scholarly journals COVID-DenseNet: A Deep Learning Architecture to Detect COVID-19 from Chest Radiology Images

2020 ◽  
Author(s):  
Laboni Sarker ◽  
Md. Mohaiminul Islam ◽  
Tanveer Hannan ◽  
Zakaria Ahmed
Keyword(s):  
Deep Learning ◽  
Cross Validation ◽  
Critical Factors ◽  
Effective Screening ◽  
Average Accuracy ◽  
Radiological Images ◽  
Learning Technique ◽  
Chest Radiology ◽  
Fold Cross Validation ◽  
Radiology Image

Coronavirus disease (COVID-19) is a pandemic infectious disease that has a severe risk of spreading rapidly. The quick identification and isolation of the affected persons is the very first step to fight against this virus. In this regard, chest radiology images have been proven to be an effective screening approach of COVID-19 affected patients. A number of AI based solutions have been developed to make the screening of radiological images faster and more accurate in detecting COVID-19. In this study, we are proposing a deep learning based approach using Densenet-121 to effectively detect COVID-19 patients. We incorporated transfer learning technique to leverage the information regarding radiology image learned by another model (CheXNet) which was trained on a huge Radiology dataset of 112,120 images. We trained and tested our model on COVIDx dataset containing 13,800 chest radiography images across 13,725 patients. To check the robustness of our model, we performed both two-class and three-class classifications and achieved 96.49% and 93.71% accuracy respectively. To further validate the consistency of our performance, we performed patient-wise k-fold cross-validation and achieved an average accuracy of 92.91% for three class task. Moreover, we performed an interpretability analysis using Grad-CAM to highlight the most important image regions in making a prediction. Besides ensuring trustworthiness, this explainability can also provide new insights about the critical factors regarding COVID-19. Finally, we developed a website that takes chest radiology images as input and generates probabilities of the presence of COVID-19 or pneumonia and a heatmap highlighting the probable infected regions. Code and models' weights are availabe.

A Novel Method for Gender and Age Detection Based on EEG Brain Signals

2021 ◽  
Vol 18 (5) ◽  
Author(s):  
Haitham Issa ◽  
Sali Issa ◽  
Wahab Shah
Keyword(s):  
Cross Validation ◽  
Image Feature ◽  
Emotional States ◽  
Time Frequency ◽  
Brain Signals ◽  
Average Accuracy ◽  
Gender And Age ◽  
Novel Method ◽  
Fold Cross Validation ◽  
Validation Strategy

This paper presents a new gender and age classification system based on Electroencephalography (EEG) brain signals. First, Continuous Wavelet Transform (CWT) technique is used to get the time-frequency information of only one EEG electrode for eight distinct emotional states instead of the ordinary neutral or relax states. Then, sequential steps are implemented to extract the improved grayscale image feature. For system evaluation, a three-fold-cross validation strategy is applied to construct four different classifiers. The experimental test shows that the proposed extracted feature with Convolutional Neural Network (CNN) classifier improves the performance of both gender and age classification, and achieves an average accuracy of 96.3% and 89% for gender and age classification, respectively. Moreover, the ability to predict human gender and age during the mood of different emotional states is practically approved.

scholarly journals Deep6mA: A deep learning framework for exploring similar patterns in DNA N6-methyladenine sites across different species

2021 ◽  
Vol 17 (2) ◽  
pp. e1008767
Author(s):  
Zutan Li ◽  
Hangjin Jiang ◽  
Lingpeng Kong ◽  
Yuanyuan Chen ◽  
Kun Lang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Prediction Accuracy ◽  
Cross Validation ◽  
Biological Processes ◽  
Biological Functions ◽  
Learning Framework ◽  
Wide Range ◽  
Genomic Scale ◽  
Downstream Gene Expression ◽  
Fold Cross Validation

N6-methyladenine (6mA) is an important DNA modification form associated with a wide range of biological processes. Identifying accurately 6mA sites on a genomic scale is crucial for under-standing of 6mA’s biological functions. However, the existing experimental techniques for detecting 6mA sites are cost-ineffective, which implies the great need of developing new computational methods for this problem. In this paper, we developed, without requiring any prior knowledge of 6mA and manually crafted sequence features, a deep learning framework named Deep6mA to identify DNA 6mA sites, and its performance is superior to other DNA 6mA prediction tools. Specifically, the 5-fold cross-validation on a benchmark dataset of rice gives the sensitivity and specificity of Deep6mA as 92.96% and 95.06%, respectively, and the overall prediction accuracy is 94%. Importantly, we find that the sequences with 6mA sites share similar patterns across different species. The model trained with rice data predicts well the 6mA sites of other three species: Arabidopsis thaliana, Fragaria vesca and Rosa chinensis with a prediction accuracy over 90%. In addition, we find that (1) 6mA tends to occur at GAGG motifs, which means the sequence near the 6mA site may be conservative; (2) 6mA is enriched in the TATA box of the promoter, which may be the main source of its regulating downstream gene expression.

