Subtype-GAN: a deep learning approach for integrative cancer subtyping of multi-omics data

2021 ◽  
Author(s):  
Hai Yang ◽  
Rui Chen ◽  
Dongdong Li ◽  
Zhe Wang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Latent Variables ◽  
Supplementary Information ◽  
Learning Approach ◽  
Data Sets ◽  
Omics Data ◽  
Data Set ◽  
Benchmark Data ◽  
Cancer Pathogenesis

Abstract Motivation The discovery of cancer subtyping can help explore cancer pathogenesis, determine clinical actionability in treatment, and improve patients' survival rates. However, due to the diversity and complexity of multi-omics data, it is still challenging to develop integrated clustering algorithms for tumor molecular subtyping. Results We propose Subtype-GAN, a deep adversarial learning approach based on the multiple-input multiple-output neural network to model the complex omics data accurately. With the latent variables extracted from the neural network, Subtype-GAN uses consensus clustering and the Gaussian Mixture model to identify tumor samples' molecular subtypes. Compared with other state-of-the-art subtyping approaches, Subtype-GAN achieved outstanding performance on the benchmark data sets consisting of ∼4,000 TCGA tumors from 10 types of cancer. We found that on the comparison data set, the clustering scheme of Subtype-GAN is not always similar to that of the deep learning method AE but is identical to that of NEMO, MCCA, VAE, and other excellent approaches. Finally, we applied Subtype-GAN to the BRCA data set and automatically obtained the number of subtypes and the subtype labels of 1031 BRCA tumors. Through the detailed analysis, we found that the identified subtypes are clinically meaningful and show distinct patterns in the feature space, demonstrating the practicality of Subtype-GAN. Availability The source codes, the clustering results of Subtype-GAN across the benchmark data sets are available at https://github.com/haiyang1986/Subtype-GAN. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Mimicry Embedding Facilitates Advanced Neural Network Training for Image-Based Pathogen Detection

mSphere ◽  
2020 ◽  
Vol 5 (5) ◽  
Author(s):  
Artur Yakimovich ◽  
Moona Huttunen ◽  
Jerzy Samolej ◽  
Barbara Clough ◽  
Nagisa Yoshida ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Network Evolution ◽  
Great Promise ◽  
Data Sets ◽  
Imaging Data ◽  
Data Set ◽  
Novel Strategy

ABSTRACT The use of deep neural networks (DNNs) for analysis of complex biomedical images shows great promise but is hampered by a lack of large verified data sets for rapid network evolution. Here, we present a novel strategy, termed “mimicry embedding,” for rapid application of neural network architecture-based analysis of pathogen imaging data sets. Embedding of a novel host-pathogen data set, such that it mimics a verified data set, enables efficient deep learning using high expressive capacity architectures and seamless architecture switching. We applied this strategy across various microbiological phenotypes, from superresolved viruses to in vitro and in vivo parasitic infections. We demonstrate that mimicry embedding enables efficient and accurate analysis of two- and three-dimensional microscopy data sets. The results suggest that transfer learning from pretrained network data may be a powerful general strategy for analysis of heterogeneous pathogen fluorescence imaging data sets. IMPORTANCE In biology, the use of deep neural networks (DNNs) for analysis of pathogen infection is hampered by a lack of large verified data sets needed for rapid network evolution. Artificial neural networks detect handwritten digits with high precision thanks to large data sets, such as MNIST, that allow nearly unlimited training. Here, we developed a novel strategy we call mimicry embedding, which allows artificial intelligence (AI)-based analysis of variable pathogen-host data sets. We show that deep learning can be used to detect and classify single pathogens based on small differences.

scholarly journals Towards Mapping Images to Text Using Deep-Learning Architectures

Mathematics ◽  
2020 ◽  
Vol 8 (9) ◽  
pp. 1606
Author(s):  
Daniela Onita ◽  
Adriana Birlutiu ◽  
Liviu P. Dinu
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Deep Learning ◽  
Image Features ◽  
The Other ◽  
Data Sets ◽  
Network Architectures ◽  
Learning Approaches ◽  
Data Set ◽  
Pixel Value

