18,410 Hits in 6.4 sec

Quantitative Structure Activity Relationship for Drug Discovery

Quantitative structure-activity relationship (QSAR), gives useful information for drug design and medicinal chemistry.  ...  A time consuming and expensive process for pharmaceutical industries is drug discovery.  ...  LITERATURE SURVEY The paper "Neural networks in building QSAR models" analyses a portion of the necessary methods being performed for structuring models similar to the quantitative structure-activity relationship  ... 
doi:10.35940/ijitee.i1096.0789s19 fatcat:lfz5a3lwn5c2hjkfoup37k7bie

A renaissance of neural networks in drug discovery

Igor I. Baskin, David Winkler, Igor V. Tetko
2016 Expert Opinion on Drug Discovery  
Neural networks are becoming a very popular method for solving machine learning and 10 artificial intelligence problems.  ...  For the last 25 years, this approach to modeling structure-activity 70 relationships has matured into a well-established scientific field with numerous theoretical approaches and successful practical applications  ...  Analysis of the internal representations developed by neural networks for structures applied to quantitative structure-activity relationship studies of benzodiazepines.  ... 
doi:10.1080/17460441.2016.1201262 pmid:27295548 fatcat:2cbfrf6jbzbolkxkriudetdfm4

U-Net Based Multispectral Image Generation from an RGB Image

Tao Zeng, Changyu Diao, Dongming Lu
2021 IEEE Access  
VARIANT U-NET DEEP NEURAL NETWORK We propose a deep neural network as well as loss function to generate more fine-grained multispectral images.  ...  The third section introduces our variant U-Net deep neural network structure and optimization method.  ...  He is currently a professor with the College of Computer Science and Technology, Zhejiang University, Hangzhou, China.  ... 
doi:10.1109/access.2021.3066472 fatcat:3ajrwpf3n5ewnkzni7o4mdwzle

Review of deep learning for photoacoustic imaging

Changchun Yang, Hengrong Lan, Feng Gao, Fei Gao
2021 Photoacoustics  
This boom originated in 2009, when a new model emerged, that is, the deep artificial neural network, which began to surpass other established mature models on some important benchmarks.  ...  , from image reconstruction to disease diagnosis, (iii) providing some open source materials and other resources for researchers interested in applying deep learning to photoacoustic imaging.  ...  Chuangjian Cai [104] proposed the first deep learning framework, ResU-net, for quantitative PA imaging.  ... 
doi:10.1016/j.pacs.2020.100215 pmid:33425679 pmcid:PMC7779783 fatcat:7nhzn342dvhurkxyvgzpwwuotm

Attenuation correction for brain PET imaging using deep neural network based on Dixon and ZTE MR images

Kuang Gong, Jaewon Yang, Kyungsang Kim, Georges El Fakhri, Youngho Seo, Quanzheng Li
2018 Physics in Medicine and Biology  
To address this issue, we present deep neural network methods to derive the continuous attenuation coefficients for brain PET imaging from MR images.  ...  With only Dixon MR images as the network input, the existing U-net structure was adopted and analysis using forty patient data sets shows it is superior than other Dixon based methods.  ...  Pseudo CT generation using deep neural network The basic module of a convolutional neural network includes a convolution layer and an activation layer.  ... 
doi:10.1088/1361-6560/aac763 pmid:29790857 pmcid:PMC6031313 fatcat:nq4wdyts4vebbei3fslptklypa

Deep learning for photoacoustic imaging: a survey [article]

Changchun Yang, Hengrong Lan, Feng Gao, Fei Gao
2020 arXiv   pre-print
This boom originated in 2009, when a new model emerged, that is, the deep artificial neural network, which began to surpass other established mature models on some important benchmarks.  ...  , from image reconstruction to disease diagnosis, (iii) providing some open source materials and other resources for researchers interested in applying deep learning to photoacoustic imaging.  ...  Li, A deep learning method Sensing 2020, International Society for Optics and Photonics, 2020, p. based on U-Net for quantitative photoacoustic imaging, Photons Plus 112402N.  ... 
arXiv:2008.04221v4 fatcat:rjocswwer5brrg7ibrzke7ps6i

Single Image Depth Estimation With Integration of Parametric Learning and Non-Parametric Sampling

Hyungjoo Jung, Kwanghoon Sohn
2016 Journal of Korea Multimedia Society  
Understanding 3D structure of scenes is of a great interest in various vision-related tasks. In this paper, we present a unified approach for estimating depth from a single monocular image.  ...  Experimental results demonstrate that the proposed method outperforms state-of-the-art methods both qualitatively and quantitatively.  ...  [14] propose a deep convolution neural network, which estimates depth using continuous CRFs and deep CNNs. CRF network captures the relationship between superpixels in an input image.  ... 
doi:10.9717/kmms.2016.19.9.1659 fatcat:idda3quaxjagvoync7wvjunvse

Deep Learning based Dimple Segmentation for Quantitative Fractography [article]

Ashish Sinha, K S Suresh
2020 arXiv   pre-print
extended to account for brittle characteristics as well.  ...  In this work, we try to address the challenging problem of dimple detection and segmentation in Titanium alloys using machine learning methods, especially neural networks.  ...  Our work explores the application of deep learning methods in fractography, an active field of research in material science.  ... 
arXiv:2007.02267v3 fatcat:asri5cb6cvhz5mbeyrlqxiaboa

