201
|
Roy S, Tyagi M, Bansal V, Jain V. SVD-CLAHE boosting and balanced loss function for Covid-19 detection from an imbalanced Chest X-Ray dataset. Comput Biol Med 2022; 150:106092. [PMID: 36208598 PMCID: PMC9514969 DOI: 10.1016/j.compbiomed.2022.106092] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2022] [Revised: 08/15/2022] [Accepted: 09/03/2022] [Indexed: 11/23/2022]
Abstract
Covid-19 disease has had a disastrous effect on the health of the global population, for the last two years. Automatic early detection of Covid-19 disease from Chest X-Ray (CXR) images is a very crucial step for human survival against Covid-19. In this paper, we propose a novel data-augmentation technique, called SVD-CLAHE Boosting and a novel loss function Balanced Weighted Categorical Cross Entropy (BWCCE), in order to detect Covid 19 disease efficiently from a highly class-imbalanced Chest X-Ray image dataset. Our proposed SVD-CLAHE Boosting method is comprised of both oversampling and under-sampling methods. First, a novel Singular Value Decomposition (SVD) based contrast enhancement and Contrast Limited Adaptive Histogram Equalization (CLAHE) methods are employed for oversampling the data in minor classes. Simultaneously, a Random Under Sampling (RUS) method is incorporated in major classes, so that the number of images per class will be more balanced. Thereafter, Balanced Weighted Categorical Cross Entropy (BWCCE) loss function is proposed in order to further reduce small class imbalance after SVD-CLAHE Boosting. Experimental results reveal that ResNet-50 model on the augmented dataset (by SVD-CLAHE Boosting), along with BWCCE loss function, achieved 95% F1 score, 94% accuracy, 95% recall, 96% precision and 96% AUC, which is far better than the results by other conventional Convolutional Neural Network (CNN) models like InceptionV3, DenseNet-121, Xception etc. as well as other existing models like Covid-Lite and Covid-Net. Hence, our proposed framework outperforms other existing methods for Covid-19 detection. Furthermore, the same experiment is conducted on VGG-19 model in order to check the validity of our proposed framework. Both ResNet-50 and VGG-19 model are pre-trained on the ImageNet dataset. We publicly shared our proposed augmented dataset on Kaggle website (https://www.kaggle.com/tr1gg3rtrash/balanced-augmented-covid-cxr-dataset), so that any research community can widely utilize this dataset. Our code is available on GitHub website online (https://github.com/MrinalTyagi/SVD-CLAHE-and-BWCCE).
Collapse
Affiliation(s)
- Santanu Roy
- School of Engineering and Technology, Christ (Deemed to be University), Bangalore 560074, India.
| | - Mrinal Tyagi
- Bharati Vidyapeeth's College of Engineering, New Delhi 110063, India.
| | - Vibhuti Bansal
- Bharati Vidyapeeth's College of Engineering, New Delhi 110063, India.
| | - Vikas Jain
- School of Computer Science Engineering and Technology, Bennett University, Greater Noida, UP 201310, India.
| |
Collapse
|
202
|
Lian L, Luo X, Pan C, Huang J, Hong W, Xu Z. Lung image segmentation based on DRD U-Net and combined WGAN with Deep Neural Network. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 226:107097. [PMID: 36088814 PMCID: PMC9423883 DOI: 10.1016/j.cmpb.2022.107097] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/12/2022] [Revised: 08/13/2022] [Accepted: 08/26/2022] [Indexed: 06/15/2023]
Abstract
PURPOSE COVID-19 is a hot issue right now, and it's causing a huge number of infections in people, posing a grave threat to human life. Deep learning-based image diagnostic technology can effectively enhance the deficiencies of the current main detection method. This paper proposes a multi-classification model diagnosis based on segmentation and classification multi-task. METHOD In the segmentation task, the end-to-end DRD U-Net model is used to segment the lung lesions to improve the ability of feature reuse and target segmentation. In the classification task, the model combined with WGAN and Deep Neural Network classifier is used to effectively solve the problem of multi-classification of COVID-19 images with small samples, to achieve the goal of effectively distinguishing COVID-19 patients, other pneumonia patients, and normal subjects. RESULTS Experiments are carried out on common X-ray image and CT image data sets. The results display that in the segmentation task, the model is optimal in the key indicators of DSC and HD, and the error is increased by 0.33% and reduced by 3.57 mm compared with the original network U-Net. In the classification task, compared with SMOTE oversampling method, accuracy increased from 65.32% to 73.84%, F-measure increased from 67.65% to 74.65%, G-mean increased from 66.52% to 74.37%. At the same time, compared with other classical multi-task models, the results also have some advantages. CONCLUSION This study provides new possibilities for COVID-19 image diagnosis methods, improves the accuracy of diagnosis, and hopes to provide substantial help for COVID-19 diagnosis.
Collapse
Affiliation(s)
- Luoyu Lian
- Department of Thoracic Surgery, Quanzhou First Hospital Affiliated to Fujian Medical University, 248-252 East Street, Licheng District, Quanzhou, Fujian 362000, China.
| | - Xin Luo
- Department of Cardiac and Thoracic Surgery, Longyan First Affiliated Hospital of Fujian Medical University, Longyan, Fujian 364000, China
| | - Canyu Pan
- Department of Medical Imaging, Quanzhou First Hospital Affiliated to Fujian Medical University, Quanzhou, Fujian 362000, China
| | - Jinlong Huang
- Department of Thoracic Surgery, Quanzhou First Hospital Affiliated to Fujian Medical University, 248-252 East Street, Licheng District, Quanzhou, Fujian 362000, China
| | - Wenshan Hong
- Department of Thoracic Surgery, Quanzhou First Hospital Affiliated to Fujian Medical University, 248-252 East Street, Licheng District, Quanzhou, Fujian 362000, China
| | - Zhendong Xu
- Department of Thoracic Surgery, Quanzhou First Hospital Affiliated to Fujian Medical University, 248-252 East Street, Licheng District, Quanzhou, Fujian 362000, China.
| |
Collapse
|
203
|
Xiao B, Yang Z, Qiu X, Xiao J, Wang G, Zeng W, Li W, Nian Y, Chen W. PAM-DenseNet: A Deep Convolutional Neural Network for Computer-Aided COVID-19 Diagnosis. IEEE TRANSACTIONS ON CYBERNETICS 2022; 52:12163-12174. [PMID: 34428169 PMCID: PMC9647723 DOI: 10.1109/tcyb.2020.3042837] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/18/2020] [Revised: 11/14/2020] [Accepted: 12/02/2020] [Indexed: 05/07/2023]
Abstract
Currently, several convolutional neural network (CNN)-based methods have been proposed for computer-aided COVID-19 diagnosis based on lung computed tomography (CT) scans. However, the lesions of pneumonia in CT scans have wide variations in appearances, sizes, and locations in the lung regions, and the manifestations of COVID-19 in CT scans are also similar to other types of viral pneumonia, which hinders the further improvement of CNN-based methods. Delineating infection regions manually is a solution to this issue, while excessive workload of physicians during the epidemic makes it difficult for manual delineation. In this article, we propose a CNN called dense connectivity network with parallel attention module (PAM-DenseNet), which can perform well on coarse labels without manually delineated infection regions. The parallel attention module automatically learns to strengthen informative features from both channelwise and spatialwise simultaneously, which can make the network pay more attention to the infection regions without any manual delineation. The dense connectivity structure performs feature maps reuse by introducing direct connections from previous layers to all subsequent layers, which can extract representative features from fewer CT slices. The proposed network is first trained on 3530 lung CT slices selected from 382 COVID-19 lung CT scans, 372 lung CT scans infected by other pneumonia, and 200 normal lung CT scans to obtain a pretrained model for slicewise prediction. We then apply this pretrained model to a CT scans dataset containing 94 COVID-19 CT scans, 93 other pneumonia CT scans, and 93 normal lung scans, and achieve patientwise prediction through a voting mechanism. The experimental results show that the proposed network achieves promising results with an accuracy of 94.29%, a precision of 93.75%, a sensitivity of 95.74%, and a specificity of 96.77%, which is comparable to the methods that are based on manually delineated infection regions.
Collapse
Affiliation(s)
- Bin Xiao
- School of Computer Science and TechnologyChongqing University of Posts and TelecommunicationsChongqing400065China
| | - Zeyu Yang
- School of Computer Science and TechnologyChongqing University of Posts and TelecommunicationsChongqing400065China
| | - Xiaoming Qiu
- Department of RadiologyHuangshi Central Hospital (Affiliated Hospital of Hubei Polytechnic University) Edong Healthcare GroupHuangshi435002China
| | - Jingjing Xiao
- Xinqiao HospitalArmy Medical UniversityChongqing400038China
| | - Guoyin Wang
- School of Computer Science and TechnologyChongqing University of Posts and TelecommunicationsChongqing400065China
| | - Wenbing Zeng
- Department of RadiologyChongqing Three Gorges Center HospitalChongqing404000China
| | - Weisheng Li
- School of Computer Science and TechnologyChongqing University of Posts and TelecommunicationsChongqing400065China
| | - Yongjian Nian
- School of Biomedical Engineering and Imaging MedicineArmy Medical UniversityChongqing400038China
| | - Wei Chen
- Department of RadiologySouthwest HospitalArmy Medical UniversityChongqing400038China
| |
Collapse
|
204
|
Jalali Moghaddam M, Ghavipour M. Towards smart diagnostic methods for COVID-19: Review of deep learning for medical imaging. IPEM-TRANSLATION 2022; 3:100008. [PMID: 36312890 PMCID: PMC9597575 DOI: 10.1016/j.ipemt.2022.100008] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/01/2022] [Revised: 10/20/2022] [Accepted: 10/24/2022] [Indexed: 11/08/2022]
Abstract
The infectious disease known as COVID-19 has spread dramatically all over the world since December 2019. The fast diagnosis and isolation of infected patients are key factors in slowing down the spread of this virus and better management of the pandemic. Although the CT and X-ray modalities are commonly used for the diagnosis of COVID-19, identifying COVID-19 patients from medical images is a time-consuming and error-prone task. Artificial intelligence has shown to have great potential to speed up and optimize the prognosis and diagnosis process of COVID-19. Herein, we review publications on the application of deep learning (DL) techniques for diagnostics of patients with COVID-19 using CT and X-ray chest images for a period from January 2020 to October 2021. Our review focuses solely on peer-reviewed, well-documented articles. It provides a comprehensive summary of the technical details of models developed in these articles and discusses the challenges in the smart diagnosis of COVID-19 using DL techniques. Based on these challenges, it seems that the effectiveness of the developed models in clinical use needs to be further investigated. This review provides some recommendations to help researchers develop more accurate prediction models.
Collapse
Affiliation(s)
- Marjan Jalali Moghaddam
- Department of Computer Engineering and Information Technology, Amirkabir University of Technology, Tehran, Iran
| | - Mina Ghavipour
- Department of Computer Engineering and Information Technology, Amirkabir University of Technology, Tehran, Iran
| |
Collapse
|
205
|
Sharma A, Mishra PK. Covid-MANet: Multi-task attention network for explainable diagnosis and severity assessment of COVID-19 from CXR images. PATTERN RECOGNITION 2022; 131:108826. [PMID: 35698723 PMCID: PMC9170279 DOI: 10.1016/j.patcog.2022.108826] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/21/2021] [Revised: 04/24/2022] [Accepted: 06/02/2022] [Indexed: 05/17/2023]
Abstract
The devastating outbreak of Coronavirus Disease (COVID-19) cases in early 2020 led the world to face health crises. Subsequently, the exponential reproduction rate of COVID-19 disease can only be reduced by early diagnosis of COVID-19 infection cases correctly. The initial research findings reported that radiological examinations using CT and CXR modality have successfully reduced false negatives by RT-PCR test. This research study aims to develop an explainable diagnosis system for the detection and infection region quantification of COVID-19 disease. The existing research studies successfully explored deep learning approaches with higher performance measures but lacked generalization and interpretability for COVID-19 diagnosis. In this study, we address these issues by the Covid-MANet network, an automated end-to-end multi-task attention network that works for 5 classes in three stages for COVID-19 infection screening. The first stage of the Covid-MANet network localizes attention of the model to the relevant lungs region for disease recognition. The second stage of the Covid-MANet network differentiates COVID-19 cases from bacterial pneumonia, viral pneumonia, normal and tuberculosis cases, respectively. To improve the interpretation and explainability, three experiments have been conducted in exploration of the most coherent and appropriate classification approach. Moreover, the multi-scale attention model MA-DenseNet201 proposed for the classification of COVID-19 cases. The final stage of the Covid-MANet network quantifies the proportion of infection and severity of COVID-19 in the lungs. The COVID-19 cases are graded into more specific severity levels such as mild, moderate, severe, and critical as per the score assigned by the RALE scoring system. The MA-DenseNet201 classification model outperforms eight state-of-the-art CNN models, in terms of sensitivity and interpretation with lung localization network. The COVID-19 infection segmentation by UNet with DenseNet121 encoder achieves dice score of 86.15% outperforming UNet, UNet++, AttentionUNet, R2UNet, with VGG16, ResNet50 and DenseNet201 encoder. The proposed network not only classifies images based on the predicted label but also highlights the infection by segmentation/localization of model-focused regions to support explainable decisions. MA-DenseNet201 model with a segmentation-based cropping approach achieves maximum interpretation of 96% with COVID-19 sensitivity of 97.75%. Finally, based on class-varied sensitivity analysis Covid-MANet ensemble network of MA-DenseNet201, ResNet50 and MobileNet achieve 95.05% accuracy and 98.75% COVID-19 sensitivity. The proposed model is externally validated on an unseen dataset, yields 98.17% COVID-19 sensitivity.
