Journal: European Radiology

Article Title: Evaluation of a novel deep learning–based classifier for perifissural nodules

doi: 10.1007/s00330-020-07509-x

Figure Lengend Snippet: Performance of PFN-CNN for the classification of typical PFNs

Article Snippet: The CNN-based PFN classifier was developed by Optellum Ltd. and was initialized from a lung cancer prediction model trained on around 16,000 NLST nodule images, for the task of distinguishing malignant from benign nodules based on analyzing a cuboidal volume of CT data centered on each nodule.

Techniques:

Journal: European Radiology

Article Title: Evaluation of a novel deep learning–based classifier for perifissural nodules

doi: 10.1007/s00330-020-07509-x

Figure Lengend Snippet: Examples from the test dataset along with scores generated by the PFN-CNN

Article Snippet: The CNN-based PFN classifier was developed by Optellum Ltd. and was initialized from a lung cancer prediction model trained on around 16,000 NLST nodule images, for the task of distinguishing malignant from benign nodules based on analyzing a cuboidal volume of CT data centered on each nodule.

Techniques: Generated

Journal: European Radiology

Article Title: Evaluation of a novel deep learning–based classifier for perifissural nodules

doi: 10.1007/s00330-020-07509-x

Figure Lengend Snippet: Examples from the test dataset along with scores generated by the PFN-CNN

Article Snippet: The CNN-based PFN classifier was developed by Optellum Ltd. and was initialized from a lung cancer prediction model trained on around 16,000 NLST nodule images, for the task of distinguishing malignant from benign nodules based on analyzing a cuboidal volume of CT data centered on each nodule.

Techniques: Generated

Journal: Computers in Biology and Medicine

Article Title: COVID-19 detection in chest X-ray images using deep boosted hybrid learning

doi: 10.1016/j.compbiomed.2021.104816

Figure Lengend Snippet: Performance of the developed COVID-19 detection models on the unseen dataset.

Article Snippet: To identify the significance of exploitation of deep feature engineering, for comparison purposes, we have used a Softmax classifier-based implementation of existing CNN models as well.

Techniques:

Journal: Computers in Biology and Medicine

Article Title: COVID-19 detection in chest X-ray images using deep boosted hybrid learning

doi: 10.1016/j.compbiomed.2021.104816

Figure Lengend Snippet: Performance comparison of hybrid based DHL and Softmax classifier-based implementation of well-established CNN models.

Article Snippet: To identify the significance of exploitation of deep feature engineering, for comparison purposes, we have used a Softmax classifier-based implementation of existing CNN models as well.

Techniques: Comparison

Journal: Computers in Biology and Medicine

Article Title: COVID-19 detection in chest X-ray images using deep boosted hybrid learning

doi: 10.1016/j.compbiomed.2021.104816

Figure Lengend Snippet: ROC curve for the proposed frameworks (DHL, DBHL), the developed and well-established CNN Models. The square bracket values represent the tolerance or error, calculated at a 95% confidence interval .

Article Snippet: To identify the significance of exploitation of deep feature engineering, for comparison purposes, we have used a Softmax classifier-based implementation of existing CNN models as well.

Techniques:

Journal: Frontiers in Physiology

Article Title: qInward variability-based in-silico proarrhythmic risk assessment of drugs using deep learning model

doi: 10.3389/fphys.2022.1080190

Figure Lengend Snippet: Schematic of the proposed algorithm for TdP-risk assessment; (A) , flow chart of the process; (B) , the proposed convolutional neural network (CNN) classifier using in silico feature variability; MCMC, Markov-chain Monte Carlo; H, Hill coefficients; IC50, the half inhibitory concentration; Conv1D, one-dimensional CNN layer; Batch Norm, Batch Normalization; MaxP 1D, one-dimensional max pooling layer; str, strides; ReLU, Rectified Linear Unit activation function.

Article Snippet: Notably, the CNN classifier using qInward variability was the best model to classify the high- and low-risk in the 16-test drugs of the Chantest datasets.

Techniques: In Silico, Concentration Assay, Activation Assay

Journal: Frontiers in Physiology

Article Title: qInward variability-based in-silico proarrhythmic risk assessment of drugs using deep learning model

doi: 10.3389/fphys.2022.1080190

Figure Lengend Snippet: Schematic of 10,000-test algorithm; CNN, convolutional neural network model; AUC, area under the receiver operating curve; LR, likelihood ratio.

Article Snippet: Notably, the CNN classifier using qInward variability was the best model to classify the high- and low-risk in the 16-test drugs of the Chantest datasets.

Techniques:

Journal: Frontiers in Physiology

Article Title: qInward variability-based in-silico proarrhythmic risk assessment of drugs using deep learning model

doi: 10.3389/fphys.2022.1080190

Figure Lengend Snippet: CNN classifier performance for 16 test drugs according to the in silico feature variabilities; performance indexes represent the median, the minimum, and the maximum values as the results of 10,000 times test algorithms; Three asterisks (***) denote excellent performance over 0.9 of the median AUC value, two asterisks (**) for good performance over 0.8 of the median AUC value, and one asterisk (*) for moderate performance over 0.7 of the median AUC value.

Article Snippet: Notably, the CNN classifier using qInward variability was the best model to classify the high- and low-risk in the 16-test drugs of the Chantest datasets.

Techniques: In Silico

Journal: Frontiers in Physiology

Article Title: qInward variability-based in-silico proarrhythmic risk assessment of drugs using deep learning model

doi: 10.3389/fphys.2022.1080190

Figure Lengend Snippet: Distribution of AUCs based on the TdP-risk using qInward variability of 16 test drugs in the Chantest dataset; (A–C) , AUC distribution for the high, intermediate, and low-risk of the CNN classifier for 16 test drugs.

