Transfer-to-Transfer Learning Approach for Computer Aided Detection of COVID-19 in Chest Radiographs

The coronavirus disease 2019 (COVID-19) global pandemic has severely impacted lives across the globe. Respiratory disorders in COVID-19 patients are caused by lung opacities similar to viral pneumonia. A Computer-Aided Detection (CAD) system for the detection of COVID-19 using chest radiographs would provide a second opinion for radiologists. For this research, we utilize publicly available datasets that have been marked by radiologists into two-classes (COVID-19 and non-COVID-19). We address the class imbalance problem associated with the training dataset by proposing a novel transfer-to-transfer learning approach, where we break a highly imbalanced training dataset into a group of balanced mini-sets and apply transfer learning between these. We demonstrate the efficacy of the method using well-established deep convolutional neural networks. Our proposed training mechanism is more robust to limited training data and class imbalance. We study the performance of our algorithm(s) based on 10-fold cross validation and two hold-out validation experiments to demonstrate its efficacy. We achieved an overall sensitivity of 0.94 for the hold-out validation experiments containing 2265 and 2139 marked as COVID-19 chest radiographs, respectively. For the 10-fold cross validation experiment, we achieve an overall Area under the Receiver Operating Characteristic curve (AUC) value of 0.996 for COVID-19 detection. This paper serves as a proof-of-concept that an automated detection approach can be developed with a limited set of COVID-19 images, and in areas with scarcity of trained radiologists.

Download Full-text

Towards computer-aided severity assessment via deep neural networks for geographic and opacity extent scoring of SARS-CoV-2 chest X-rays

Scientific Reports ◽

10.1038/s41598-021-88538-4 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

A. Wong ◽

Z. Q. Lin ◽

L. Wang ◽

A. G. Chung ◽

B. Shen ◽

...

Keyword(s):

Neural Networks ◽

Monte Carlo ◽

Lung Disease ◽

Disease Severity ◽

Deep Neural Networks ◽

Cross Validation ◽

X Rays ◽

Computer Aided ◽

Monte Carlo Cross Validation ◽

Validation Experiments

AbstractA critical step in effective care and treatment planning for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the cause for the coronavirus disease 2019 (COVID-19) pandemic, is the assessment of the severity of disease progression. Chest x-rays (CXRs) are often used to assess SARS-CoV-2 severity, with two important assessment metrics being extent of lung involvement and degree of opacity. In this proof-of-concept study, we assess the feasibility of computer-aided scoring of CXRs of SARS-CoV-2 lung disease severity using a deep learning system. Data consisted of 396 CXRs from SARS-CoV-2 positive patient cases. Geographic extent and opacity extent were scored by two board-certified expert chest radiologists (with 20+ years of experience) and a 2nd-year radiology resident. The deep neural networks used in this study, which we name COVID-Net S, are based on a COVID-Net network architecture. 100 versions of the network were independently learned (50 to perform geographic extent scoring and 50 to perform opacity extent scoring) using random subsets of CXRs from the study, and we evaluated the networks using stratified Monte Carlo cross-validation experiments. The COVID-Net S deep neural networks yielded R$$^2$$ 2 of $$0.664 \pm 0.032$$ 0.664 ± 0.032 and $$0.635 \pm 0.044$$ 0.635 ± 0.044 between predicted scores and radiologist scores for geographic extent and opacity extent, respectively, in stratified Monte Carlo cross-validation experiments. The best performing COVID-Net S networks achieved R$$^2$$ 2 of 0.739 and 0.741 between predicted scores and radiologist scores for geographic extent and opacity extent, respectively. The results are promising and suggest that the use of deep neural networks on CXRs could be an effective tool for computer-aided assessment of SARS-CoV-2 lung disease severity, although additional studies are needed before adoption for routine clinical use.

Download Full-text

Evaluation of the feasibility of explainable computer-aided detection of cardiomegaly on chest radiographs using deep learning

Scientific Reports ◽

10.1038/s41598-021-96433-1 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Mu Sook Lee ◽

Yong Soo Kim ◽

Minki Kim ◽

Muhammad Usman ◽

Shi Sub Byon ◽

...

Keyword(s):

Deep Learning ◽

Diagnostic Performance ◽

Absolute Error ◽

Training Dataset ◽

Computer Aided Detection ◽

Test Dataset ◽

Cardiothoracic Ratio ◽

Computer Aided ◽

Chest X Ray ◽

Public Datasets

AbstractWe examined the feasibility of explainable computer-aided detection of cardiomegaly in routine clinical practice using segmentation-based methods. Overall, 793 retrospectively acquired posterior–anterior (PA) chest X-ray images (CXRs) of 793 patients were used to train deep learning (DL) models for lung and heart segmentation. The training dataset included PA CXRs from two public datasets and in-house PA CXRs. Two fully automated segmentation-based methods using state-of-the-art DL models for lung and heart segmentation were developed. The diagnostic performance was assessed and the reliability of the automatic cardiothoracic ratio (CTR) calculation was determined using the mean absolute error and paired t-test. The effects of thoracic pathological conditions on performance were assessed using subgroup analysis. One thousand PA CXRs of 1000 patients (480 men, 520 women; mean age 63 ± 23 years) were included. The CTR values derived from the DL models and diagnostic performance exhibited excellent agreement with reference standards for the whole test dataset. Performance of segmentation-based methods differed based on thoracic conditions. When tested using CXRs with lesions obscuring heart borders, the performance was lower than that for other thoracic pathological findings. Thus, segmentation-based methods using DL could detect cardiomegaly; however, the feasibility of computer-aided detection of cardiomegaly without human intervention was limited.