The impact of indexing approaches on Arabic text classification

2016 ◽  
Vol 43 (2) ◽  
pp. 159-173 ◽  
Author(s):  
Amer Al-Badarneh ◽  
Emad Al-Shawakfa ◽  
Basel Bani-Ismail ◽  
Khaleel Al-Rababah ◽  
Safwan Shatnawi
Keyword(s):  
Cross Validation ◽  
Arabic Text ◽  
Word Form ◽  
Bayes Classifier ◽  
Stem Form ◽  
Average Accuracy ◽  
Arabic Text Classification ◽  
The Impact ◽  
And Storage ◽  
Fold Cross Validation

This paper investigates the impact of using different indexing approaches (full-word, stem, and root) when classifying Arabic text. In this study, the naïve Bayes classifier is used to construct the multinomial classification models and is evaluated using stratified k-fold cross-validation ( k ranges from 2 to 10). It is also uses a corpus that consists of 1000 normalized Arabic documents. The results of one experiment in this study show that significant accuracy improvements have occurred when the full-word form is used in most k-folds. Further experiments show that the classifier has achieved the highest accuracy in the eight-fold by using 7/8–1/8 train–test ratio, despite the indexing approach being used. The overall results of this study show that the classifier has achieved the maximum micro-average accuracy 99.36%, either by using the full-word form or the stem form. This proves that the stem is a better choice to use when classifying Arabic text, because it makes the corpus dataset smaller and this will enhance both the processing time and storage utilization, and achieve the highest level of accuracy.

scholarly journals Soil Mapping Based on the Integration of the Similarity-Based Approach and Random Forests

Land ◽  
2020 ◽  
Vol 9 (6) ◽  
pp. 174
Author(s):  
Desheng Wang ◽  
A-Xing Zhu
Keyword(s):  
Random Forests ◽  
Cross Validation ◽  
Soil Mapping ◽  
High Quality ◽  
Integrated Method ◽  
Average Accuracy ◽  
Soil Information ◽  
Fold Cross Validation

Digital soil mapping (DSM) is currently the primary framework for predicting the spatial variation of soil information (soil type or soil properties). Random forests and similarity-based methods have been used widely in DSM. However, the accuracy of the similarity-based approach is limited, and the performance of random forests is affected by the quality of the feature set. The objective of this study was to present a method for soil mapping by integrating the similarity-based approach and the random forests method. The Heshan area (Heilongjiang province, China) was selected as the case study for mapping soil subgroups. The results of the regular validation samples showed that the overall accuracy of the integrated method (71.79%) is higher than that of a similarity-based approach (58.97%) and random forests (66.67%). The results of the 5-fold cross-validation showed that the overall accuracy of the integrated method, similarity-based approach, and random forests range from 55% to 72.73%, 43.48% to 69.57%, and 54.17% to 70.83%, with an average accuracy of 66.61%, 57.39%, and 59.62%, respectively. These results suggest that the proposed method can produce a high-quality covariate set and achieve a better performance than either the random forests or similarity-based approach alone.

scholarly journals Assessing PD-L1 Expression Level via Preoperative MRI in HCC Based on Integrating Deep Learning and Radiomics Features

Diagnostics ◽  
2021 ◽  
Vol 11 (10) ◽  
pp. 1875
Author(s):  
Yuchi Tian ◽  
Temitope Emmanuel Komolafe ◽  
Jian Zheng ◽  
Guofeng Zhou ◽  
Tao Chen ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Deep Learning ◽  
Cross Validation ◽  
Predictive Ability ◽  
Feature Space ◽  
Integrated Model ◽  
Expression Level ◽  
Deep Learning Features ◽  
Expression Status ◽  
Fold Cross Validation