Article Snippet: Notably, the CNN classifier using qInward variability was the best model to classify the high- and low-risk in the 16-test drugs of the Chantest datasets.

Techniques:

Journal: Frontiers in Physiology

Article Title: qInward variability-based in-silico proarrhythmic risk assessment of drugs using deep learning model

doi: 10.3389/fphys.2022.1080190

Figure Lengend Snippet: CNN classifier performance for 16 test drugs according to the in silico feature variabilities of a merged dataset; performance indexes represent the median, the minimum, and the maximum values as the results of 10,000 times test algorithms; Three asterisks (***) denote excellent performance over 0.9 of the median AUC value, two asterisks (**) for good performance over 0.8 of the median AUC value, and one asterisk (*) for moderate performance over 0.7 of the median AUC value.

Article Snippet: Notably, the CNN classifier using qInward variability was the best model to classify the high- and low-risk in the 16-test drugs of the Chantest datasets.

Techniques: In Silico

Journal: Frontiers in Physiology

Article Title: qInward variability-based in-silico proarrhythmic risk assessment of drugs using deep learning model

doi: 10.3389/fphys.2022.1080190

Figure Lengend Snippet: CNN classifier performance for all 28 drugs according to the in silico feature variabilities of a merged dataset; performance indexes represent the median, the minimum, and the maximum values as the results of 10,000 times test algorithms; Three asterisks (***) denote excellent performance over 0.9 of the median AUC value, two asterisks (**) for good performance over 0.8 of the median AUC value, and one asterisk (*) for moderate performance over 0.7 of the median AUC value.

Article Snippet: Notably, the CNN classifier using qInward variability was the best model to classify the high- and low-risk in the 16-test drugs of the Chantest datasets.

Techniques: In Silico

Journal: Frontiers in Physiology

Article Title: qInward variability-based in-silico proarrhythmic risk assessment of drugs using deep learning model

doi: 10.3389/fphys.2022.1080190

Figure Lengend Snippet: Distribution of AUCs based on the TdP-risk using qInward variability merged of three datasets; (A–C) , AUC distribution for the high, intermediate, and low-risk of the CNN classifier for 16 test drugs; (D–F) , AUC distribution for the high, intermediate, and low-risk for the CNN classifier for 28 drugs.

Article Snippet: Notably, the CNN classifier using qInward variability was the best model to classify the high- and low-risk in the 16-test drugs of the Chantest datasets.

Techniques:

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Average Statistical Features for STFT Dimensionally Reduced Adeno Carcinoma and Meso Cancer Cases.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques:

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Scatter plot for STFT based Dimensionality Reduction Method in Meso and Adeno Carcinoma Cancer Classes.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques:

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Normal Probability plot for STFT Dimensionality Reduction Method with PSO Feature Selection in Adeno Carcinoma Cancer Classes.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques: Selection

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Normal probability plot for STFT Dimensionality Reduction Method with PSO Feature Selection in Meso Carcinoma Cancer Classes.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques: Selection

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Histogram for STFT Dimensionality Reduction Method with Harmonic Search Feature Selection in Adeno Carcinoma Cancer Classes.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques: Selection

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Histogram for STFT Dimensionality Reduction Method with Harmonic Search Feature Selection in Meso Carcinoma Cancer Classes.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques: Selection

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Analysis of Friedman Test in Feature Selection Methods on STFT Data.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques: Selection

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Training and Testing MSE Analysis of Classifiers for STFT Dimensionality Reduction Technique without and with PSO and Harmonic Search Feature Selection.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques: Selection

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Training and Testing Parameters of CNN Methodology for Raw Data and STFT Dimensionally reduced inputs.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques:

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Training and Testing Accuracy Analysis of various Classifiers in CNN Method with Raw Data and STFT features.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques:

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Performance Analysis of Classifiers for STFT Dimensionality Reduction Technique without Feature Selection.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques: Selection

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Performance Analysis of Classifiers for STFT Dimensionality Reduction Technique with PSO Feature Selection.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques: Selection

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Performance Analysis of Classifiers for STFT Dimensionality Reduction Technique with Harmonic Search Feature Selection.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques: Selection

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Performance Analysis of Classifiers for STFT Dimensionality Reduction Technique with CNN Method.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques:

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Performance of Classifiers in terms of MCC and Kappa Parameters for Raw and STFT Inputs for CNN Methods.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques:

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Performance of Classifiers in terms of Accuracy, F1 Score and Error Rate Parameters for Raw and STFT Inputs in CNN Methods.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques:

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Computational Complexity of the Classifiers for STFT Dimensionality Reduction Method without and with Feature selection methods and CNN Models.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques: Selection

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Comparison with Existing Works in Adenocarcinoma and Mesothelioma lung cancer classification from microarray gene datasets.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques: Comparison, Microarray, Selection, Gene Expression

Journal: Bioengineering

Article Title: Evaluation and Exploration of Machine Learning and Convolutional Neural Network Classifiers in Detection of Lung Cancer from Microarray Gene—A Paradigm Shift

doi: 10.3390/bioengineering10080933

Figure Lengend Snippet: Comparison of previous works involving lung and other types of cancer classification from microarray gene datasets.

Article Snippet: Softmax Discriminant Classifier with CNN and STFT DR , 91.666 , 93.54 , 96.67 , 95.08197.

Techniques: Comparison, Microarray, Selection