Collapse
Affiliation(s)
- Ajay Sharma
- Department of Computer Science, Institute of Science, Banaras Hindu University, Varanasi 221005, India
| | - Pramod Kumar Mishra
- Department of Computer Science, Institute of Science, Banaras Hindu University, Varanasi 221005, India
| |
Collapse
|
206
|
An evaluation of lightweight deep learning techniques in medical imaging for high precision COVID-19 diagnostics. HEALTHCARE ANALYTICS 2022. [PMID: 37520618 PMCID: PMC9396460 DOI: 10.1016/j.health.2022.100096] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
Abstract
Timely and rapid diagnoses are core to informing on optimum interventions that curb the spread of COVID-19. The use of medical images such as chest X-rays and CTs has been advocated to supplement the Reverse-Transcription Polymerase Chain Reaction (RT-PCR) test, which in turn has stimulated the application of deep learning techniques in the development of automated systems for the detection of infections. Decision support systems relax the challenges inherent to the physical examination of images, which is both time consuming and requires interpretation by highly trained clinicians. A review of relevant reported studies to date shows that most deep learning algorithms utilised approaches are not amenable to implementation on resource-constrained devices. Given the rate of infections is increasing, rapid, trusted diagnoses are a central tool in the management of the spread, mandating a need for a low-cost and mobile point-of-care detection systems, especially for middle- and low-income nations. The paper presents the development and evaluation of the performance of lightweight deep learning technique for the detection of COVID-19 using the MobileNetV2 model. Results demonstrate that the performance of the lightweight deep learning model is competitive with respect to heavyweight models but delivers a significant increase in the efficiency of deployment, notably in the lowering of the cost and memory requirements of computing resources.
Collapse
|
207
|
Cao K, Deng T, Zhang C, Lu L, Li L. A CNN-transformer fusion network for COVID-19 CXR image classification. PLoS One 2022; 17:e0276758. [PMID: 36301907 PMCID: PMC9612494 DOI: 10.1371/journal.pone.0276758] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2022] [Accepted: 10/12/2022] [Indexed: 11/04/2022] Open
Abstract
The global health crisis due to the fast spread of coronavirus disease (Covid-19) has caused great danger to all aspects of healthcare, economy, and other aspects. The highly infectious and insidious nature of the new coronavirus greatly increases the difficulty of outbreak prevention and control. The early and rapid detection of Covid-19 is an effective way to reduce the spread of Covid-19. However, detecting Covid-19 accurately and quickly in large populations remains to be a major challenge worldwide. In this study, A CNN-transformer fusion framework is proposed for the automatic classification of pneumonia on chest X-ray. This framework includes two parts: data processing and image classification. The data processing stage is to eliminate the differences between data from different medical institutions so that they have the same storage format; in the image classification stage, we use a multi-branch network with a custom convolution module and a transformer module, including feature extraction, feature focus, and feature classification sub-networks. Feature extraction subnetworks extract the shallow features of the image and interact with the information through the convolution and transformer modules. Both the local and global features are extracted by the convolution module and transformer module of feature-focus subnetworks, and are classified by the feature classification subnetworks. The proposed network could decide whether or not a patient has pneumonia, and differentiate between Covid-19 and bacterial pneumonia. This network was implemented on the collected benchmark datasets and the result shows that accuracy, precision, recall, and F1 score are 97.09%, 97.16%, 96.93%, and 97.04%, respectively. Our network was compared with other researchers' proposed methods and achieved better results in terms of accuracy, precision, and F1 score, proving that it is superior for Covid-19 detection. With further improvements to this network, we hope that it will provide doctors with an effective tool for diagnosing Covid-19.
Collapse
Affiliation(s)
- Kai Cao
- Key Laboratory of China’s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou, Gansu, China
| | - Tao Deng
- School of Mathematics and Computer Science, Northwest Minzu University, Lanzhou, Gansu, China
- Key Laboratory of Streaming Data Computing Technologies and Application, Northwest Minzu University, Lanzhou, Gansu, China
| | - Chuanlin Zhang
- School of Mathematics and Computer Science, Northwest Minzu University, Lanzhou, Gansu, China
| | - Limeng Lu
- Key Laboratory of China’s Ethnic Languages and Information Technology of Ministry of Education, Northwest Minzu University, Lanzhou, Gansu, China
| | - Lin Li
- School of Computing, University of Leeds, Leeds, United Kingdom
| |
Collapse
|
208
|
Addo D, Zhou S, Jackson JK, Nneji GU, Monday HN, Sarpong K, Patamia RA, Ekong F, Owusu-Agyei CA. EVAE-Net: An Ensemble Variational Autoencoder Deep Learning Network for COVID-19 Classification Based on Chest X-ray Images. Diagnostics (Basel) 2022; 12:2569. [PMID: 36359413 PMCID: PMC9689048 DOI: 10.3390/diagnostics12112569] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2022] [Revised: 10/13/2022] [Accepted: 10/18/2022] [Indexed: 09/08/2024] Open
Abstract
The COVID-19 pandemic has had a significant impact on many lives and the economies of many countries since late December 2019. Early detection with high accuracy is essential to help break the chain of transmission. Several radiological methodologies, such as CT scan and chest X-ray, have been employed in diagnosing and monitoring COVID-19 disease. Still, these methodologies are time-consuming and require trial and error. Machine learning techniques are currently being applied by several studies to deal with COVID-19. This study exploits the latent embeddings of variational autoencoders combined with ensemble techniques to propose three effective EVAE-Net models to detect COVID-19 disease. Two encoders are trained on chest X-ray images to generate two feature maps. The feature maps are concatenated and passed to either a combined or individual reparameterization phase to generate latent embeddings by sampling from a distribution. The latent embeddings are concatenated and passed to a classification head for classification. The COVID-19 Radiography Dataset from Kaggle is the source of chest X-ray images. The performances of the three models are evaluated. The proposed model shows satisfactory performance, with the best model achieving 99.19% and 98.66% accuracy on four classes and three classes, respectively.
Collapse
Affiliation(s)
- Daniel Addo
- School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610056, China
| | - Shijie Zhou
- School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610056, China
| | - Jehoiada Kofi Jackson
- School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610056, China
| | - Grace Ugochi Nneji
- Department of Computing, Oxford Brookes College of Chengdu University of Technology, Chengdu 610059, China
| | - Happy Nkanta Monday
- Department of Computing, Oxford Brookes College of Chengdu University of Technology, Chengdu 610059, China
| | - Kwabena Sarpong
- School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610056, China
| | - Rutherford Agbeshi Patamia
- School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610056, China
| | - Favour Ekong
- School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610056, China
| | | |
Collapse
|
209
|
Faragallah OS, El-Hoseny HM, El-Sayed HS. Efficient COVID-19 super pixel segmentation algorithm using MCFO-based SLIC. JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING 2022; 14:9217-9232. [PMID: 36310644 PMCID: PMC9589839 DOI: 10.1007/s12652-022-04425-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/14/2021] [Accepted: 09/14/2022] [Indexed: 06/08/2023]
Abstract
In computer vision segmentation field, super pixel identity has become an important index in the recently segmentation algorithms especially in medical images. Simple Linear Iterative Clustering (SLIC) algorithm is one of the most popular super pixel methods as it has a great robustness, less sensitive to the image type and benefit to the boundary recall in different kinds of image processing. Recently, COVID-19 severity increased with the lack of an effective treatment or vaccine. As the Corona virus spreads in an unknown manner, th-ere is a strong need for segmenting the lungs infected regions for fast tracking and early detection, no matter how small. This may consider difficult to be achieved with traditional segmentation techniques. From this perspective, this paper presents an efficient modified central force optimization (MCFO)-based SLIC segmentation algorithm to discuss chest CT images for detecting the positive COVID-19 cases. The proposed MCFO-based SLIC segmentation algorithm performance is evaluated and compared with the thresholding segmentation algorithm using different evaluation metrics such as accuracy, boundary recall, F-measure, similarity index, MCC, Dice, and Jaccard. The outcomes demonstrated that the proposed MCFO-based SLIC segmentation algorithm has achieved better detection for the small infected regions in CT lung scans than the thresholding segmentation.
Collapse
Affiliation(s)
- Osama S. Faragallah
- Department of Information Technology, College of Computers and Information Technology, Taif University, P.O. Box 11099, Taif, 21944 Saudi Arabia
| | - Heba M. El-Hoseny
- Department of Computer Science, The Higher Future Institute for Specialized Technological Studies, El Shorouk, Egypt
| | - Hala S. El-Sayed
- Department of Electrical Engineering, Faculty of Engineering, Menoufia University, Shebin El-Kom, 32511 Egypt
| |
Collapse
|
210
|
Fast COVID-19 Detection from Chest X-Ray Images Using DCT Compression. APPLIED COMPUTATIONAL INTELLIGENCE AND SOFT COMPUTING 2022. [DOI: 10.1155/2022/2656818] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022] Open
Abstract
Novel coronavirus (COVID-19) is a new strain of coronavirus, first identified in a cluster with pneumonia symptoms caused by SARS-CoV-2 virus. It is fast spreading all over the world. Most infected people will develop mild to moderate illness and recover without hospitalization. Currently, real-time quantitative reverse transcription-PCR (rqRT-PCR) is popular for coronavirus detection due to its high specificity, simple quantitative analysis, and higher sensitivity than conventional RT-PCR. Antigen tests are also commonly used. It is very essential for the automatic detection of COVID-19 from publicly available resources. Chest X-ray (CXR) images are used for the classification of COVID-19, normal, and viral pneumonia cases. The CXR images are divided into sub-blocks for finding out the discrete cosine transform (DCT) for every sub-block in this proposed method. In order to produce a compressed version for each CXR image, the DCT energy compaction capability is used. For each image, hardly few spectral DCT components are included as features. The dimension of the final feature vectors is reduced by scanning the compressed images using average pooling windows. In the 3-set classification, a multilayer artificial neural network is used. It is essential to triage non-COVID-19 patients with pneumonia to give out hospital resources efficiently. Higher size feature vectors are used for designing binary classification for COVID-19 and pneumonia. The proposed method achieved an average accuracy of 95% and 94% for the 3-set classification and binary classification, respectively. The proposed method achieves better accuracy than that of the recent state-of-the-art techniques. Also, the time required for the implementation is less.
Collapse
|
211
|
Khosravi B, Rouzrokh P, Faghani S, Moassefi M, Vahdati S, Mahmoudi E, Chalian H, Erickson BJ. Machine Learning and Deep Learning in Cardiothoracic Imaging: A Scoping Review. Diagnostics (Basel) 2022; 12:2512. [PMID: 36292201 PMCID: PMC9600598 DOI: 10.3390/diagnostics12102512] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/17/2022] [Revised: 10/14/2022] [Accepted: 10/15/2022] [Indexed: 01/17/2023] Open
Abstract
Machine-learning (ML) and deep-learning (DL) algorithms are part of a group of modeling algorithms that grasp the hidden patterns in data based on a training process, enabling them to extract complex information from the input data. In the past decade, these algorithms have been increasingly used for image processing, specifically in the medical domain. Cardiothoracic imaging is one of the early adopters of ML/DL research, and the COVID-19 pandemic resulted in more research focus on the feasibility and applications of ML/DL in cardiothoracic imaging. In this scoping review, we systematically searched available peer-reviewed medical literature on cardiothoracic imaging and quantitatively extracted key data elements in order to get a big picture of how ML/DL have been used in the rapidly evolving cardiothoracic imaging field. During this report, we provide insights on different applications of ML/DL and some nuances pertaining to this specific field of research. Finally, we provide general suggestions on how researchers can make their research more than just a proof-of-concept and move toward clinical adoption.
Collapse
Affiliation(s)
- Bardia Khosravi
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
- Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN 55905, USA
| | - Pouria Rouzrokh
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
- Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN 55905, USA
| | - Shahriar Faghani
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
| | - Mana Moassefi
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
| | - Sanaz Vahdati
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
| | - Elham Mahmoudi
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
| | - Hamid Chalian
- Department of Radiology, Cardiothoracic Imaging, University of Washington, Seattle, WA 98195, USA
| | - Bradley J. Erickson
- Radiology Informatics Lab (RIL), Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA
| |
Collapse
|
212
|
Zhang S, Yuan GC. Deep Transfer Learning for COVID-19 Detection and Lesion Recognition Using Chest CT Images. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2022; 2022:4509394. [PMID: 36285284 PMCID: PMC9588382 DOI: 10.1155/2022/4509394] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/02/2022] [Revised: 09/11/2022] [Accepted: 09/24/2022] [Indexed: 12/15/2022]
Abstract
Starting from December 2019, the global pandemic of coronavirus disease 2019 (COVID-19) is continuously expanding and has caused several millions of deaths worldwide. Fast and accurate diagnostic methods for COVID-19 detection play a vital role in containing the plague. Chest computed tomography (CT) is one of the most commonly used diagnosis methods. However, a complete CT-scan has hundreds of slices, and it is time-consuming for radiologists to check each slice to diagnose COVID-19. This study introduces a novel method for fast and automated COVID-19 diagnosis using the chest CT scans. The proposed models are based on the state-of-the-art deep convolutional neural network (CNN) architecture, and a 2D global max pooling (globalMaxPool2D) layer is used to improve the performance. We compare the proposed models to the existing state-of-the-art deep learning models such as CNN based models and vision transformer (ViT) models. Based off of metric such as area under curve (AUC), sensitivity, specificity, accuracy, and false discovery rate (FDR), experimental results show that the proposed models outperform the previous methods, and the best model achieves an area under curve of 0.9744 and accuracy 94.12% on our test datasets. It is also shown that the accuracy is improved by around 1% by using the 2D global max pooling layer. Moreover, a heatmap method to highlight the lesion area on COVID-19 chest CT images is introduced in the paper. This heatmap method is helpful for a radiologist to identify the abnormal pattern of COVID-19 on chest CT images. In addition, we also developed a freely accessible online simulation software for automated COVID-19 detection using CT images. The proposed deep learning models and software tool can be used by radiologist to diagnose COVID-19 more accurately and efficiently.