Download Full-text

Interclass Interference Suppression in Multi-Class Problems

Applied Sciences ◽

10.3390/app11010450 ◽

2021 ◽

Vol 11 (1) ◽

pp. 450

Author(s):

Jinfu Liu ◽

Mingliang Bai ◽

Na Jiang ◽

Ran Cheng ◽

Xianling Li ◽

...

Keyword(s):

Classification Accuracy ◽

Cross Validation ◽

Selection Process ◽

Interference Suppression ◽

Generalization Ability ◽

Suppression Effect ◽

Binary Classifiers ◽

The One ◽

Fold Cross Validation ◽

Validation Experiments

Multi-classifiers are widely applied in many practical problems. But the features that can significantly discriminate a certain class from others are often deleted in the feature selection process of multi-classifiers, which seriously decreases the generalization ability. This paper refers to this phenomenon as interclass interference in multi-class problems and analyzes its reason in detail. Then, this paper summarizes three interclass interference suppression methods including the method based on all-features, one-class classifiers and binary classifiers and compares their effects on interclass interference via the 10-fold cross-validation experiments in 14 UCI datasets. Experiments show that the method based on binary classifiers can suppress the interclass interference efficiently and obtain the best classification accuracy among the three methods. Further experiments were done to compare the suppression effect of two methods based on binary classifiers including the one-versus-one method and one-versus-all method. Results show that the one-versus-one method can obtain a better suppression effect on interclass interference and obtain better classification accuracy. By proposing the concept of interclass inference and studying its suppression methods, this paper significantly improves the generalization ability of multi-classifiers.

Download Full-text

Optimal matrix size of chest radiographs for computer-aided detection on lung nodule or mass with deep learning

European Radiology ◽

10.1007/s00330-020-06892-9 ◽

2020 ◽

Vol 30 (9) ◽

pp. 4943-4951

Author(s):

Young-Gon Kim ◽

Sang Min Lee ◽

Kyung Hee Lee ◽

Ryoungwoo Jang ◽

Joon Beom Seo ◽

...

Keyword(s):

Deep Learning ◽

Lung Nodule ◽

Chest Radiographs ◽

Computer Aided Detection ◽

Matrix Size ◽

Computer Aided

Download Full-text

Sensitivity of Computer-Aided Detection (CAD) Device for Lung Nodule Detection on Chest Radiography: A Real-Life Application

Radiology and Medical Diagnostic Imaging ◽

10.31487/j.rdi.2020.02.05 ◽

2020 ◽

pp. 1-5

Author(s):

Ammar Chaudhry ◽

William H. Moore

Keyword(s):

Sensitivity And Specificity ◽

Chest Radiography ◽

Predictive Value ◽

Lung Nodule ◽

Chest Radiographs ◽

Lung Nodules ◽

Computer Aided Detection ◽

Cad System ◽

Computer Aided ◽

The Mean

Purpose: The radiographic diagnosis of lung nodules is associated with low sensitivity and specificity. Computer-aided detection (CAD) system has been shown to have higher accuracy in the detection of lung nodules. The purpose of this study is to assess the effect on sensitivity and specificity when a CAD system is used to review chest radiographs in real-time setting. Methods: Sixty-three patients, including 24 controls, who had chest radiographs and CT within three months were included in this study. Three radiologists were presented chest radiographs without CAD and were asked to mark all lung nodules. Then the radiologists were allowed to see the CAD region-of-interest (ROI) marks and were asked to agree or disagree with the marks. All marks were correlated with CT studies. Results: The mean sensitivity of the three radiologists without CAD was 16.1%, which showed a statistically significant improvement to 22.5% with CAD. The mean specificity of the three radiologists was 52.5% without CAD and decreased to 48.1% with CAD. There was no significant change in the positive predictive value or negative predictive value. Conclusion: The addition of a CAD system to chest radiography interpretation statistically improves the detection of lung nodules without affecting its specificity. Thus suggesting CAD would improve overall detection of lung nodules.