Images and text represent types of content that are used together for conveying a message. The process of mapping images to text can provide very useful information and can be included in many applications from the medical domain, applications for blind people, social networking, etc. In this paper, we investigate an approach for mapping images to text using a Kernel Ridge Regression model. We considered two types of features: simple RGB pixel-value features and image features extracted with deep-learning approaches. We investigated several neural network architectures for image feature extraction: VGG16, Inception V3, ResNet50, Xception. The experimental evaluation was performed on three data sets from different domains. The texts associated with images represent objective descriptions for two of the three data sets and subjective descriptions for the other data set. The experimental results show that the more complex deep-learning approaches that were used for feature extraction perform better than simple RGB pixel-value approaches. Moreover, the ResNet50 network architecture performs best in comparison to the other three deep network architectures considered for extracting image features. The model error obtained using the ResNet50 network is less by approx. 0.30 than other neural network architectures. We extracted natural language descriptors of images and we made a comparison between original and generated descriptive words. Furthermore, we investigated if there is a difference in performance between the type of text associated with the images: subjective or objective. The proposed model generated more similar descriptions to the original ones for the data set containing objective descriptions whose vocabulary is simpler, bigger and clearer.

scholarly journals Dark blood ischemic LGE segmentation using a deep learning approach

2021 ◽  
Vol 22 (Supplement_2) ◽  
Author(s):  
C Torlasco ◽  
D Papetti ◽  
R Mene ◽  
J Artico ◽  
A Seraphim ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
High Performance ◽  
Clinical Decision Making ◽  
Data Augmentation ◽  
Clinical Decision ◽  
Learning Approach ◽  
Dark Blood ◽  
Data Set ◽  
Automated Method

Abstract Funding Acknowledgements Type of funding sources: None. Introduction The extent of ischemic scar detected by Cardiac Magnetic Resonance (CMR) with late gadolinium enhancement (LGE) is linked with long-term prognosis, but scar quantification is time-consuming. Deep Learning (DL) approaches appear promising in CMR segmentation.  Purpose: To train and apply a deep learning approach to dark blood (DB) CMR-LGE for ischemic scar segmentation, comparing results to 4-Standard Deviation (4-SD) semi-automated method. Methods: We trained and validated a dual neural network infrastructure on a dataset of DB-LGE short-axis stacks, acquired at 1.5T from 33 patients with ischemic scar. The DL architectures were an evolution of the U-Net Convolutional Neural Network (CNN), using data augmentation to increase generalization. The CNNs worked together to identify and segment 1) the myocardium and 2) areas of LGE. The first CNN simultaneously cropped the region of interest (RoI) according to the bounding box of the heart and calculated the area of myocardium. The cropped RoI was then processed by the second CNN, which identified the overall LGE area. The extent of scar was calculated as the ratio of the two areas. For comparison, endo- and epi-cardial borders were manually contoured and scars segmented by a 4-SD technique with a validated software. Results: The two U-Net networks were implemented with two free and open-source software library for machine learning. We performed 5-fold cross-validation over a dataset of 108 and 385 labelled CMR images of the myocardium and scar, respectively. We obtained high performance (> ∼0.85) as measured by the Intersection over Union metric (IoU) on the training sets, in the case of scar segmentation. With regards to heart recognition, the performance was lower (> ∼0.7), although improved (∼ 0.75) by detecting the cardiac area instead of heart boundaries. On the validation set, performances oscillated between 0.8 and 0.85 for scar tissue recognition, and dropped to ∼0.7 for myocardium segmentation. We believe that underrepresented samples and noise might be affecting the overall performances, so that additional data might be beneficial. Figure1: examples of heart segmentation (upper left panel: training; upper right panel: validation) and of scar segmentation (lower left panel: training; lower right panel: validation). Conclusion: Our CNNs show promising results in automatically segmenting LV and quantify ischemic scars on DB-LGE-CMR images. The performances of our method can further improve by expanding the data set used for the training. If implemented in a clinical routine, this process can speed up the CMR analysis process and aid in the clinical decision-making. Abstract Figure.

scholarly journals An Interaction-Based Convolutional Neural Network (ICNN) Toward a Better Understanding of COVID-19 X-ray Images

Algorithms ◽  
2021 ◽  
Vol 14 (11) ◽  
pp. 337
Author(s):  
Shaw-Hwa Lo ◽  
Yiqiao Yin
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Explanatory Power ◽  
Prediction Performance ◽  
Data Sets ◽  
Real World Data ◽  
Data Set ◽  
Model Free