Collapse
Affiliation(s)
- Sai Zhang
- Qualcomm Inc., 5775 Morehouse Drive, San Diego, CA 92121, USA
| | - Guo-Chang Yuan
- Department of Emergency Medicine, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China
| |
Collapse
|
213
|
Duanmu H, Ren T, Li H, Mehta N, Singer AJ, Levsky JM, Lipton ML, Duong TQ. Deep learning of longitudinal chest X-ray and clinical variables predicts duration on ventilator and mortality in COVID-19 patients. Biomed Eng Online 2022; 21:77. [PMID: 36242040 PMCID: PMC9568988 DOI: 10.1186/s12938-022-01045-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2022] [Accepted: 09/16/2022] [Indexed: 11/10/2022] Open
Abstract
Objectives To use deep learning of serial portable chest X-ray (pCXR) and clinical variables to predict mortality and duration on invasive mechanical ventilation (IMV) for Coronavirus disease 2019 (COVID-19) patients. Methods This is a retrospective study. Serial pCXR and serial clinical variables were analyzed for data from day 1, day 5, day 1–3, day 3–5, or day 1–5 on IMV (110 IMV survivors and 76 IMV non-survivors). The outcome variables were duration on IMV and mortality. With fivefold cross-validation, the performance of the proposed deep learning system was evaluated by receiver operating characteristic (ROC) analysis and correlation analysis. Results Predictive models using 5-consecutive-day data outperformed those using 3-consecutive-day and 1-day data. Prediction using data closer to the outcome was generally better (i.e., day 5 data performed better than day 1 data, and day 3–5 data performed better than day 1–3 data). Prediction performance was generally better for the combined pCXR and non-imaging clinical data than either alone. The combined pCXR and non-imaging data of 5 consecutive days predicted mortality with an accuracy of 85 ± 3.5% (95% confidence interval (CI)) and an area under the curve (AUC) of 0.87 ± 0.05 (95% CI) and predicted the duration needed to be on IMV to within 2.56 ± 0.21 (95% CI) days on the validation dataset. Conclusions Deep learning of longitudinal pCXR and clinical data have the potential to accurately predict mortality and duration on IMV in COVID-19 patients. Longitudinal pCXR could have prognostic value if these findings can be validated in a large, multi-institutional cohort.
Collapse
Affiliation(s)
- Hongyi Duanmu
- Department of Radiology, Albert Einstein College of Medicine, Bronx, NY, 10461, USA
| | - Thomas Ren
- Department of Radiology, Albert Einstein College of Medicine, Bronx, NY, 10461, USA
| | - Haifang Li
- Department of Radiology, Albert Einstein College of Medicine, Bronx, NY, 10461, USA
| | - Neil Mehta
- Department of Radiology, Albert Einstein College of Medicine, Bronx, NY, 10461, USA
| | - Adam J Singer
- Department of Emergency Medicine, Renaissance School of Medicine, Stony Brook University, Stony Brook, NY, 11794, USA
| | - Jeffrey M Levsky
- Department of Radiology, Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, NY, 10461, USA
| | - Michael L Lipton
- Department of Radiology, Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, NY, 10461, USA
| | - Tim Q Duong
- Department of Radiology, Montefiore Medical Center, Albert Einstein College of Medicine, Bronx, NY, 10461, USA.
| |
Collapse
|
214
|
Shokri F, Rezapoor S, Najafi M, Asadi M, Karimi alavije M, Abolhassani M, Moieneddin MH, Ashrafi AM, Gholipour N, Naderi P, Charati JY, Alizadeh-Navaei R, Saeedi M, Heidary M, Rostamnezhad M. Efficacy of drug regimen with and without oseltamivir in hospitalized patients with COVID-19: A retrospective study. VACUNAS 2022; 24:141-149. [PMID: 36211984 PMCID: PMC9531663 DOI: 10.1016/j.vacun.2022.09.077] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/13/2022] [Accepted: 09/16/2022] [Indexed: 11/05/2022]
Abstract
Introduction Coronavirus disease 2019 (COVID-19) is the most critical issue in nowadays medicine. We aimed to evaluate the use and therapeutic outcomes of oseltamivir, an antiviral drug for patients with COVID-19. Materials and method In an observational study conducted at Imam Khomeini Hospital in Amol, Iran, data for 544 patients with laboratory and CT scan result confirmed COVID-19 were retrospectively collected between February 24th and April 13th 2020. To compare the characteristics of patients based on gender, the chi-square test was used. Logistic regression was used to evaluate the effect of oseltamivir on the outcome of treatment. Logrank test were used to compare the length of hospital stay in people treated with oseltamivir and drugs other than oseltamivir. Results Kaplan–Meier and logrank test showed no significant reduction in hospitalization time and survival rate following treatment with oseltamivir. However, a significant increase in lymphocytes count and reduction of C-reactive protein (CRP) level detected. Conclusion Administration of oseltamivir for patients with COVID-19 didn't show any improvement in hospitalization duration and survival rate.
Collapse
Affiliation(s)
- Fazlollah Shokri
- Department of Medical Genetics, Faculty of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
| | - Saeed Rezapoor
- Department of Radiology, Imam Khomeini Hospital, Amol, Iran
| | - Masoud Najafi
- Medical Technology Research Center, Kermanshah University of Medical Sciences, Kermanshah, Iran,Radiology and Nuclear Medicine Department, Kermanshah University of Medical Sciences, Kermanshah, Iran
| | - Mohsen Asadi
- Department of Hematology and Blood Banking, Faculty of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
| | | | - Moussa Abolhassani
- International Federation of Inventors' Associations (IFIA), Geneva, Switzerland
| | | | - Amir Muhammad Ashrafi
- Student Research Committee, Amol Faculty of Nursing, Mazandaran University of Medical Sciences, Sari, Iran
| | - Narges Gholipour
- Student Research Committee, School of Nursing and Midwifery, Mazandaran University of Medical Sciences, Sari, Iran
| | - Parisa Naderi
- Department of Biology, Faculty of Cellular and Molecular Sciences, Central Tehran Branch, Islamic Azad University, Tehran, Iran
| | - Jamshid Yazdani Charati
- Department of Biostatistics, Faculty of Health, Mazandaran University of Medical Sciences, Sari, Iran
| | - Reza Alizadeh-Navaei
- Gastrointestinal Cancer Research Center, Non-communicable Diseases Institute, Mazandaran University of Medical Sciences, Sari, Iran
| | - Majid Saeedi
- Department of Pharmaceutics, Faculty of Pharmacy, Mazandaran University of Medical Science, Sari, Iran
| | - Mohsen Heidary
- Cellular and Molecular Research Center, Sabzevar University of Medical Sciences, Sabzevar, Iran,Corresponding authors
| | - Mostafa Rostamnezhad
- Department of Pharmaceutics, Faculty of Pharmacy, Tehran University of Medical Sciences, Tehran, Iran,Corresponding authors
| |
Collapse
|
215
|
Brizawasi A, Ahirwar AK, Prabhat, Kaim K, Ahirwar P, Kumawat R, Prasad J. COVID-19: a viewpoint from hepatic perspective. Horm Mol Biol Clin Investig 2022; 44:97-103. [PMID: 36190156 DOI: 10.1515/hmbci-2022-0026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2022] [Accepted: 07/20/2022] [Indexed: 11/15/2022]
Abstract
Coronaviruses as such are known since last century. The name is derived from their shape which has crown (corona) like radiating spikes. The recent one however is a different one from the Coronavirus involved in SARS (2002-2004) and MERS (2012) in being highly infectious. Initially COVID 19 had a high case fatality rate which has now decreased to a significant extent. Many cases of COVID 19 are asymptomatic with a significant number of positive cases developing a triad of fever, breathlessness and GI symptoms. Recent travel increases the probability of infection. The pathogenesis involves ACE 2 receptors. So, it has been found that there are more cases and mortality among hypertensive individuals. Even higher among the people who use ACE inhibitor in comparison to those who use other anti-hypertensive drugs. Treatment is usually symptomatic. Antiviral drugs and vaccines against COVID-19 are being used. Deranged liver enzymes are common in COVID-19, however, serious liver injury is not much documented. Liver injury is either due to disease itself or due to antiviral drugs. Extra care like strict social distancing, avoiding unnecessary contact is needed for those with autoimmune hepatitis, liver cancer and those who are in immunosuppression because of a scheduled or already liver transplant. Further research is definitely needed in this field. The upcoming researches should also focus on liver injuries associated with disease course and derangements arising as side effects of treatment of COVID-19.
Collapse
Affiliation(s)
| | - Ashok Kumar Ahirwar
- Department of Biochemistry, University College of Medical Sciences, New Delhi, India
| | - Prabhat
- Department of Biochemistry, All India Institute of Medical Sciences, Gorakhpur, Uttar Pradesh, India
| | | | - Pradeep Ahirwar
- Department of Radio-diagnosis, Index Medical College, Hospital & Research Centre, Indore, Madhya Pradesh, India
| | - Rajani Kumawat
- Department of Biochemistry, All India Institute of Medical Sciences, Bathinda, Punjab, India
| | - Jitender Prasad
- Department of Biochemistry, All India Institute of Medical Sciences, Deoghar, Jharkhand, India
| |
Collapse
|
216
|
Han J, Yang X, Xu W, Jin R, Meng S, Ding L, Zhang Y, Hu X, Liu W, Li H, Meng F. Lung ultrasonography findings of coronavirus disease 2019 patients: Comparison between primary and secondary regions of China. Immun Inflamm Dis 2022; 10:e713. [PMID: 36169247 PMCID: PMC9514061 DOI: 10.1002/iid3.713] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2022] [Revised: 09/05/2022] [Accepted: 09/12/2022] [Indexed: 12/02/2022] Open
Abstract
BACKGROUND An unexplained pneumonia occurred in Wuhan, China in December 2019, later identified and named coronavirus disease 2019 (COVID-19). This study aimed to compare the ultrasonographic features of the lung between patients with COVID-19 in Wuhan (the primary region) and those in Beijing (the secondary region) and to find the value of applying ultrasound in COVID-19. METHODS A total of 248 COVID-19 cases were collected, including long-term residents in Wuhan (138), those who had a short-term stay in Wuhan (72), and those who had never visited Wuhan (38). Ultrasound examination was performed daily; the highest lung ultrasound score (LUS) was the first comparison point, while the LUS of the fifth day thereafter was the second comparison point. The differences between overall treatment and ultrasonography of left and right lungs among groups were compared. RESULTS The severity decreased significantly after treatment. The scores of the groups with long-term residence and short-term stay in Wuhan were higher than those of the group that had never been to Wuhan. CONCLUSION Ultrasonography is effective for dynamic monitoring of COVID-19. The ultrasonographic features of patients in the Wuhan area indicated relatively severe disease. Thus, Wuhan was the main affected area of china.
Collapse
Affiliation(s)
- Jing Han
- Ultrasound and Functional Diagnosis Center, Beijing You An HospitalCapital Medical UniversityBeijingChina
| | - Xi Yang
- Department of ultrasoundHanyang Hospital Affiliated to Wuhan University of Science and TechnologyWuhanChina
| | - Wei Xu
- Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education/Beijing), Department of Hepato‐Pancreato‐Biliary SurgeryPeking University Cancer Hospital and InstituteBeijingChina
| | - Ronghua Jin
- Beijing You An HospitalCapital Medical UniversityBeijingChina
| | - Sha Meng
- Department of Science and Technology, Beijing You An HospitalCapital Medical UniversityBeijingChina
| | - Lei Ding
- Ultrasound and Functional Diagnosis Center, Beijing You An HospitalCapital Medical UniversityBeijingChina
| | - Yuan Zhang
- Ultrasound and Functional Diagnosis Center, Beijing You An HospitalCapital Medical UniversityBeijingChina
| | | | - Weiyuan Liu
- Ultrasound and Functional Diagnosis Center, Beijing You An HospitalCapital Medical UniversityBeijingChina
| | - Haowen Li
- Ultrasonography, China Aerospace Science and Industry Corporation 731 HospitalBeijingChina
| | - Fankun Meng
- Ultrasound and Functional Diagnosis Center, Beijing You An HospitalCapital Medical UniversityBeijingChina
| |
Collapse
|
217
|
Srivastava G, Pradhan N, Saini Y. Ensemble of Deep Neural Networks based on Condorcet's Jury Theorem for screening Covid-19 and Pneumonia from radiograph images. Comput Biol Med 2022; 149:105979. [PMID: 36063689 PMCID: PMC9404085 DOI: 10.1016/j.compbiomed.2022.105979] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/02/2022] [Revised: 08/03/2022] [Accepted: 08/13/2022] [Indexed: 11/04/2022]
Abstract
COVID-19 detection using Artificial Intelligence and Computer-Aided Diagnosis has been the subject of several studies. Deep Neural Networks with hundreds or even millions of parameters (weights) are referred to as "black boxes" because their behavior is difficult to comprehend, even when the model's structure and weights are visible. On the same dataset, different Deep Convolutional Neural Networks perform differently. So, we do not necessarily have to rely on just one model; instead, we can evaluate our final score by combining multiple models. While including multiple models in the voter pool, it is not always true that the accuracy will improve. So, In this regard, the authors proposed a novel approach to determine the voting ensemble score of individual classifiers based on Condorcet's Jury Theorem (CJT). The authors demonstrated that the theorem holds while ensembling the N number of classifiers in Neural Networks. With the help of CJT, the authors proved that a model's presence in the voter pool would improve the likelihood that the majority vote will be accurate if it is more accurate than the other models. Besides this, the authors also proposed a Domain Extended Transfer Learning (DETL) ensemble model as a soft voting ensemble method and compared it with CJT based ensemble method. Furthermore, as deep learning models typically fail in real-world testing, a novel dataset has been used with no duplicate images. Duplicates in the dataset are quite problematic since they might affect the training process. Therefore, having a dataset devoid of duplicate images is considered to prevent data leakage problems that might impede the thorough assessment of the trained models. The authors also employed an algorithm for faster training to save computational efforts. Our proposed method and experimental results outperformed the state-of-the-art with the DETL-based ensemble model showing an accuracy of 97.26%, COVID-19, sensitivity of 98.37%, and specificity of 100%. CJT-based ensemble model showed an accuracy of 98.22%, COVID-19, sensitivity of 98.37%, and specificity of 99.79%.