Application of Deep Learning to Biomedical Informatics

Yanshan Wang
2016 International Journal of Applied Science - Research and Review  
used to learn hierarchical representations of images for segmentation of tibial cartilage in low field knee MRI scans [13]; a unified deep learning framework is developed for feature representation and  ...  Application of Deep Learning to Biomedical Informatics.  ...  © Under License of Creative Commons Attribution 3.0 License Vol. 3 No. 5: 3 2016International Journal of Applied Science -Research and Review as a method for quantitative structure-activity relationships  ... 
doi:10.21767/2349-7238.100048 fatcat:jaq45k6hgfflppoehdumytegpu

LCPR-Net: low-count PET image reconstruction using the domain transform and cycle-consistent generative adversarial networks

Hengzhi Xue, Qiyang Zhang, Sijuan Zou, Weiguang Zhang, Chao Zhou, Changjun Tie, Qian Wan, Yueyang Teng, Yongchang Li, Dong Liang, Xin Liu, Yongfeng Yang (+3 others)
2021 Quantitative Imaging in Medicine and Surgery  
Therefore, we propose a deep learning method called LCPR-Net, which is used for directly reconstructing full-count (FC) PET images from corresponding LC sinogram data.  ...  In this process, we merge a convolutional neural network (CNN) and a residual network for feature extraction and image reconstruction.  ...  Acknowledgments The authors would like to thank the editor and anonymous reviewers for their constructive comments and suggestions.  ... 
doi:10.21037/qims-20-66 pmid:33532274 pmcid:PMC7779905 fatcat:d26gj4qsrbcd3jtcifsuepo3jq

Research on Spatialization of Urban Area Based on Deep Learning

2020 Automation and Machine Learning  
Two different supervised algorithms (Support Vector Machine & Deep Learning) was used for classification.  ...  During Deep learning, two kinds of semantic segmentation network models are selected: FCN (Full Convolution Neural Network) model, and U-Net model to classify source data and analyze the effects of different  ...  SVM is a supervised learning method that looks at data and sorts it into one of the two categories. An SVM outputs a map of the sorted data with the margins between the two as far apart as possible.  ... 
doi:10.23977/autml.2020.020101 fatcat:xxgnqpqyybdbdlfu2talfduopi

Geometric and Topological Inference for Deep Representations of Complex Networks [article]

Baihan Lin
2022 arXiv   pre-print
Global surrogate models that approximate the predictions of a black box model (e.g. an artificial or biological neural net) are usually used to provide valuable theoretical insights for the model interpretability  ...  In order to evaluate how well a surrogate model can account for the representation in another model, we need to develop inference methods for model comparison.  ...  Nikolaus Kriegeskorte, who supervised and assisted the research, and the reviewers for their comments to the manuscript.  ... 
arXiv:2203.05488v1 fatcat:5x7q4azgobc2dhedv36ncse3sa

Deep-learning: investigating deep neural networks hyper-parameters and comparison of performance to shallow methods for modeling bioactivity data

Alexios Koutsoukas, Keith J. Monaghan, Xiaoli Li, Jun Huan
2017 Journal of Cheminformatics  
Applications range from quantitative structure-property relationships (QSPRs) [1-3], quantitative structure-activity relationships (QSARs) [4, 5] to in silico mode-of-action analysis and predictive toxicology  ...  Results: We show that feed-forward deep neural networks are capable of achieving strong classification performance and outperform shallow methods across diverse activity classes when optimized.  ...  Min Shen at National Center for Advancing Translational Sciences for her help in performing research on applying deep learning for cheminformatics.  ... 
doi:10.1186/s13321-017-0226-y pmid:29086090 pmcid:PMC5489441 fatcat:7mdy7aqlbjfi3kc2s6uzn46kqi

Artificial intelligence in musculoskeletal ultrasound imaging

YiRang Shin, Jaemoon Yang, Young Han Lee, Sungjun Kim
2020 Ultrasonography  
This review provides an overview of classical machine learning techniques and modern deep learning approaches for musculoskeletal US, with a focus on the key categories of detection and diagnosis of musculoskeletal  ...  Moreover, we outline challenges and a range of opportunities for AI in musculoskeletal US practice.  ...  Acknowledgments This work was supported by a National Research Foundation (NRF) grant funded by the Korean government, Ministry of Science and ICT (MSIP, 2018R1A2B6009076).  ... 
doi:10.14366/usg.20080 pmid:33242932 pmcid:PMC7758096 fatcat:frgqfa5r5vawze43oe2iip2zvm

Diagnostic Model of Coronary Microvascular Disease Combined with Full Convolution Deep Network with Balanced Cross-entropy Cost Function

Shiwen Pan, Wei Zhang, Wanjun Zhang, Liang Xu, Guohua Fan, Jianping Gong, Bo Zhang, Haibo Gu
2019 IEEE Access  
Furthermore, batch normalization is employed to decrease the gradient vanishing in the training process, so as to reduce the difficulty of training the deep neural network.  ...  exacts the feature and edge information, therefore the complex background disturbance is suppressed convincingly, and the vessel segmentation precision is improved effectively, the segmentation precision for  ...  TABLE 1 . 1 Time for training the deep neural networks. TABLE 2 . 2 Quantitative result. VOLUME 7, 2019  ... 
doi:10.1109/access.2019.2958825 fatcat:hoeiyvujwvbthpjzikqnupxi5m
« Previous Showing results 1 — 15 out of 18,410 results