The field of explainable artificial intelligence (XAI) aims to build explainable and interpretable machine learning (or deep learning) methods without sacrificing prediction performance. Convolutional neural networks (CNNs) have been successful in making predictions, especially in image classification. These popular and well-documented successes use extremely deep CNNs such as VGG16, DenseNet121, and Xception. However, these well-known deep learning models use tens of millions of parameters based on a large number of pretrained filters that have been repurposed from previous data sets. Among these identified filters, a large portion contain no information yet remain as input features. Thus far, there is no effective method to omit these noisy features from a data set, and their existence negatively impacts prediction performance. In this paper, a novel interaction-based convolutional neural network (ICNN) is introduced that does not make assumptions about the relevance of local information. Instead, a model-free influence score (I-score) is proposed to directly extract the influential information from images to form important variable modules. This innovative technique replaces all pretrained filters found by trial-and-error with explainable, influential, and predictive variable sets (modules) determined by the I-score. In other words, future researchers need not rely on pretrained filters; the suggested algorithm identifies only the variables or pixels with high I-score values that are extremely predictive and important. The proposed method and algorithm were tested on real-world data set and a state-of-the-art prediction performance of 99.8% was achieved without sacrificing the explanatory power of the model. This proposed design can efficiently screen patients infected by COVID-19 before human diagnosis and can be a benchmark for addressing future XAI problems in large-scale data sets.

A Deep Learning based Arabic Script Recognition System: Benchmark on KHAT

2020 ◽  
Vol 17 (3) ◽  
pp. 299-305 ◽  
Author(s):  
Riaz Ahmad ◽  
Saeeda Naz ◽  
Muhammad Afzal ◽  
Sheikh Rashid ◽  
Marcus Liwicki ◽  
...  
Keyword(s):  
Deep Learning ◽  
Character Recognition ◽  
Data Augmentation ◽  
Short Term Memory ◽  
Recognition System ◽  
Learning Approach ◽  
Arabic Text ◽  
Data Set ◽  
Processing Step ◽  
Handwritten Arabic

This paper presents a deep learning benchmark on a complex dataset known as KFUPM Handwritten Arabic TexT (KHATT). The KHATT data-set consists of complex patterns of handwritten Arabic text-lines. This paper contributes mainly in three aspects i.e., (1) pre-processing, (2) deep learning based approach, and (3) data-augmentation. The pre-processing step includes pruning of white extra spaces plus de-skewing the skewed text-lines. We deploy a deep learning approach based on Multi-Dimensional Long Short-Term Memory (MDLSTM) networks and Connectionist Temporal Classification (CTC). The MDLSTM has the advantage of scanning the Arabic text-lines in all directions (horizontal and vertical) to cover dots, diacritics, strokes and fine inflammation. The data-augmentation with a deep learning approach proves to achieve better and promising improvement in results by gaining 80.02% Character Recognition (CR) over 75.08% as baseline.

Human Activity Recognition using Fourier Transform Inspired Deep Learning Combination Model

2019 ◽  
Vol 9 (1) ◽  
pp. 16-31
Author(s):  
Kyungkoo Jun
Keyword(s):  
Fourier Transform ◽  
Deep Learning ◽  
Short Term Memory ◽  
Window Size ◽  
Sensor Data ◽  
Data Sets ◽  
Data Set ◽  
Proposed Model ◽  
Testing Data ◽  
Labeling Scheme

Background & Objective: This paper proposes a Fourier transform inspired method to classify human activities from time series sensor data. Methods: Our method begins by decomposing 1D input signal into 2D patterns, which is motivated by the Fourier conversion. The decomposition is helped by Long Short-Term Memory (LSTM) which captures the temporal dependency from the signal and then produces encoded sequences. The sequences, once arranged into the 2D array, can represent the fingerprints of the signals. The benefit of such transformation is that we can exploit the recent advances of the deep learning models for the image classification such as Convolutional Neural Network (CNN). Results: The proposed model, as a result, is the combination of LSTM and CNN. We evaluate the model over two data sets. For the first data set, which is more standardized than the other, our model outperforms previous works or at least equal. In the case of the second data set, we devise the schemes to generate training and testing data by changing the parameters of the window size, the sliding size, and the labeling scheme. Conclusion: The evaluation results show that the accuracy is over 95% for some cases. We also analyze the effect of the parameters on the performance.

scholarly journals Investigating the impact of pre-processing techniques and pre-trained word embeddings in detecting Arabic health information on social media