Collapse
Affiliation(s)
- Gaurav Srivastava
- Department of Computer Science and Engineering, Manipal University Jaipur, 303007, Rajasthan, India.
| | - Nitesh Pradhan
- Department of Computer Science and Engineering, Manipal University Jaipur, 303007, Rajasthan, India.
| | - Yashwin Saini
- Department of Computer Science and Engineering, Manipal University Jaipur, 303007, Rajasthan, India
| |
Collapse
|
218
|
Chainchel Singh MK, Mohd Noor MH, Ibrahim MA, Siew SF, Lai PS, Lai PS. Use of Post-Mortem Computed Tomography During the COVID-19 Pandemic: The Malaysian Experience. Malays J Med Sci 2022; 29:83-92. [PMID: 36474535 PMCID: PMC9681000 DOI: 10.21315/mjms2022.29.5.9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2021] [Accepted: 02/03/2022] [Indexed: 11/06/2022] Open
Abstract
Background COVID-19 was declared a pandemic by the World Health Organization (WHO). COVID-19 is highly contagious, making it a threat to healthcare workers, including those working in mortuaries. Therefore, it is important to determine if the cause of death (COD) could be identified using limited autopsy, diagnostic tests and post-mortem imaging modalities instead of full autopsy. This study aims to examine the effectiveness of post-mortem imaging, specifically post-mortem computed tomography (PMCT) at determining the COD during a pandemic. Methods This cross-sectional study included 172 subjects with suspected or unknown COVID-19 status brought in dead to the institute's mortuary during the pandemic in Malaysia. PMCT images reported by forensic radiologists and their agreement with conventional autopsy findings by forensic pathologists regarding COD were analysed to look at the effectiveness of PMCT in determining COD during a pandemic. Results Analysis showed that 78.7% (133) of cases reported by forensic radiologists concurred with the COD certified by forensic pathologists. Of these cases, 85 (63.9%) had undergone only external examination and real-time reverse transcriptase polymerase chain reaction (rRT-PCR) COVID-19 testing, meaning that imaging was the sole method used to determine the COD besides history from available medical records and the investigating police officer. Conclusion PMCT can be used as a complement to medicolegal autopsies in pandemic contexts, as it provides significant information on the possible COD without jeopardising the safety of mortuary health care workers.
Collapse
Affiliation(s)
- Mansharan Kaur Chainchel Singh
- Institute of Pathology, Laboratory and Forensic Medicine (I-PPerForM), Universiti Teknologi MARA (UiTM), Selangor, Malaysia,Faculty of Medicine, Universiti Teknologi MARA (UiTM), Selangor, Malaysia,National Institute of Forensic Medicine, Hospital Kuala Lumpur, Kuala Lumpur, Malaysia
| | - Mohamad Helmee Mohd Noor
- National Institute of Forensic Medicine, Hospital Kuala Lumpur, Kuala Lumpur, Malaysia,Radiology Department, Hospital Kuala Lumpur, Kuala Lumpur, Malaysia
| | | | - Sheue Feng Siew
- National Institute of Forensic Medicine, Hospital Kuala Lumpur, Kuala Lumpur, Malaysia
| | - Poh Soon Lai
- National Institute of Forensic Medicine, Hospital Kuala Lumpur, Kuala Lumpur, Malaysia
| | | | | | | | | | | | | | | | | |
Collapse
|
219
|
Alyafei K, Ahmed R, Abir FF, Chowdhury MEH, Naji KK. A comprehensive review of COVID-19 detection techniques: From laboratory systems to wearable devices. Comput Biol Med 2022; 149:106070. [PMID: 36099862 PMCID: PMC9433350 DOI: 10.1016/j.compbiomed.2022.106070] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2022] [Revised: 08/03/2022] [Accepted: 08/27/2022] [Indexed: 11/30/2022]
Abstract
Screening of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) among symptomatic and asymptomatic patients offers unique opportunities for curtailing the transmission of novel coronavirus disease 2019, commonly known as COVID-19. Molecular diagnostic techniques, namely reverse transcription loop-mediated isothermal amplification (RT-LAMP), reverse transcription-polymerase chain reaction (RT-PCR), and immunoassays, have been frequently used to identify COVID-19 infection. Although these techniques are robust and accurate, mass testing of potentially infected individuals has shown difficulty due to the resources, manpower, and costs it entails. Moreover, as these techniques are typically used to test symptomatic patients, healthcare systems have failed to screen asymptomatic patients, whereas the spread of COVID-19 by these asymptomatic individuals has turned into a crucial problem. Besides, respiratory infections or cardiovascular conditions generally demonstrate changes in physiological parameters, namely body temperature, blood pressure, and breathing rate, which signifies the onset of diseases. Such vitals monitoring systems have shown promising results employing artificial intelligence (AI). Therefore, the potential use of wearable devices for monitoring asymptomatic COVID-19 individuals has recently been explored. This work summarizes the efforts that have been made in the domains from laboratory-based testing to asymptomatic patient monitoring via wearable systems.
Collapse
Affiliation(s)
- Khalid Alyafei
- Department of Mechanical and Industrial Engineering, College of Engineering, Qatar University, Doha, 2713, Qatar
| | - Rashid Ahmed
- Department of Mechanical and Industrial Engineering, College of Engineering, Qatar University, Doha, 2713, Qatar; Department of Biotechnology, Mirpur University of Science and Technology (MUST), Mirpur, 10250, AJK, Pakistan
| | - Farhan Fuad Abir
- Department of Electrical Engineering, Qatar University, Doha, 2713, Qatar
| | | | | |
Collapse
|
220
|
Karthik R, Menaka R, Hariharan M, Kathiresan GS. AI for COVID-19 Detection from Radiographs: Incisive Analysis of State of the Art Techniques, Key Challenges and Future Directions. Ing Rech Biomed 2022; 43:486-510. [PMID: 34336141 PMCID: PMC8312058 DOI: 10.1016/j.irbm.2021.07.002] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2021] [Revised: 06/14/2021] [Accepted: 07/19/2021] [Indexed: 12/24/2022]
Abstract
Background and objective In recent years, Artificial Intelligence has had an evident impact on the way research addresses challenges in different domains. It has proven to be a huge asset, especially in the medical field, allowing for time-efficient and reliable solutions. This research aims to spotlight the impact of deep learning and machine learning models in the detection of COVID-19 from medical images. This is achieved by conducting a review of the state-of-the-art approaches proposed by the recent works in this field. Methods The main focus of this study is the recent developments of classification and segmentation approaches to image-based COVID-19 detection. The study reviews 140 research papers published in different academic research databases. These papers have been screened and filtered based on specified criteria, to acquire insights prudent to image-based COVID-19 detection. Results The methods discussed in this review include different types of imaging modality, predominantly X-rays and CT scans. These modalities are used for classification and segmentation tasks as well. This review seeks to categorize and discuss the different deep learning and machine learning architectures employed for these tasks, based on the imaging modality utilized. It also hints at other possible deep learning and machine learning architectures that can be proposed for better results towards COVID-19 detection. Along with that, a detailed overview of the emerging trends and breakthroughs in Artificial Intelligence-based COVID-19 detection has been discussed as well. Conclusion This work concludes by stipulating the technical and non-technical challenges faced by researchers and illustrates the advantages of image-based COVID-19 detection with Artificial Intelligence techniques.
Collapse
Affiliation(s)
- R Karthik
- Centre for Cyber Physical Systems, Vellore Institute of Technology, Chennai, India
| | - R Menaka
- Centre for Cyber Physical Systems, Vellore Institute of Technology, Chennai, India
| | - M Hariharan
- School of Computing Sciences and Engineering, Vellore Institute of Technology, Chennai, India
| | - G S Kathiresan
- School of Electronics Engineering, Vellore Institute of Technology, Chennai, India
| |
Collapse
|
221
|
Wang H, Luo L, Lv W, Jin T, Jiang M, Miao M, Chen Q. Comparison of chest CT features between progressive and nonprogressive patients with COVID-19 pneumonia: A meta-analysis. Medicine (Baltimore) 2022; 101:e30744. [PMID: 36181019 PMCID: PMC9524519 DOI: 10.1097/md.0000000000030744] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/05/2023] Open
Abstract
OBJECTIVE The aim of this study was to compare the radiographic features of patients with progressive and nonprogressive coronavirus disease 2019 (COVID-19) pneumonia. METHODS PubMed, Embase, and Cochrane Library databases were searched from January 1, 2020, to February 28, 2022, by using the keywords: "COVID-19", "novel Coronavirus", "2019-novel coronavirus", "CT", "radiology" and "imaging". We summarized the computed tomography manifestations of progressive and nonprogressive COVID-19 pneumonia. The meta-analysis was performed using the Stata statistical software version 16.0. RESULTS A total of 10 studies with 1092 patients were included in this analysis. The findings of this meta-analysis indicated that the dominating computed tomography characteristics of progressive patients were a crazy-paving pattern (odds ratio [OR] = 2.10) and patchy shadowing (OR = 1.64). The dominating lesions distribution of progressive patients were bilateral (OR = 11.62), central mixed subpleural (OR = 1.37), and central (OR = 1.36). The other dominating lesions of progressive patients were pleura thickening (OR = 2.13), lymphadenopathy (OR = 1.74), vascular enlargement (OR = 1.39), air bronchogram (OR = 1.29), and pleural effusion (OR = 1.29). Two patterns of lesions showed significant links with the progression of disease: nodule (P = .001) and crazy-paving pattern (P = .023). Four lesions distribution showed significant links with the progression of disease: bilateral (P = .004), right upper lobe (P = .003), right middle lobe (P = .001), and left upper lobe (P = .018). CONCLUSION Nodules, crazy-paving pattern, and/or new lesions in bilateral, upper and middle lobe of right lung, and lower lobe of left lung may indicate disease deterioration. Clinicians should formulate or modify treatment strategies in time according to these specific conditions.
Collapse
Affiliation(s)
- Haijing Wang
- Baotou Medical College, Inner Mongolia University of Science and Technology, Baotou City, Inner Mongolia Autonomous Region, China
- Department of Imaging, the First Affiliated Hospital of Baotou Medical College, Inner Mongolia University of Science and Technology, Baotou City, Inner Mongolia Autonomous Region, China
| | - Lin Luo
- Department of Imaging, the First Affiliated Hospital of Baotou Medical College, Inner Mongolia University of Science and Technology, Baotou City, Inner Mongolia Autonomous Region, China
| | - Wenwu Lv
- Department of Imaging, the First Affiliated Hospital of Baotou Medical College, Inner Mongolia University of Science and Technology, Baotou City, Inner Mongolia Autonomous Region, China
| | - Tao Jin
- Department of Imaging, the First Affiliated Hospital of Baotou Medical College, Inner Mongolia University of Science and Technology, Baotou City, Inner Mongolia Autonomous Region, China
| | - Mingkuan Jiang
- Baotou Medical College, Inner Mongolia University of Science and Technology, Baotou City, Inner Mongolia Autonomous Region, China
| | - Miao Miao
- Baotou Medical College, Inner Mongolia University of Science and Technology, Baotou City, Inner Mongolia Autonomous Region, China
| | - Qiang Chen
- Department of Imaging, the First Affiliated Hospital of Baotou Medical College, Inner Mongolia University of Science and Technology, Baotou City, Inner Mongolia Autonomous Region, China
- *Correspondence: Qiang Chen, Department of Imaging, the First Affiliated Hospital of Baotou Medical College, Baotou City, Inner Mongolia University of Science and Technology, China (E-mail: )
| |
Collapse
|
222
|
Tortolini C, Angeloni A, Antiochia R. A Comparative Study of Voltammetric vs Impedimetric Immunosensor for Rapid SARS-CoV-2 Detection at the Point-of-care. ELECTROANAL 2022; 35:ELAN202200349. [PMID: 36247366 PMCID: PMC9538619 DOI: 10.1002/elan.202200349] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2022] [Accepted: 09/15/2022] [Indexed: 11/09/2022]
Abstract
Here, a novel biosensing platform for the detection of SARS-CoV-2 usable both at voltammetric and impedimetric mode is reported. The platform was constructed on a multi-walled carbon nanotubes (MWCNTs) screen-printed electrode (SPE) functionalized by methylene blue (MB), antibodies against SARS-CoV-2 spike protein (SP), a bioactive layer of chitosan (CS) and protein A (PrA). The voltammetric sensor showed superior performances both in phosphate buffer solution (PBS) and spiked-saliva samples, with LOD values of 5.0±0.1 and 30±2.1 ng/mL, compared to 20±1.8 and 50±2.5 ng/mL for the impedimetric sensor. Moreover, the voltammetric immunosensor was tested in real saliva, showing promising results.