To assess if quantitative integrated deep learning and radiomics features can predict the PD-L1 expression level in preoperative MRI of hepatocellular carcinoma (HCC) patients. The data in this study consist of 103 hepatocellular carcinoma patients who received immunotherapy in a single center. These patients were divided into a high PD-L1 expression group (30 patients) and a low PD-L1 expression group (73 patients). Both radiomics and deep learning features were extracted from their MRI sequence of T2-WI, which were merged into an integrative feature space for machine learning for the prediction of PD-L1 expression. The five-fold cross-validation was adopted to validate the performance of the model, while the AUC was used to assess the predictive ability of the model. Based on the five-fold cross-validation, the integrated model achieved the best prediction performance, with an AUC score of 0.897 ± 0.084, followed by the deep learning-based model with an AUC of 0.852 ± 0.043 then the radiomics-based model with AUC of 0.794 ± 0.035. The feature set integrating radiomics and deep learning features is more effective in predicting PD-L1 expression level than only one feature type. The integrated model can achieve fast and accurate prediction of PD-L1 expression status in preoperative MRI of HCC patients.

scholarly journals Classification of Stages Diabetic Retinopathy Using MobileNetV2 Model

10.29007/h46n ◽  
2022 ◽  
Author(s):  
Hoang Nhut Huynh ◽  
Minh Thanh Do ◽  
Gia Thinh Huynh ◽  
Anh Tu Tran ◽  
Trung Nghia Tran
Keyword(s):  
Diabetic Retinopathy ◽  
Deep Learning ◽  
High Performance ◽  
Vision Loss ◽  
Training Model ◽  
Average Accuracy ◽  
Common Diagnosis ◽  
Learning Technique ◽  
The Common

Diabetic retinopathy (DR) is a complication of diabetes mellitus that causes retinal damage that can lead to vision loss if not detected and treated promptly. The common diagnosis stages of the disease take time, effort, and cost and can be misdiagnosed. In the recent period with the explosion of artificial intelligence, deep learning has become the most popular tool with high performance in many fields, especially in the analysis and classification of medical images. The Convolutional Neural Network (CNN) is more widely used as a deep learning method in medical imaging analysis with highly effective. In this paper, the five-stage image of modern DR (healthy, mild, moderate, severe, and proliferative) can be detected and classified using the deep learning technique. After cross-validation training and testing on the corresponding 5,590-image dataset, a pre-MobileNetV2 training model is proposed in classifying stages of diabetic retinopathy. The average accuracy of the model achieved was 93.89% with the precision of 94.00%, recall 92.00% and f1-score 90.00%. The corresponding thermal image is also given to help experts for evaluating the influence of the retina in each different stage.

scholarly journals CGENet: A Deep Graph Model for COVID-19 Detection Based on Chest CT

Biology ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 33
Author(s):  
Si-Yuan Lu ◽  
Zheng Zhang ◽  
Yu-Dong Zhang ◽  
Shui-Hua Wang
Keyword(s):  
Extreme Learning Machine ◽  
Cross Validation ◽  
Graph Model ◽  
Chest Ct ◽  
Selection Algorithm ◽  
Efficient Tool ◽  
K Nearest Neighbors ◽  
Average Accuracy ◽  
Learning Machine ◽  
Fold Cross Validation

Accurate and timely diagnosis of COVID-19 is indispensable to control its spread. This study proposes a novel explainable COVID-19 diagnosis system called CGENet based on graph embedding and an extreme learning machine for chest CT images. We put forward an optimal backbone selection algorithm to select the best backbone for the CGENet based on transfer learning. Then, we introduced graph theory into the ResNet-18 based on the k-nearest neighbors. Finally, an extreme learning machine was trained as the classifier of the CGENet. The proposed CGENet was evaluated on a large publicly-available COVID-19 dataset and produced an average accuracy of 97.78% based on 5-fold cross-validation. In addition, we utilized the Grad-CAM maps to present a visual explanation of the CGENet based on COVID-19 samples. In all, the proposed CGENet can be an effective and efficient tool to assist COVID-19 diagnosis.

scholarly journals 0616 Validation of a Sleep Headband for Detecting Obstructive Sleep Apnea

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A236-A236
Author(s):  
A Guillot ◽  
T Moutakanni ◽  
M Harris ◽  
P J Arnal ◽  
V Thorey
Keyword(s):  
Obstructive Sleep Apnea ◽  
Deep Learning ◽  
Sleep Apnea ◽  
Cross Validation ◽  
Apnea Hypopnea Index ◽  
Learning Approach ◽  
Specificity And Sensitivity ◽  
Obstructive Sleep ◽  
Fold Cross Validation ◽  
At Home