Download Full-text

The Animal Classification: An Evaluation of Different Transfer Learning Pipeline

Mekatronika ◽

10.15282/mekatronika.v3i1.6680 ◽

2021 ◽

Vol 3 (1) ◽

pp. 27-31

Author(s):

Ken-ji Ee ◽

Ahmad Fakhri Bin Ab. Nasir ◽

Anwar P. P. Abdul Majeed ◽

Mohd Azraai Mohd Razman ◽

Nur Hafieza Ismail

Keyword(s):

Transfer Learning ◽

Classification System ◽

Cross Validation ◽

Support Vector ◽

Svm Classifier ◽

Average Classification Accuracy ◽

Validation Technique ◽

Search Approach ◽

Fold Cross Validation

The animal classification system is a technology to classify the animal class (type) automatically and useful in many applications. There are many types of learning models applied to this technology recently. Nonetheless, it is worth noting that the extraction of the features and the classification of the animal features is non-trivial, particularly in the deep learning approach for a successful animal classification system. The use of Transfer Learning (TL) has been demonstrated to be a powerful tool in the extraction of essential features. However, the employment of such a method towards animal classification applications are somewhat limited. The present study aims to determine a suitable TL-conventional classifier pipeline for animal classification. The VGG16 and VGG19 were used in extracting features and then coupled with either k-Nearest Neighbour (k-NN) or Support Vector Machine (SVM) classifier. Prior to that, a total of 4000 images were gathered consisting of a total of five classes which are cows, goats, buffalos, dogs, and cats. The data was split into the ratio of 80:20 for train and test. The classifiers hyper parameters are tuned by the Grids Search approach that utilises the five-fold cross-validation technique. It was demonstrated from the study that the best TL pipeline identified is the VGG16 along with an optimised SVM, as it was able to yield an average classification accuracy of 0.975. The findings of the present investigation could facilitate animal classification application, i.e. for monitoring animals in wildlife.

Download Full-text

Computer-aided Detection of Lung Cancer on Chest Radiographs: Effect on Observer Performance

Radiology ◽

10.1148/radiol.10092437 ◽

2010 ◽

Vol 257 (2) ◽

pp. 532-540 ◽

Cited By ~ 39

Author(s):

Bartjan de Hoop ◽

Diederik W. De Boo ◽

Hester A. Gietema ◽

Frans van Hoorn ◽

Banafsche Mearadji ◽

...

Keyword(s):

Lung Cancer ◽

Chest Radiographs ◽

Observer Performance ◽

Computer Aided Detection ◽

Computer Aided

Download Full-text

Predict Epitranscriptome Targets and Regulatory Functions of N6-Methyladenosine (m6A) Writers and Erasers

Evolutionary Bioinformatics ◽

10.1177/1176934319871290 ◽

2019 ◽

Vol 15 ◽

pp. 117693431987129 ◽

Cited By ~ 5

Author(s):

Yiyou Song ◽

Qingru Xu ◽

Zhen Wei ◽

Di Zhen ◽

Jionglong Su ◽

...

Keyword(s):

Cross Validation ◽

Target Prediction ◽

Learning Approach ◽

Genomic Features ◽

Machine Learning Approach ◽

Functional Relevance ◽

A Site ◽

Site Identification ◽

Regulatory Functions ◽

Fold Cross Validation

Currently, although many successful bioinformatics efforts have been reported in the epitranscriptomics field for N6-methyladenosine (m6A) site identification, none is focused on the substrate specificity of different m6A-related enzymes, ie, the methyltransferases (writers) and demethylases (erasers). In this work, to untangle the target specificity and the regulatory functions of different RNA m6A writers (METTL3-METT14 and METTL16) and erasers (ALKBH5 and FTO), we extracted 49 genomic features along with the conventional sequence features and used the machine learning approach of random forest to predict their epitranscriptome substrates. Our method achieved reasonable performance on both the writer target prediction (as high as 0.918) and the eraser target prediction (as high as 0.888) in a 5-fold cross-validation, and results of the gene ontology analysis of their preferential targets further revealed the functional relevance of different RNA methylation writers and erasers.

Download Full-text

A Computer-Aided Detection System for Digital Chest Radiographs

Journal of Healthcare Engineering ◽

10.1155/2016/8208923 ◽

2016 ◽

Vol 2016 ◽

pp. 1-9 ◽

Cited By ~ 6

Author(s):

Juan Manuel Carrillo-de-Gea ◽

Ginés García-Mateos ◽

José Luis Fernández-Alemán ◽

José Luis Hernández-Hernández

Keyword(s):

Template Matching ◽

Detection System ◽

Local Binary Patterns ◽

Chest Radiographs ◽

Computer Aided Detection ◽

Success Rates ◽

Novel Approach ◽

Computer Aided ◽

Digital Chest ◽

Areas Of Interest

Computer-aided detection systems aim at the automatic detection of diseases using different medical imaging modalities. In this paper, a novel approach to detecting normality/pathology in digital chest radiographs is proposed. The problem tackled is complicated since it is not focused on particular diseases but anything that differs from what is considered as normality. First, the areas of interest of the chest are found using template matching on the images. Then, a texture descriptor called local binary patterns (LBP) is computed for those areas. After that, LBP histograms are applied in a classifier algorithm, which produces the final normality/pathology decision. Our experimental results show the feasibility of the proposal, with success rates above 87% in the best cases. Moreover, our technique is able to locate the possible areas of pathology in nonnormal radiographs. Strengths and limitations of the proposed approach are described in the Conclusions.

Download Full-text