Collapse
Affiliation(s)
- Cristina Tortolini
- Department of Experimental MedicineUniversity of Rome “La Sapienza”Viale Regina Elena 32400166RomeItaly
| | - Antonio Angeloni
- Department of Experimental MedicineUniversity of Rome “La Sapienza”Viale Regina Elena 32400166RomeItaly
| | - Riccarda Antiochia
- Department of Chemistry and Drug TechnologiesUniversity of Rome “La Sapienza”P.le Aldo Moro 500185RomeItaly
| |
Collapse
|
223
|
Koh SJT, Nafea M, Nugroho H. Towards edge devices implementation: deep learning model with visualization for COVID-19 prediction from chest X-ray. ADVANCES IN COMPUTATIONAL INTELLIGENCE 2022; 2:33. [PMID: 36187081 PMCID: PMC9516511 DOI: 10.1007/s43674-022-00044-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/02/2021] [Revised: 05/17/2022] [Accepted: 09/01/2022] [Indexed: 10/29/2022]
Abstract
Due to the outbreak of COVID-19 disease globally, countries around the world are facing shortages of resources (i.e. testing kits, medicine). A quick diagnosis of COVID-19 and isolating patients are crucial in curbing the pandemic, especially in rural areas. This is because the disease is highly contagious and can spread easily. To assist doctors, several studies have proposed an initial detection of COVID-19 cases using radiological images. In this paper, we propose an alternative method for analyzing chest X-ray images to provide an efficient and accurate diagnosis of COVID-19 which can run on edge devices. The approach acts as an enabler for the deep learning model to be deployed in practical application. Here, the convolutional neural network models which are fine-tuned to predict COVID-19 and pneumonia infection from chest X-ray images are developed by adopting transfer learning techniques. The developed model yielded an accuracy of 98.13%, sensitivity of 97.7%, and specificity of 99.1%. To highlight the important regions in the X-ray images which directs the model to its decision/prediction, we adopted the Gradient Class Activation Map (Grad-CAM). The generated heat maps from the Grad-CAM were then compared with the annotated X-ray images by board-certified radiologists. Results showed that the findings strongly correlate with clinical evidence. For practical deployment, we implemented the trained model in edge devices (NCS2) and this has achieved an improvement of 90% in inference speed compared to CPU. This shows that the developed model has the potential to be implemented on the edge, for example in primary care clinics and rural areas which are not well-equipped or do not have access to stable internet connections.
Collapse
Affiliation(s)
- Shaline Jia Thean Koh
- Present Address: Department of Electrical and Electronic Engineering, University of Nottingham Malaysia, Semenyih, 43500 Malaysia
| | - Marwan Nafea
- Present Address: Department of Electrical and Electronic Engineering, University of Nottingham Malaysia, Semenyih, 43500 Malaysia
| | - Hermawan Nugroho
- Present Address: Department of Electrical and Electronic Engineering, University of Nottingham Malaysia, Semenyih, 43500 Malaysia
| |
Collapse
|
224
|
Muzoğlu N, Halefoğlu AM, Avci MO, Kaya Karaaslan M, Yarman BSB. Detection of COVID-19 and its pulmonary stage using Bayesian hyperparameter optimization and deep feature selection methods. EXPERT SYSTEMS 2022; 40:e13141. [PMID: 36245832 PMCID: PMC9537791 DOI: 10.1111/exsy.13141] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/06/2022] [Revised: 07/25/2022] [Accepted: 09/05/2022] [Indexed: 06/16/2023]
Abstract
Since the first case of COVID-19 was reported in December 2019, many studies have been carried out on artificial intelligence for the rapid diagnosis of the disease to support health services. Therefore, in this study, we present a powerful approach to detect COVID-19 and COVID-19 findings from computed tomography images using pre-trained models using two different datasets. COVID-19, influenza A (H1N1) pneumonia, bacterial pneumonia and healthy lung image classes were used in the first dataset. Consolidation, crazy-paving pattern, ground-glass opacity, ground-glass opacity and consolidation, ground-glass opacity and nodule classes were used in the second dataset. The study consists of four steps. In the first two steps, distinctive features were extracted from the final layers of the pre-trained ShuffleNet, GoogLeNet and MobileNetV2 models trained with the datasets. In the next steps, the most relevant features were selected from the models using the Sine-Cosine optimization algorithm. Then, the hyperparameters of the Support Vector Machines were optimized with the Bayesian optimization algorithm and used to reclassify the feature subset that achieved the highest accuracy in the third step. The overall accuracy obtained for the first and second datasets is 99.46% and 99.82%, respectively. Finally, the performance of the results visualized with Occlusion Sensitivity Maps was compared with Gradient-weighted class activation mapping. The approach proposed in this paper outperformed other methods in detecting COVID-19 from multiclass viral pneumonia. Moreover, detecting the stages of COVID-19 in the lungs was an innovative and successful approach.
Collapse
Affiliation(s)
- Nedim Muzoğlu
- Department of Biomedical Engineering, Faculty of EngineeringIstanbul University‐CerrahpasaIstanbulTurkey
| | - Ahmet Mesrur Halefoğlu
- Department of RadiologySisli Hamidiye Etfal Training and Research Hospital, Health Sciences UniversityIstanbulTurkey
| | - Muhammed Onur Avci
- Department of Biomedical Engineering, Faculty of EngineeringIstanbul University‐CerrahpasaIstanbulTurkey
| | - Melike Kaya Karaaslan
- Department of Biomedical SciencesFaculty of Engineering, Kocaeli UniversityKocaeliTurkey
| | - Bekir Sıddık Binboğa Yarman
- Department of Electrical‐Electronics Engineering, Faculty of EngineeringIstanbul University‐CerrahpasaIstanbulTurkey
| |
Collapse
|
225
|
Negroni D, Carriero S, Passarella I, Siani A, Biondetti P, Pizzolante A, Saba L, Guzzardi G. Preliminary Analysis of the Effects of Ad26.COV2.S Vaccination on CT Findings and High Intensive Care Admission Rates of COVID-19 Patients. Tomography 2022; 8:2403-2410. [PMID: 36287798 PMCID: PMC9611738 DOI: 10.3390/tomography8050199] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/03/2022] [Revised: 09/19/2022] [Accepted: 09/20/2022] [Indexed: 11/16/2022] Open
Abstract
On 27 February 2021, the Food and Drug Administration(FDA) authorized the administration of the adenovirus-based Ad26.COV2-S vaccine (J&J-Janssen) for the prevention of COVID-19, a viral pandemic that, to date, has killed more than 5.5 million people. Performed during the early phase of the COVID-19 4th wave, this retrospective observational study aims to report the computerized tomography (CT) findings and intensive care unit admission rates of Ad26.COV2-S-vaccinated vs. unvaccinated COVID-19 patients. From the 1st to the 23rd of December 2021, all confirmed COVID-19 patients that had been subjected to chest non-contrast CT scan analysis were enrolled in the study. These were divided into Ad26.COV2.S-vaccinated (group 1) and unvaccinated patients (group 2). The RSNA severity score was calculated for each patient and correlated to CT findings and type of admission to a healthcare setting after CT-i.e., home care, ordinary hospitalization, sub-intensive care, and intensive care. Descriptive and inference statistical analyses were performed by comparing the data from the two groups. Data from a total of 71 patients were collected: 10 patients in group 1 (4M, 6F, mean age 63.5 years, SD ± 4.2) and 61 patients in group 2 (32M, 29F, mean age 64.7 years, SD ± 3.7). Statistical analysis showed lower values of RSNA severity in group 1 compared to group 2 (mean value 14.1 vs. 15.7, p = 0.009, respectively). Furthermore, vaccinated patients were less frequently admitted to both sub-intensive and high-intensive care units than group 2, with an odds ratio of 0.45 [95%CI (0.01; 3.92)]. Ad26.COV2.S vaccination protects from severe COVID-19 based on CT severity scores. As a result, Ad26.COV2.S-vaccinated COVID-19 patients are more frequently admitted to home in comparison with unvaccinated patients.
Collapse
Affiliation(s)
- Davide Negroni
- Department of Radiology, University of Piemonte Orientale, Piedmont, 28100 Novara, Italy
| | - Serena Carriero
- Department of Radiology, Fondazione IRCCS Ca’ Granda Ospedale Maggiore Policlinico, 20122 Milan, Italy
| | - Ilaria Passarella
- Departement of Internal Medicine, ASST Ovest Milanese Ospedale Fornaroli, 20013 Magenta, Italy
| | - Agnese Siani
- Department of Radiology, University of Piemonte Orientale, Piedmont, 28100 Novara, Italy
| | - Pierpaolo Biondetti
- Department of Radiology, Fondazione IRCCS Ca’ Granda Ospedale Maggiore Policlinico, 20122 Milan, Italy
| | - Antonio Pizzolante
- Department of Radiology, University of Piemonte Orientale, Piedmont, 28100 Novara, Italy
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria Cagliari, 09124 Polo di Monserrato, Italy
| | - Giuseppe Guzzardi
- Department of Radiology, University of Piemonte Orientale, Piedmont, 28100 Novara, Italy
| |
Collapse
|
226
|
Jangam E, Annavarapu CSR, Barreto AAD. A multi-class classification framework for disease screening and disease diagnosis of COVID-19 from chest X-ray images. MULTIMEDIA TOOLS AND APPLICATIONS 2022; 82:14367-14401. [PMID: 36157353 PMCID: PMC9490695 DOI: 10.1007/s11042-022-13710-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/14/2021] [Revised: 05/05/2022] [Accepted: 08/24/2022] [Indexed: 06/16/2023]
Abstract
To accurately diagnose multiple lung diseases from chest X-rays, the critical aspect is to identify lung diseases with high sensitivity and specificity. This study proposed a novel multi-class classification framework that minimises either false positives or false negatives that is useful in computer aided diagnosis or computer aided detection respectively. To minimise false positives or false negatives, we generated respective stacked ensemble from pre-trained models and fully connected layers using selection metric and systematic method. The diversity of base classifiers was based on diverse set of false positives or false negatives generated. The proposed multi-class framework was evaluated on two chest X-ray datasets, and the performance was compared with the existing models and base classifiers. Moreover, we used LIME (Local Interpretable Model-agnostic Explanations) to locate the regions focused by the multi-class classification framework.
Collapse
Affiliation(s)
- Ebenezer Jangam
- Department of Information Technology, Velagapudi Ramakrishna Siddhartha Engineering College, Vijayawada, Andhra Pradesh India
- Department of Computer Science Engineering, Indian Institute of Technology(ISM), Dhanbad, Jharkhand India
| | | | | |
Collapse
|
227
|
Liu XP, Yang X, Xiong M, Mao X, Jin X, Li Z, Zhou S, Chang H. Development and validation of chest CT-based imaging biomarkers for early stage COVID-19 screening. Front Public Health 2022; 10:1004117. [PMID: 36211676 PMCID: PMC9533142 DOI: 10.3389/fpubh.2022.1004117] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2022] [Accepted: 08/15/2022] [Indexed: 01/27/2023] Open
Abstract
Coronavirus Disease 2019 (COVID-19) is currently a global pandemic, and early screening is one of the key factors for COVID-19 control and treatment. Here, we developed and validated chest CT-based imaging biomarkers for COVID-19 patient screening from two independent hospitals with 419 patients. We identified the vasculature-like signals from CT images and found that, compared to healthy and community acquired pneumonia (CAP) patients, COVID-19 patients display a significantly higher abundance of these signals. Furthermore, unsupervised feature learning led to the discovery of clinical-relevant imaging biomarkers from the vasculature-like signals for accurate and sensitive COVID-19 screening that have been double-blindly validated in an independent hospital (sensitivity: 0.941, specificity: 0.920, AUC: 0.971, accuracy 0.931, F1 score: 0.929). Our findings could open a new avenue to assist screening of COVID-19 patients.
Collapse
Affiliation(s)
- Xiao-Ping Liu
- Department of Pathology, Zhongnan Hospital of Wuhan University, Wuhan, China
- Department of Urology, Zhongnan Hospital of Wuhan University, Wuhan, China
| | - Xu Yang
- Key Laboratory of Modern Toxicology of Ministry of Education, School of Public Health, Nanjing Medical University, Nanjing, China
| | - Miao Xiong
- Department of Radiology, Wuhan Third Hospital, Tongren Hospital of Wuhan University, Wuhan, China
| | - Xuanyu Mao
- Department of Emergency, Zhongnan Hospital of Wuhan University, Wuhan, China
| | - Xiaoqing Jin
- Department of Emergency, Zhongnan Hospital of Wuhan University, Wuhan, China
| | - Zhiqiang Li
- Department of Neurosurgery, Zhongnan Hospital of Wuhan University, Wuhan, China
| | - Shuang Zhou
- Hubei Province Hospital of Traditional Chinese Medicine, Affiliated Hospital of Hubei University of Traditional Chinese Medicine, Hubei Institute of Traditional Chinese Medicine, Wuhan, China
| | - Hang Chang
- Department of Emergency, Zhongnan Hospital of Wuhan University, Wuhan, China
| |
Collapse
|
228
|
Chen J, Li Y, Guo L, Zhou X, Zhu Y, He Q, Han H, Feng Q. Machine learning techniques for CT imaging diagnosis of novel coronavirus pneumonia: a review. Neural Comput Appl 2022; 36:1-19. [PMID: 36159188 PMCID: PMC9483435 DOI: 10.1007/s00521-022-07709-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2022] [Accepted: 08/04/2022] [Indexed: 11/20/2022]
Abstract
Since 2020, novel coronavirus pneumonia has been spreading rapidly around the world, bringing tremendous pressure on medical diagnosis and treatment for hospitals. Medical imaging methods, such as computed tomography (CT), play a crucial role in diagnosing and treating COVID-19. A large number of CT images (with large volume) are produced during the CT-based medical diagnosis. In such a situation, the diagnostic judgement by human eyes on the thousands of CT images is inefficient and time-consuming. Recently, in order to improve diagnostic efficiency, the machine learning technology is being widely used in computer-aided diagnosis and treatment systems (i.e., CT Imaging) to help doctors perform accurate analysis and provide them with effective diagnostic decision support. In this paper, we comprehensively review these frequently used machine learning methods applied in the CT Imaging Diagnosis for the COVID-19, discuss the machine learning-based applications from the various kinds of aspects including the image acquisition and pre-processing, image segmentation, quantitative analysis and diagnosis, and disease follow-up and prognosis. Moreover, we also discuss the limitations of the up-to-date machine learning technology in the context of CT imaging computer-aided diagnosis.