Abstract Introduction Polysomnography (PSG) is the gold-standard to diagnose obstructive sleep apnea (OSA). OSA severity diagnosis is defined by the apnea-hypopnea index (AHI) defined as the number of apnea and hypopnea events measured per hour of sleep. The Dreem2 headband (DH) is a self-administered, easy to use device that measure EEG, breathing frequency, heart rate and sound at-home. In our study, we assessed the performance of the DH to automatically detects OSA compared to 3 sleep’s experts scoring on PSG. Methods 41 subjects (8 females, 42.6 ± 13.7 y.o.) having a suspicion of OSA performed a night at-home wearing both a PSG and the DH. Each PSG record was scored for apnea and hypopnea events by 3 independent trained sleep experts following AASM guidelines. The deep learning approach DOSED, was trained on the DH signals using the manual apnea scoring. 10-fold cross-validation was used to provide predictions for each of the 41 subjects with the DH. Results We observed an average AHI expert’s scoring of 13.6 ± 10.1 CI[10.5, 16.5] compared to 12.9 ± 10.3 CI[9.6, 15.8] for the DH. Both, the correlation between the 3 scorers (r= 0.88, p < 0.001) and the DH and the scorers (r=0.79, p< 0.001) were significant. The specificity and sensitivity to detect mild OSA (AHI ≤ 5) was 84.4 % and 96.4 % for the DH and 86.5 % and 86.0% for the scorers. Conclusion The results show that the DH using deep learning can detect OSA with an accuracy similar to the sleep experts. The use of DH paves the way for longitudinal monitoring of patients with a suspicion of OSA and its accessibility could lead to better screening of the general population. Support This Study has been supported by Dreem sas.

scholarly journals Hierarchy-Based File Fragment Classification

2020 ◽  
Vol 2 (3) ◽  
pp. 216-232
Author(s):  
Manish Bhatt ◽  
Avdesh Mishra ◽  
Md Wasi Ul Kabir ◽  
S. E. Blake-Gatto ◽  
Rishav Rajendra ◽  
...  
Keyword(s):  
Cross Validation ◽  
Hierarchical Classification ◽  
Future Research ◽  
Support Vector ◽  
Challenging Problem ◽  
Fine Grain ◽  
Average Accuracy ◽  
Vector Machines ◽  
Essential Problem ◽  
Fold Cross Validation

File fragment classification is an essential problem in digital forensics. Although several attempts had been made to solve this challenging problem, a general solution has not been found. In this work, we propose a hierarchical machine-learning-based approach with optimized support vector machines (SVM) as the base classifiers for file fragment classification. This approach consists of more general classifiers at the top level and more specialized fine-grain classifiers at the lower levels of the hierarchy. We also propose a primitive taxonomy for file types that can be used to perform hierarchical classification. We evaluate our model with a dataset of 14 file types, with 1000 fragments measuring 512 bytes from each file type derived from a subset of the publicly available Digital Corpora, the govdocs1 corpus. Our experiment shows comparable results to the present literature, with an average accuracy of 67.78% and an F1-measure of 65% using 10-fold cross-validation. We then improve on the hierarchy and find better results, with an increase in the F1-measure of 1%. Finally, we make our assessment and observations, then conclude the paper by discussing the scope of future research.

scholarly journals Traditional Chinese Medicine (TCM) Diagnosis Model Building Based on Multi-label Classification

2018 ◽  
Vol 232 ◽  
pp. 02026
Author(s):  
Lu Zhou ◽  
Guang-geng Li ◽  
Yu-mei Zhou ◽  
Dan Yin ◽  
Yan Sun ◽  
...  
Keyword(s):  
Cross Validation ◽  
Model Building ◽  
Learning Algorithm ◽  
Training Data ◽  
Average Precision ◽  
Test Dataset ◽  
Average Accuracy ◽  
Good Potential ◽  
Diagnosis Model ◽  
Fold Cross Validation

In the study, we propose a TCM diagnosis model that can be used for multi-label classification and give clear diagnosis, as well as the basis for diagnosis and differentiation when the symptoms correspond to multiple diseases or syndromes. The implementation of the model is divided into three steps. Firstly, choose the machine learning algorithm to train the TCM diagnosis model. The features of the training data are symptoms and the labels are diseases or syndromes. Secondly, give the number α (α>1, α∈Z+), the model will output the diagnoses with the top α highest probability according to the input symptoms as candidate diagnoses. Finally, the rules of differential diagnosis are designed to determine which candidate diagnoses should be reserved, thereby complete the multi-label classification. In our test dataset, by 10-fold cross-validation, the average accuracy of the single label classification was 0.882; the average precision was 0.974; the average recall was 1.000; the average f1 score was 0.967; the average accuracy of the multi-label classification was 0.706; the average micro precision was 0.934; the average micro recall was 0.941 and the average hamming loss was 0.060. Through the test we can know that this model had a good potential for auxiliary decision making in clinical diagnosis and treatment.

Sign in / Sign up

Export Citation Format

Share Document