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Yahya Albalawi ◽  
Jim Buckley ◽  
Nikola S. Nikolov
Keyword(s):  
Social Media ◽  
Deep Learning ◽  
Comprehensive Evaluation ◽  
Classification Problem ◽  
Data Sets ◽  
Word Embeddings ◽  
Data Set ◽  
Lower Accuracy ◽  
Health Related ◽  
The Impact

AbstractThis paper presents a comprehensive evaluation of data pre-processing and word embedding techniques in the context of Arabic document classification in the domain of health-related communication on social media. We evaluate 26 text pre-processings applied to Arabic tweets within the process of training a classifier to identify health-related tweets. For this task we use the (traditional) machine learning classifiers KNN, SVM, Multinomial NB and Logistic Regression. Furthermore, we report experimental results with the deep learning architectures BLSTM and CNN for the same text classification problem. Since word embeddings are more typically used as the input layer in deep networks, in the deep learning experiments we evaluate several state-of-the-art pre-trained word embeddings with the same text pre-processing applied. To achieve these goals, we use two data sets: one for both training and testing, and another for testing the generality of our models only. Our results point to the conclusion that only four out of the 26 pre-processings improve the classification accuracy significantly. For the first data set of Arabic tweets, we found that Mazajak CBOW pre-trained word embeddings as the input to a BLSTM deep network led to the most accurate classifier with F1 score of 89.7%. For the second data set, Mazajak Skip-Gram pre-trained word embeddings as the input to BLSTM led to the most accurate model with F1 score of 75.2% and accuracy of 90.7% compared to F1 score of 90.8% achieved by Mazajak CBOW for the same architecture but with lower accuracy of 70.89%. Our results also show that the performance of the best of the traditional classifier we trained is comparable to the deep learning methods on the first dataset, but significantly worse on the second dataset.

A Comparison Study of Mahalanobis-Taguchi System and Neural Network for Multivariate Pattern Recognition

2005 ◽  
Author(s):  
Jungeui Hong ◽  
Elizabeth A. Cudney ◽  
Genichi Taguchi ◽  
Rajesh Jugulum ◽  
Kioumars Paryani ◽  
...  
Keyword(s):  
Neural Network ◽  
Small Data ◽  
Data Sets ◽  
Comparison Study ◽  
Data Set ◽  
Set Size ◽  
Breast Cancer Study ◽  
Discriminant Ability ◽  
Small Data Sets ◽  
Multivariate Pattern

The Mahalanobis-Taguchi System is a diagnosis and predictive method for analyzing patterns in multivariate cases. The goal of this study is to compare the ability of the Mahalanobis-Taguchi System and a neural network to discriminate using small data sets. We examine the discriminant ability as a function of data set size using an application area where reliable data is publicly available. The study uses the Wisconsin Breast Cancer study with nine attributes and one class.

scholarly journals RISC-V Virtual Platform-Based Convolutional Neural Network Accelerator Implemented in SystemC

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1514
Author(s):  
Seung-Ho Lim ◽  
WoonSik William Suh ◽  
Jin-Young Kim ◽  
Sang-Young Cho
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Model ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
System Level ◽  
Neural Network Models ◽  
Data Set ◽  
Embedded Device ◽  
Virtual Platform

The optimization for hardware processor and system for performing deep learning operations such as Convolutional Neural Networks (CNN) in resource limited embedded devices are recent active research area. In order to perform an optimized deep neural network model using the limited computational unit and memory of an embedded device, it is necessary to quickly apply various configurations of hardware modules to various deep neural network models and find the optimal combination. The Electronic System Level (ESL) Simulator based on SystemC is very useful for rapid hardware modeling and verification. In this paper, we designed and implemented a Deep Learning Accelerator (DLA) that performs Deep Neural Network (DNN) operation based on the RISC-V Virtual Platform implemented in SystemC in order to enable rapid and diverse analysis of deep learning operations in an embedded device based on the RISC-V processor, which is a recently emerging embedded processor. The developed RISC-V based DLA prototype can analyze the hardware requirements according to the CNN data set through the configuration of the CNN DLA architecture, and it is possible to run RISC-V compiled software on the platform, can perform a real neural network model like Darknet. We performed the Darknet CNN model on the developed DLA prototype, and confirmed that computational overhead and inference errors can be analyzed with the DLA prototype developed by analyzing the DLA architecture for various data sets.

Sign in / Sign up

Export Citation Format

Share Document