Collapse
Affiliation(s)
- Jingjing Chen
- Zhejiang University City College, Hangzhou, China
- Zhijiang College of Zhejiang University of Technology, Shaoxing, China
| | - Yixiao Li
- Faculty of Science, Zhejiang University of Technology, Hangzhou, China
| | - Lingling Guo
- College of Chemical Engineering, Zhejiang University of Technology, Hangzhou, China
| | - Xiaokang Zhou
- Faculty of Data Science, Shiga University, Hikone, Japan
- RIKEN Center for Advanced Intelligence Project, Tokyo, Japan
| | - Yihan Zhu
- College of Chemical Engineering, Zhejiang University of Technology, Hangzhou, China
| | - Qingfeng He
- School of Pharmacy, Fudan University, Shanghai, China
| | - Haijun Han
- School of Medicine, Zhejiang University City College, Hangzhou, China
| | - Qilong Feng
- College of Chemical Engineering, Zhejiang University of Technology, Hangzhou, China
| |
Collapse
|
229
|
Owais M, Baek NR, Park KR. DMDF-Net: Dual multiscale dilated fusion network for accurate segmentation of lesions related to COVID-19 in lung radiographic scans. EXPERT SYSTEMS WITH APPLICATIONS 2022; 202:117360. [PMID: 35529253 PMCID: PMC9057951 DOI: 10.1016/j.eswa.2022.117360] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/13/2021] [Revised: 01/24/2022] [Accepted: 04/25/2022] [Indexed: 05/14/2023]
Abstract
The recent disaster of COVID-19 has brought the whole world to the verge of devastation because of its highly transmissible nature. In this pandemic, radiographic imaging modalities, particularly, computed tomography (CT), have shown remarkable performance for the effective diagnosis of this virus. However, the diagnostic assessment of CT data is a human-dependent process that requires sufficient time by expert radiologists. Recent developments in artificial intelligence have substituted several personal diagnostic procedures with computer-aided diagnosis (CAD) methods that can make an effective diagnosis, even in real time. In response to COVID-19, various CAD methods have been developed in the literature, which can detect and localize infectious regions in chest CT images. However, most existing methods do not provide cross-data analysis, which is an essential measure for assessing the generality of a CAD method. A few studies have performed cross-data analysis in their methods. Nevertheless, these methods show limited results in real-world scenarios without addressing generality issues. Therefore, in this study, we attempt to address generality issues and propose a deep learning-based CAD solution for the diagnosis of COVID-19 lesions from chest CT images. We propose a dual multiscale dilated fusion network (DMDF-Net) for the robust segmentation of small lesions in a given CT image. The proposed network mainly utilizes the strength of multiscale deep features fusion inside the encoder and decoder modules in a mutually beneficial manner to achieve superior segmentation performance. Additional pre- and post-processing steps are introduced in the proposed method to address the generality issues and further improve the diagnostic performance. Mainly, the concept of post-region of interest (ROI) fusion is introduced in the post-processing step, which reduces the number of false-positives and provides a way to accurately quantify the infected area of lung. Consequently, the proposed framework outperforms various state-of-the-art methods by accomplishing superior infection segmentation results with an average Dice similarity coefficient of 75.7%, Intersection over Union of 67.22%, Average Precision of 69.92%, Sensitivity of 72.78%, Specificity of 99.79%, Enhance-Alignment Measure of 91.11%, and Mean Absolute Error of 0.026.
Collapse
Affiliation(s)
- Muhammad Owais
- Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, South Korea
| | - Na Rae Baek
- Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, South Korea
| | - Kang Ryoung Park
- Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, South Korea
| |
Collapse
|
230
|
Pramanik R, Dey S, Malakar S, Mirjalili S, Sarkar R. TOPSIS aided ensemble of CNN models for screening COVID-19 in chest X-ray images. Sci Rep 2022; 12:15409. [PMID: 36104401 PMCID: PMC9471038 DOI: 10.1038/s41598-022-18463-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2021] [Accepted: 08/12/2022] [Indexed: 11/23/2022] Open
Abstract
The novel coronavirus (COVID-19), has undoubtedly imprinted our lives with its deadly impact. Early testing with isolation of the individual is the best possible way to curb the spread of this deadly virus. Computer aided diagnosis (CAD) provides an alternative and cheap option for screening of the said virus. In this paper, we propose a convolution neural network (CNN)-based CAD method for COVID-19 and pneumonia detection from chest X-ray images. We consider three input types for three identical base classifiers. To capture maximum possible complementary features, we consider the original RGB image, Red channel image and the original image stacked with Robert's edge information. After that we develop an ensemble strategy based on the technique for order preference by similarity to an ideal solution (TOPSIS) to aggregate the outcomes of base classifiers. The overall framework, called TOPCONet, is very light in comparison with standard CNN models in terms of the number of trainable parameters required. TOPCONet achieves state-of-the-art results when evaluated on the three publicly available datasets: (1) IEEE COVID-19 dataset + Kaggle Pneumonia Dataset, (2) Kaggle Radiography dataset and (3) COVIDx.
Collapse
|
231
|
Pellegrino F, Carnevale A, Bisi R, Cavedagna D, Reverberi R, Uccelli L, Leprotti S, Giganti M. Best Practices on Radiology Department Workflow: Tips from the Impact of the COVID-19 Lockdown on an Italian University Hospital. Healthcare (Basel) 2022; 10:healthcare10091771. [PMID: 36141383 PMCID: PMC9498676 DOI: 10.3390/healthcare10091771] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2022] [Revised: 09/11/2022] [Accepted: 09/12/2022] [Indexed: 12/02/2022] Open
Abstract
Purpose: The workload of the radiology department (RD) of a university hospital in northern Italy dramatically changed during the COVID-19 outbreak. The restrictive measures of the COVID-19 pandemic lockdown influenced the use of radiological services and particularly in the emergency department (ED). Methods: Data on diagnostic services from March 2020 to May 2020 were retrospectively collected and analysed in aggregate form and compared with those of the same timeframe in the previous year. Data were sorted by patient type in the following categories: inpatients, outpatients, and ED patients; the latter divided in “traumatic” and “not traumatic” cases. Results: Compared to 2019, 6449 fewer patients (−32.6%) were assisted in the RD. This decrease was more pronounced for the emergency radiology unit (ERU) (−41%) compared to the general radiology unit (−25.7%). The proportion of investigations performed for trauma appeared to decrease significantly from 14.8% to 12.5% during the COVID-19 emergency (p < 0.001). Similarly, the proportion of assisted traumatic patients decreased from 16.6% to 12.5% (p < 0.001). The number of emergency patients assisted by the RD was significantly reduced from 45% during routine activity to 39.4% in the COVID-19 outbreak (p < 0.001). Conclusion: The COVID-19 outbreak had a tremendous impact on all radiology activities. We documented a drastic reduction in total imaging volume compared to 2019 because of both the pandemic and the lockdown. In this context, investigations performed for trauma showed a substantial decrease.
Collapse
Affiliation(s)
- Fabio Pellegrino
- Department of Translational Medicine, University of Ferrara, 44124 Ferrara, Italy
- Correspondence:
| | - Aldo Carnevale
- Department of Translational Medicine, University of Ferrara, 44124 Ferrara, Italy
| | - Riccardo Bisi
- Department of Translational Medicine, University of Ferrara, 44124 Ferrara, Italy
| | - Davide Cavedagna
- Department of Radiology, Sant’Anna University Hospital Ferrara, 44124 Ferrara, Italy
| | - Roberto Reverberi
- Blood Transfusion Service, Azienda Ospedaliera Universitaria di Ferrara, 44124 Ferrara, Italy
| | - Licia Uccelli
- Department of Translational Medicine, University of Ferrara, 44124 Ferrara, Italy
| | - Stefano Leprotti
- Department of Radiology, Sant’Anna University Hospital Ferrara, 44124 Ferrara, Italy
| | - Melchiore Giganti
- Department of Translational Medicine, University of Ferrara, 44124 Ferrara, Italy
| |
Collapse
|
232
|
A semi-supervised learning approach for COVID-19 detection from chest CT scans. Neurocomputing 2022; 503:314-324. [PMID: 35765410 PMCID: PMC9221925 DOI: 10.1016/j.neucom.2022.06.076] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/23/2022] [Revised: 05/11/2022] [Accepted: 06/18/2022] [Indexed: 01/17/2023]
Abstract
COVID-19 has spread rapidly all over the world and has infected more than 200 countries and regions. Early screening of suspected infected patients is essential for preventing and combating COVID-19. Computed Tomography (CT) is a fast and efficient tool which can quickly provide chest scan results. To reduce the burden on doctors of reading CTs, in this article, a high precision diagnosis algorithm of COVID-19 from chest CTs is designed for intelligent diagnosis. A semi-supervised learning approach is developed to solve the problem when only small amount of labelled data is available. While following the MixMatch rules to conduct sophisticated data augmentation, we introduce a model training technique to reduce the risk of model over-fitting. At the same time, a new data enhancement method is proposed to modify the regularization term in MixMatch. To further enhance the generalization of the model, a convolutional neural network based on an attention mechanism is then developed that enables to extract multi-scale features on CT scans. The proposed algorithm is evaluated on an independent CT dataset of the chest from COVID-19 and achieves the area under the receiver operating characteristic curve (AUC) value of 0.932, accuracy of 90.1%, sensitivity of 91.4%, specificity of 88.9%, and F1-score of 89.9%. The results show that the proposed algorithm can accurately diagnose whether a chest CT belongs to a positive or negative indication of COVID-19, and can help doctors to diagnose rapidly in the early stages of a COVID-19 outbreak.
Collapse
|
233
|
Wang G, Guo S, Han L, Cekderi AB. Two-dimensional reciprocal cross entropy multi-threshold combined with improved firefly algorithm for lung parenchyma segmentation of COVID-19 CT image. Biomed Signal Process Control 2022; 78:103933. [PMID: 35774106 PMCID: PMC9217142 DOI: 10.1016/j.bspc.2022.103933] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2022] [Revised: 05/28/2022] [Accepted: 06/18/2022] [Indexed: 12/01/2022]
Abstract
The lesions of COVID-19 CT image show various kinds of ground-glass opacity and consolidation, which are distributed in left lung, right lung or both lungs. The lung lobes are uneven and it have similar gray value to the surrounding arteries, veins, and bronchi. The lesions of COVID-19 have different sizes and shapes in different periods. Accurate segmentation of lung parenchyma in CT image is a key step in COVID-19 detection and diagnosis. Aiming at the unideal effect of traditional image segmentation methods on lung parenchyma segmentation in CT images, a lung parenchyma segmentation method based on two-dimensional reciprocal cross entropy multi-threshold combined with improved firefly algorithm is proposed. Firstly, the optimal threshold method is used to realize the initial segmentation of the lung, so that the segmentation threshold can change adaptively according to the detailed information of lung lobes, trachea, bronchi and ground-glass opacity. Then the lung parenchyma is further processed to obtain the lung parenchyma template, and then the defective template is repaired combined with the improved Freeman chain code and Bezier curve. Finally, the lung parenchyma is extracted by multiplying the template with the lung CT image. The accuracy of lung parenchyma segmentation has been improved in the contrast clarity of CT image and the consistency of lung parenchyma regional features, with an average segmentation accuracy rate of 97.4%. The experimental results show that for COVID-19 and suspected cases, the method has an ideal segmentation effect, and it has good accuracy and robustness.
Collapse
Affiliation(s)
- Guowei Wang
- State Key Laboratory of Intelligent Control and Decision of Complex Systems, School of Automation, Beijing Institute of Technology, Beijing 100081, China
| | - Shuli Guo
- State Key Laboratory of Intelligent Control and Decision of Complex Systems, School of Automation, Beijing Institute of Technology, Beijing 100081, China
| | - Lina Han
- Department of Cardiology, The Second Medical Center, National Clinical Research Center for Geriatric Diseases, Chinese PLA General Hospital, Beijing, China
| | - Anil Baris Cekderi
- State Key Laboratory of Intelligent Control and Decision of Complex Systems, School of Automation, Beijing Institute of Technology, Beijing 100081, China
| |
Collapse
|
234
|
Aslan M. CoviDetNet: A new COVID-19 diagnostic system based on deep features of chest x-ray. INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2022; 32:1447-1463. [PMID: 35935665 PMCID: PMC9347592 DOI: 10.1002/ima.22771] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/07/2021] [Revised: 05/11/2022] [Accepted: 05/23/2022] [Indexed: 06/15/2023]
Abstract
COVID-19 has emerged as a global pandemic affecting the world, and its adverse effects on society still continue. So far, about 243.57 million people have been diagnosed with COVID-19, of which about 4.94 million have died. In this study, a new model, called COVIDetNet, is proposed for automated COVID-19 detection. A lightweight CNN architecture trained instead of the popular and pretrained convolution neural network (CNN) models such as VGG16, VGG19, AlexNet, ResNet50, ResNet100, and MobileNetV2 from scratch with chest x-ray (CXR) images was designed. A new feature set was created by concatenating the features of all layers of the designed CNN architecture. Then, the most efficient features chosen among the features concatenating with the Relief feature selection algorithm were classified using the support vector machine (SVM) method. The experimental works were carried out on a public COVID-19 CXR database. Experimental results demonstrated 99.24% accuracy, 99.60% specificity, 99.39% sensitivity, 99.04% precision, and an F1 score of 99.21%. Also, in comparison to AlexNet and VGG16 models, the deep feature extraction durations were reduced by approximately 6-fold and 38-fold, respectively. The COVIDetNet model provided a higher accuracy score than state-of-the-art models when compared to multi-class research studies. Overall, the proposed model will be beneficial for specialist medical staff to detect COVID-19 cases, as it provides faster and higher accuracy than existing CXR-based approaches.
