattern recognition steps to perform a task.  ...  ConvNets are used as encoder and decoder in convolutional autoencoders [98] .  ... 
doi:10.1186/s40537-021-00414-0 pmid:33552840 pmcid:PMC7845583 fatcat:g3p6hbjuj5c5vbe23ms4g6ed6q

Deep learning in medical imaging and radiation therapy

Berkman Sahiner, Aria Pezeshk, Lubomir M. Hadjiiski, Xiaosong Wang, Karen Drukker, Kenny H. Cha, Ronald M. Summers, Maryellen L. Giger
2018 Medical Physics (Lancaster)  
We introduce the general principles of DL and convolutional neural networks, survey five major areas of application of DL in medical imaging and radiation therapy, identify common themes, discuss methods  ...  for dataset expansion, and conclude by summarizing lessons learned, remaining challenges, and future directions.  ...  AE, autoencoder; FCN, fully convolutional network; HNN, Early classification-based approaches often utilized off- holistically nested network; LOO, leave-one-out; CV, cross-validation. the-shelf CNN features  ... 
doi:10.1002/mp.13264 pmid:30367497 fatcat:bottst5mvrbkfedbuocbrstcnm

Video Jigsaw: Unsupervised Learning of Spatiotemporal Context for Video Action Recognition [article]

Unaiza Ahsan, Rishi Madhok, Irfan Essa
2018 arXiv   pre-print
single frame from these datasets for unsupervised pretraining of our proposed video jigsaw network.  ...  We use our trained network for transfer learning tasks such as video activity recognition and demonstrate the strength of our approach on two benchmark video action recognition datasets without using a  ...  One way to learn such a representation is to use a reconstruction objective. Autoencoders [20] are neural networks designed to reconstruct the input and produce it as its output.  ... 
arXiv:1808.07507v1 fatcat:pddkk2qnpvc4xm5jf3z5ga2hvi

The MVTec 3D-AD Dataset for Unsupervised 3D Anomaly Detection and Localization [article]

Paul Bergmann, Xin Jin, David Sattlegger, Carsten Steger
2021 arXiv   pre-print
It is inspired by real-world visual inspection scenarios in which a model has to detect various types of defects on manufactured products, even if it is trained only on anomaly-free data.  ...  For all object categories, we present a training and validation set, each of which solely consists of scans of anomaly-free samples.  ...  ImageNet Classification with Deep Convolutional Neural Bergmann, P., Löwe, S., Fauser, M., Sattlegger, D., and Networks. In 25th International Conference on Neural Steger., C. (2019b).  ... 
arXiv:2112.09045v1 fatcat:23d67jcu4rcrrbi4762kekqmdi

Deep Learning-Enabled Technologies for Bioimage Analysis

Fazle Rabbi, Sajjad Rahmani Dabbagh, Pelin Angin, Ali Kemal Yetisen, Savas Tasoglu
2022 Micromachines  
Deep learning (DL) is a subfield of machine learning (ML), which has recently demonstrated its potency to significantly improve the quantification and classification workflows in biomedical and clinical  ...  emerging DL-enabled applications in cell morphology quantification in the fields of embryology, point-of-care ovulation testing, as a predictive tool for fetal heart pregnancy, cancer diagnostics via classification  ...  of convolutional neural networks (CNNs) (1980) [28, 29] , Boltzmann machine (1985) [30] , recurrent neural network (RNN) (1986) [31] , and autoencoders (1987) [32, 33] .  ... 
doi:10.3390/mi13020260 pmid:35208385 pmcid:PMC8880650 fatcat:xbem7lix4nhm7cbaauye46lnye

Continual Learning in Neural Networks [article]

Rahaf Aljundi
2019 arXiv   pre-print
Artificial neural networks have exceeded human-level performance in accomplishing several individual tasks (e.g. voice recognition, object recognition, and video games).  ...  The work described in this thesis has been dedicated to the investigation of continual learning and solutions to mitigate the forgetting phenomena in neural networks.  ...  Preprocessing We start from a robust image representation F (x), namely the activations of the last convolutional layer of AlexNet pretrained on ImageNet.  ... 
arXiv:1910.02718v2 fatcat:7jfwt7uxl5gi3j4goz6w34qkwm

2021 Index IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol. 14

2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  ., +, JSTARS 2021 730-746 Pan-Sharpening Based on Convolutional Neural Network by Using the Loss Function With No-Reference.  ...  ., +, JSTARS 2021 249-257 Pan-Sharpening Based on Convolutional Neural Network by Using the Loss Function With No-Reference.  ... 
doi:10.1109/jstars.2022.3143012 fatcat:dnetkulbyvdyne7zxlblmek2qy

A comprehensive review of artificial intelligence-based approaches for rolling element bearing PHM: shallow and deep learning

Moussa Hamadache, Joon Ha Jung, Jungho Park, Byeng D. Youn
2019 JMST Advances  
A brief description of the different bearing-failure modes is given, then, the paper presents a comprehensive representation of the different health features (indexes, criteria) used for REB fault diagnostics  ...  s [21] classification; methods are classified into (deep) convolutional neural network (CNN) approaches, (deep) recurrent neural network (RNN) approaches, restricted Boltzmann machine (RBM)based deep neural  ...  Each is briefly introduced below. • Fatigue begins as a tiny crack on the bearing surface (rollers or races) due to a material structure change, which is caused by repeated stress in the contact areas.  ... 
doi:10.1007/s42791-019-0016-y fatcat:sb3armogsvdebmwxjgpzfxwgju

Neural Regression, Representational Similarity, Model Zoology & Neural Taskonomy at Scale in Rodent Visual Cortex [article]

Colin Conwell, David Mayo, Boris Katz, Michael A. Buice, George A. Alvarez, Andrei Barbu
2021 bioRxiv   pre-print
Simultaneously, we benchmark a number of models (including vision transformers, MLP-Mixers, normalization free networks and Taskonomy encoders) outside the traditional circuit of convolutional object recognition  ...  resolve previous discrepancies, ultimately demonstrating that modern neural networks can in fact be used to explain activity in the mouse visual cortex to a more reasonable degree than previously suggested  ...  These models include convolutional networks, vision transformers, normalization-free networks and MLP-Mixer models; all models are feed-forward.  ... 
doi:10.1101/2021.06.18.448431 fatcat:aympzz3nx5fjradeqh3ek6umzi
« Previous Showing results 1 — 15 out of 187 results