Collapse
Affiliation(s)
- Muzaffer Aslan
- Electrical‐Electronics Engineering DepartmentBingol UniversityBingolTurkey
| |
Collapse
|
235
|
Cheng J, Zhao W, Liu J, Xie X, Wu S, Liu L, Yue H, Li J, Wang J, Liu J. Automated Diagnosis of COVID-19 Using Deep Supervised Autoencoder With Multi-View Features From CT Images. IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2022; 19:2723-2736. [PMID: 34351863 PMCID: PMC9647725 DOI: 10.1109/tcbb.2021.3102584] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/03/2023]
Abstract
Accurate and rapid diagnosis of coronavirus disease 2019 (COVID-19) from chest CT scans is of great importance and urgency during the worldwide outbreak. However, radiologists have to distinguish COVID-19 pneumonia from other pneumonia in a large number of CT scans, which is tedious and inefficient. Thus, it is urgently and clinically needed to develop an efficient and accurate diagnostic tool to help radiologists to fulfill the difficult task. In this study, we proposed a deep supervised autoencoder (DSAE) framework to automatically identify COVID-19 using multi-view features extracted from CT images. To fully explore features characterizing CT images from different frequency domains, DSAE was proposed to learn the latent representation by multi-task learning. The proposal was designed to both encode valuable information from different frequency features and construct a compact class structure for separability. To achieve this, we designed a multi-task loss function, which consists of a supervised loss and a reconstruction loss. Our proposed method was evaluated on a newly collected dataset of 787 subjects including COVID-19 pneumonia patients, other pneumonia patients, and normal subjects without abnormal CT findings. Extensive experimental results demonstrated that our proposed method achieved encouraging diagnostic performance and may have potential clinical application for the diagnosis of COVID-19.
Collapse
|
236
|
SARS-CoV-2 infection: Pathogenesis, Immune Responses, Diagnosis. JOURNAL OF PURE AND APPLIED MICROBIOLOGY 2022. [DOI: 10.22207/jpam.16.3.20] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/08/2023] Open
Abstract
COVID-19 has emerged as the most alarming infection of the present time instigated by the virus SARS-CoV-2. In spite of advanced research technologies, the exact pathophysiology and treatment of the condition still need to be explored. However, SARS-CoV-2 has several structural and functional similarities that resemble SARS-CoV and MERS-CoV which may be beneficial in exploring the possible treatment and diagnostic strategies for SARS-CoV-2. This review discusses the pathogen phenotype, genotype, replication, pathophysiology, elicited immune response and emerging variants of SARS-CoV-2 and their similarities with other similar viruses. SARS-CoV-2 infection is detected by a number of diagnostics techniques, their advantages and limitations are also discussed in detail. The review also focuses on nanotechnology-based easy and fast detection of SARS-CoV-2 infection. Various pathways which might play a vital role during SARS-CoV-2 infection have been elaborately discussed since immune response plays a major role during viral infections.
Collapse
|
237
|
Li J, Frenette C, Loo VG. Diagnostic yield of serial SARS-CoV-2 testing in hospitalized patients. JOURNAL OF THE ASSOCIATION OF MEDICAL MICROBIOLOGY AND INFECTIOUS DISEASE CANADA = JOURNAL OFFICIEL DE L'ASSOCIATION POUR LA MICROBIOLOGIE MEDICALE ET L'INFECTIOLOGIE CANADA 2022; 7:181-185. [PMID: 36337610 PMCID: PMC9629723 DOI: 10.3138/jammi-2022-0003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/29/2022] [Revised: 06/05/2022] [Accepted: 06/06/2022] [Indexed: 06/16/2023]
Abstract
BACKGROUND The detection rate of SARS-CoV-2 by polymerase chain reaction (PCR) varies depending on the time since exposure and is highest around the time of symptom onset. It is conceivable that patients who are incubating SARS-CoV-2 may screen negative at admission and develop transmissible but undetected asymptomatic or pre-symptomatic disease while in hospital. The incidence of COVID-19 in Montreal, Canada started to increase in December 2020. In anticipation of a much larger rise after the holiday period, the McGill University Health Centre implemented serial SARS-CoV-2 testing for all admitted patients on day 5 and 10 after admission, to evaluate the clinical utility of serial SARS-CoV-2 testing among patients who test negative on admission screening. METHODS We retrospectively analyzed the diagnostic yield of SARS-CoV-2 serial testing for patients admitted between January 4, 2021 and April 30, 2021. RESULTS A total of 1,505 patients underwent serial testing at day 5 and 841 patients underwent serial testing at day 10. Only 10 patients were positive on serial testing at day 5 and only 12 patients were positive on serial testing at day 10, for a yield at day 5 and day 10 of 0.7% and 1.4%, respectively. CONCLUSIONS The yield of serial SARS-CoV-2 testing was 0.7% at day 5 and 1.4% at day 10. We found that the yield of serial testing was higher when the community incidence was higher and could be considered in this situation. Policies which target repeat testing towards symptomatic or exposed individuals appear to be effective in identifying those with a positive test while admitted but testing negative upon admission.
Collapse
Affiliation(s)
- Jeremy Li
- Faculty of Medicine and Health Sciences, McGill University, Montreal, Quebec, Canada
| | - Charles Frenette
- Faculty of Medicine and Health Sciences, McGill University, Montreal, Quebec, Canada
- Division of Infectious Diseases, McGill University Health Centre, Montreal, Quebec, Canada
| | - Vivian G Loo
- Faculty of Medicine and Health Sciences, McGill University, Montreal, Quebec, Canada
- Division of Infectious Diseases, McGill University Health Centre, Montreal, Quebec, Canada
| |
Collapse
|
238
|
Özdemir Ö, Sönmez EB. Attention mechanism and mixup data augmentation for classification of COVID-19 Computed Tomography images. JOURNAL OF KING SAUD UNIVERSITY. COMPUTER AND INFORMATION SCIENCES 2022; 34:6199-6207. [PMID: 38620953 PMCID: PMC8280602 DOI: 10.1016/j.jksuci.2021.07.005] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/22/2021] [Revised: 07/01/2021] [Accepted: 07/07/2021] [Indexed: 12/21/2022]
Abstract
The Coronavirus disease is quickly spreading all over the world and the emergency situation is still out of control. Latest achievements of deep learning algorithms suggest the use of deep Convolutional Neural Network to implement a computer-aided diagnostic system for automatic classification of COVID-19 CT images. In this paper, we propose to employ a feature-wise attention layer in order to enhance the discriminative features obtained by convolutional networks. Moreover, the original performance of the network has been improved using the mixup data augmentation technique. This work compares the proposed attention-based model against the stacked attention networks, and traditional versus mixup data augmentation approaches. We deduced that feature-wise attention extension, while outperforming the stacked attention variants, achieves remarkable improvements over the baseline convolutional neural networks. That is, ResNet50 architecture extended with a feature-wise attention layer obtained 95.57% accuracy score, which, to best of our knowledge, fixes the state-of-the-art in the challenging COVID-CT dataset.
Collapse
Affiliation(s)
- Özgür Özdemir
- Computer Engineering Department, Istanbul Bilgi University, Turkey
| | | |
Collapse
|
239
|
Oğuz Ç, Yağanoğlu M. Detection of COVID-19 using deep learning techniques and classification methods. Inf Process Manag 2022; 59:103025. [PMID: 35821878 PMCID: PMC9263717 DOI: 10.1016/j.ipm.2022.103025] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2021] [Revised: 07/01/2022] [Accepted: 07/02/2022] [Indexed: 01/07/2023]
Abstract
Since the patient is not quarantined during the conclusion of the Polymerase Chain Reaction (PCR) test used in the diagnosis of COVID-19, the disease continues to spread. In this study, it was aimed to reduce the duration and amount of transmission of the disease by shortening the diagnosis time of COVID-19 patients with the use of Computed Tomography (CT). In addition, it is aimed to provide a decision support system to radiologists in the diagnosis of COVID-19. In this study, deep features were extracted with deep learning models such as ResNet-50, ResNet-101, AlexNet, Vgg-16, Vgg-19, GoogLeNet, SqueezeNet, Xception on 1345 CT images obtained from the radiography database of Siirt Education and Research Hospital. These deep features are given to classification methods such as Support Vector Machine (SVM), k Nearest Neighbor (kNN), Random Forest (RF), Decision Trees (DT), Naive Bayes (NB), and their performance is evaluated with test images. Accuracy value, F1-score and ROC curve were considered as success criteria. According to the data obtained as a result of the application, the best performance was obtained with ResNet-50 and SVM method. The accuracy was 96.296%, the F1-score was 95.868%, and the AUC value was 0.9821. The deep learning model and classification method examined in this study and found to be high performance can be used as an auxiliary decision support system by preventing unnecessary tests for COVID-19 disease.
Collapse
Affiliation(s)
- Çinare Oğuz
- Department of Computer Engineering, Faculty of Engineering, Ataturk University, Erzurum, Turkey
| | - Mete Yağanoğlu
- Department of Computer Engineering, Faculty of Engineering, Ataturk University, Erzurum, Turkey
| |
Collapse
|
240
|
Khalifa AM, Nouh FA, Elshaari FA. Clinical characteristics and outcomes among patients with COVID-19: A single-center retrospective observational study from Marj, Libya. Saudi Med J 2022; 43:1013-1019. [PMID: 36104061 PMCID: PMC9987663 DOI: 10.15537/smj.2022.43.9.20220343] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2022] [Accepted: 08/08/2022] [Indexed: 11/16/2022] Open
Abstract
OBJECTIVES To describe the clinical characteristics and the contributing factors potentially associated with the poorer outcome in Libyan COVID-19 ICU patients. METHODS The present work is a retrospective, single-center study, which included 94 COVID-19 patients admitted to the Isolation Department at Marj Hospital from August 21st, 2020 till April 30th, 2021. The patients' data, including their medical history, clinical manifestations, radiological imaging, and laboratory findings, were obtained from the hospital records. RESULTS A higher proportion of the admitted patients were males. The patients' mean age was 68.29 ± 13.64. The patients came with varying symptoms, but most commonly they were affected by dyspnea, fever, cough, and fatigue. Diabetes was the most common underlying comorbidity; nonetheless, other chronic diseases like hypertension, cardiovascular disease, renal disease, and lung diseases individually affected a significant proportion of patients. Although there was no effect of gender on patients' outcomes, age had a significant influence on the disease consequences. CONCLUSION There was a strong effect of age on ICU admission and patients' surviving the illness. Diabetes was the most common underlying comorbid disease in COVID-19 patients. On admission time, inflammatory markers such as CRP, D-dimer, serum ferritin, and LDH, in common, were the most important indicators of poorer prognosis. Male gender, comorbidity, and symptomology adversely affected the rate of admission but not the patient survival.
Collapse
Affiliation(s)
- Aimen M. Khalifa
- From the Department of Medicine (Khalifa), Faculty of Medicine, University of Benghazi - Marj; from the Department of Biochemistry (Nouh, Elshaari), Faculty of Medicine, University of Benghazi; and from the Libyan Center for Biotechnology Research (Elshaari), Benghazi, Libya.
| | - Fatimah A. Nouh
- From the Department of Medicine (Khalifa), Faculty of Medicine, University of Benghazi - Marj; from the Department of Biochemistry (Nouh, Elshaari), Faculty of Medicine, University of Benghazi; and from the Libyan Center for Biotechnology Research (Elshaari), Benghazi, Libya.
| | - Farag A. Elshaari
- From the Department of Medicine (Khalifa), Faculty of Medicine, University of Benghazi - Marj; from the Department of Biochemistry (Nouh, Elshaari), Faculty of Medicine, University of Benghazi; and from the Libyan Center for Biotechnology Research (Elshaari), Benghazi, Libya.
| |
Collapse
|
241
|
Polat H. A modified DeepLabV3+ based semantic segmentation of chest computed tomography images for COVID-19 lung infections. INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2022; 32:1481-1495. [PMID: 35941930 PMCID: PMC9349869 DOI: 10.1002/ima.22772] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/05/2022] [Revised: 04/19/2022] [Accepted: 05/23/2022] [Indexed: 06/15/2023]
Abstract
Coronavirus disease (COVID-19) affects the lives of billions of people worldwide and has destructive impacts on daily life routines, the global economy, and public health. Early diagnosis and quantification of COVID-19 infection have a vital role in improving treatment outcomes and interrupting transmission. For this purpose, advances in medical imaging techniques like computed tomography (CT) scans offer great potential as an alternative to RT-PCR assay. CT scans enable a better understanding of infection morphology and tracking of lesion boundaries. Since manual analysis of CT can be extremely tedious and time-consuming, robust automated image segmentation is necessary for clinical diagnosis and decision support. This paper proposes an efficient segmentation framework based on the modified DeepLabV3+ using lower atrous rates in the Atrous Spatial Pyramid Pooling (ASPP) module. The lower atrous rates make receptive small to capture intricate morphological details. The encoder part of the framework utilizes a pre-trained residual network based on dilated convolutions for optimum resolution of feature maps. In order to evaluate the robustness of the modified model, a comprehensive comparison with other state-of-the-art segmentation methods was also performed. The experiments were carried out using a fivefold cross-validation technique on a publicly available database containing 100 single-slice CT scans from >40 patients with COVID-19. The modified DeepLabV3+ achieved good segmentation performance using around 43.9 M parameters. The lower atrous rates in the ASPP module improved segmentation performance. After fivefold cross-validation, the framework achieved an overall Dice similarity coefficient score of 0.881. The results demonstrate that several minor modifications to the DeepLabV3+ pipeline can provide robust solutions for improving segmentation performance and hardware implementation.
Collapse
Affiliation(s)
- Hasan Polat
- Department of Electrical and EnergyBingol UniversityBingölTurkey
| |
Collapse
|
242
|
Gholamiankhah F, Mostafapour S, Abdi Goushbolagh N, Shojaerazavi S, Layegh P, Tabatabaei SM, Arabi H. Automated Lung Segmentation from Computed Tomography Images of Normal and COVID-19 Pneumonia Patients. IRANIAN JOURNAL OF MEDICAL SCIENCES 2022; 47:440-449. [PMID: 36117575 PMCID: PMC9445870 DOI: 10.30476/ijms.2022.90791.2178] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/24/2021] [Revised: 10/01/2021] [Accepted: 12/10/2021] [Indexed: 11/30/2022]
Abstract
Background Automated image segmentation is an essential step in quantitative image analysis. This study assesses the performance of a deep learning-based model for lung segmentation from computed tomography (CT) images of normal and COVID-19 patients. Methods A descriptive-analytical study was conducted from December 2020 to April 2021 on the CT images of patients from various educational hospitals affiliated with Mashhad University of Medical Sciences (Mashhad, Iran). Of the selected images and corresponding lung masks of 1,200 confirmed COVID-19 patients, 1,080 were used to train a residual neural network. The performance of the residual network (ResNet) model was evaluated on two distinct external test datasets, namely the remaining 120 COVID-19 and 120 normal patients. Different evaluation metrics such as Dice similarity coefficient (DSC), mean absolute error (MAE), relative mean Hounsfield unit (HU) difference, and relative volume difference were calculated to assess the accuracy of the predicted lung masks. The Mann-Whitney U test was used to assess the difference between the corresponding values in the normal and COVID-19 patients. P<0.05 was considered statistically significant. Results The ResNet model achieved a DSC of 0.980 and 0.971 and a relative mean HU difference of -2.679% and -4.403% for the normal and COVID-19 patients, respectively. Comparable performance in lung segmentation of normal and COVID-19 patients indicated the model's accuracy for identifying lung tissue in the presence of COVID-19-associated infections. Although a slightly better performance was observed in normal patients. Conclusion The ResNet model provides an accurate and reliable automated lung segmentation of COVID-19 infected lung tissue.A preprint version of this article was published on arXiv before formal peer review (https://arxiv.org/abs/2104.02042).
Collapse
Affiliation(s)
- Faeze Gholamiankhah
- Department of Medical Physics, School of Medicine, Shahid Sadoughi University of Medical Sciences, Yazd, Iran
| | - Samaneh Mostafapour
- Department of Radiology Technology, School of Paramedical Sciences, Mashhad University of Sciences, Yazd, Iran
| | - Nouraddin Abdi Goushbolagh
- Department of Medical Physics, School of Medicine, Shahid Sadoughi University of Medical Sciences, Yazd, Iran
| | - Seyedjafar Shojaerazavi
- Department of Cardiology, Ghaem Hospital, Mashhad University of Medical Sciences, Mashhad, Iran
| | - Parvaneh Layegh
- Department of Radiology, School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
| | - Seyyed Mohammad Tabatabaei
- Department of Medical Informatics, School of Medicine, Mashhad University of Medical Sciences, Mashhad, Iran
- Clinical Research Development Unit, Imam Reza Hospital, Mashhad University of Medical Sciences, Mashhad, Iran
| | - Hossein Arabi
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211 Geneva 4, Switzerland
| |
Collapse
|
243
|
Ord AA, Zamparini J, Lorentz L, Ranchod A, Moodley H. A study of the chest imaging findings of adult patients with COVID-19 on admission to a tertiary hospital in Johannesburg, South Africa. S Afr J Infect Dis 2022; 37:449. [PMID: 36092372 PMCID: PMC9452920 DOI: 10.4102/sajid.v37i1.449] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2022] [Accepted: 07/10/2022] [Indexed: 11/17/2022] Open
Abstract
Background South Africa has experienced multiple waves of the coronavirus disease 2019 (COVID-19) with little research documenting chest imaging features in an human immunodeficiency virus (HIV) and tuberculosis (TB) endemic region. Objectives Describe the chest imaging features, demographics and clinical characteristics of COVID-19 in an urban population. Method Retrospective, cross-sectional, review of chest radiographs and computed tomographies (CTs) of adults admitted to a tertiary hospital with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection, between 01 May 2020 and 30 June 2020. Imaging was reviewed by three radiologists. Clinical parameters and laboratory data were analysed. Results A total of 113 adult patients with a mean age of 46 years and 10 months were included. A total of 113 chest radiographs and six CTs were read. Nineteen patients were HIV-positive (16.8%), 40 were hypertensive and diabetic (35.4%), respectively, and one had TB (0.9%). Common symptoms included cough (n = 69; 61.6%), dyspnoea (n = 60; 53.1%) and fever (n = 46; 40.7%). Lower zone predominant ground glass opacities (58.4%) and consolidation (29.2%) were most frequent on chest radiographs. The right lower lobe was most involved (46.9% ground glass opacities and 17.7% consolidation), with relative sparing of the left upper lobe. Bilateral ground glass opacities (66.7%) were most common on CT. Among the HIV-positive, ground glass opacities and consolidation were less common than in HIV-negative or unknown patients (p = 0.037 and p = 0.05, respectively). Conclusion COVID-19 in South Africa has similar chest imaging findings to those documented globally, with some differences between HIV-positive and HIV-negative or unknown patients. The authors corroborate relative sparing of the left upper lobe; however, further research is required to validate this currently unique local finding.
Collapse
Affiliation(s)
- Ashleigh A Ord
- Department of Diagnostic Radiology, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa
| | - Jarrod Zamparini
- Department of Internal Medicine, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa
- Department of Internal Medicine, Charlotte Maxeke Johannesburg Academic Hospital, Johannesburg, South Africa
| | - Liam Lorentz
- Department of Radiology, Capital Radiology, Pretoria, South Africa
| | - Ashesh Ranchod
- Department of Diagnostic Radiology, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa
- Department of Radiology, NRS Incorporated Netcare N17 Private Hospital, Springs, South Africa
| | - Halvani Moodley
- Department of Diagnostic Radiology, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa
- Department of Diagnostic Radiology, Charlotte Maxeke Johannesburg Academic Hospital, Johannesburg, South Africa
| |
Collapse
|
244
|
Sarv Ahrabi S, Momenzadeh A, Baccarelli E, Scarpiniti M, Piazzo L. How much BiGAN and CycleGAN-learned hidden features are effective for COVID-19 detection from CT images? A comparative study. THE JOURNAL OF SUPERCOMPUTING 2022; 79:2850-2881. [PMID: 36042937 PMCID: PMC9411851 DOI: 10.1007/s11227-022-04775-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Accepted: 08/10/2022] [Indexed: 06/15/2023]
Abstract
Bidirectional generative adversarial networks (BiGANs) and cycle generative adversarial networks (CycleGANs) are two emerging machine learning models that, up to now, have been used as generative models, i.e., to generate output data sampled from a target probability distribution. However, these models are also equipped with encoding modules, which, after weakly supervised training, could be, in principle, exploited for the extraction of hidden features from the input data. At the present time, how these extracted features could be effectively exploited for classification tasks is still an unexplored field. Hence, motivated by this consideration, in this paper, we develop and numerically test the performance of a novel inference engine that relies on the exploitation of BiGAN and CycleGAN-learned hidden features for the detection of COVID-19 disease from other lung diseases in computer tomography (CT) scans. In this respect, the main contributions of the paper are twofold. First, we develop a kernel density estimation (KDE)-based inference method, which, in the training phase, leverages the hidden features extracted by BiGANs and CycleGANs for estimating the (a priori unknown) probability density function (PDF) of the CT scans of COVID-19 patients and, then, in the inference phase, uses it as a target COVID-PDF for the detection of COVID diseases. As a second major contribution, we numerically evaluate and compare the classification accuracies of the implemented BiGAN and CycleGAN models against the ones of some state-of-the-art methods, which rely on the unsupervised training of convolutional autoencoders (CAEs) for attaining feature extraction. The performance comparisons are carried out by considering a spectrum of different training loss functions and distance metrics. The obtained classification accuracies of the proposed CycleGAN-based (resp., BiGAN-based) models outperform the corresponding ones of the considered benchmark CAE-based models of about 16% (resp., 14%).
Collapse
Affiliation(s)
- Sima Sarv Ahrabi
- Department of Information Engineering, Electronics and Telecommunications, Sapienza University or Rome, Via Eudossiana, 18, 00184 Roma, Italy
| | - Alireza Momenzadeh
- Department of Information Engineering, Electronics and Telecommunications, Sapienza University or Rome, Via Eudossiana, 18, 00184 Roma, Italy
| | - Enzo Baccarelli
- Department of Information Engineering, Electronics and Telecommunications, Sapienza University or Rome, Via Eudossiana, 18, 00184 Roma, Italy
| | - Michele Scarpiniti
- Department of Information Engineering, Electronics and Telecommunications, Sapienza University or Rome, Via Eudossiana, 18, 00184 Roma, Italy
| | - Lorenzo Piazzo
- Department of Information Engineering, Electronics and Telecommunications, Sapienza University or Rome, Via Eudossiana, 18, 00184 Roma, Italy
| |
Collapse
|
245
|
Salehi M, Ardekani MA, Taramsari AB, Ghaffari H, Haghparast M. Automated deep learning-based segmentation of COVID-19 lesions from chest computed tomography images. Pol J Radiol 2022; 87:e478-e486. [PMID: 36091652 PMCID: PMC9453472 DOI: 10.5114/pjr.2022.119027] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2022] [Accepted: 03/30/2022] [Indexed: 11/30/2022] Open
Abstract
Purpose The novel coronavirus COVID-19, which spread globally in late December 2019, is a global health crisis. Chest computed tomography (CT) has played a pivotal role in providing useful information for clinicians to detect COVID-19. However, segmenting COVID-19-infected regions from chest CT results is challenging. Therefore, it is desirable to develop an efficient tool for automated segmentation of COVID-19 lesions using chest CT. Hence, we aimed to propose 2D deep-learning algorithms to automatically segment COVID-19-infected regions from chest CT slices and evaluate their performance. Material and methods Herein, 3 known deep learning networks: U-Net, U-Net++, and Res-Unet, were trained from scratch for automated segmenting of COVID-19 lesions using chest CT images. The dataset consists of 20 labelled COVID-19 chest CT volumes. A total of 2112 images were used. The dataset was split into 80% for training and validation and 20% for testing the proposed models. Segmentation performance was assessed using Dice similarity coefficient, average symmetric surface distance (ASSD), mean absolute error (MAE), sensitivity, specificity, and precision. Results All proposed models achieved good performance for COVID-19 lesion segmentation. Compared with Res-Unet, the U-Net and U-Net++ models provided better results, with a mean Dice value of 85.0%. Compared with all models, U-Net gained the highest segmentation performance, with 86.0% sensitivity and 2.22 mm ASSD. The U-Net model obtained 1%, 2%, and 0.66 mm improvement over the Res-Unet model in the Dice, sensitivity, and ASSD, respectively. Compared with Res-Unet, U-Net++ achieved 1%, 2%, 0.1 mm, and 0.23 mm improvement in the Dice, sensitivity, ASSD, and MAE, respectively. Conclusions Our data indicated that the proposed models achieve an average Dice value greater than 84.0%. Two-dimensional deep learning models were able to accurately segment COVID-19 lesions from chest CT images, assisting the radiologists in faster screening and quantification of the lesion regions for further treatment. Nevertheless, further studies will be required to evaluate the clinical performance and robustness of the proposed models for COVID-19 semantic segmentation.
Collapse
Affiliation(s)
- Mohammad Salehi
- Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Mahdieh Afkhami Ardekani
- Clinical Research Development Center, Shahid Mohammadi Hospital, Hormozgan University of Medical Sciences, Bandar-Abbas, Iran
- Department of Radiology, Faculty of Paramedicine, Hormozgan University of Medical Sciences, Bandar-Abbas, Iran
| | | | - Hamed Ghaffari
- Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Mohammad Haghparast
- Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
- Department of Radiology, Faculty of Paramedicine, Hormozgan University of Medical Sciences, Bandar-Abbas, Iran
| |
Collapse
|
246
|
Smadi AA, Abugabah A, Al-Smadi AM, Almotairi S. SEL-COVIDNET: An intelligent application for the diagnosis of COVID-19 from chest X-rays and CT-scans. INFORMATICS IN MEDICINE UNLOCKED 2022; 32:101059. [PMID: 36033909 PMCID: PMC9398554 DOI: 10.1016/j.imu.2022.101059] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/18/2022] [Revised: 08/17/2022] [Accepted: 08/17/2022] [Indexed: 11/06/2022] Open
Abstract
COVID-19 detection from medical imaging is a difficult challenge that has piqued the interest of experts worldwide. Chest X-rays and computed tomography (CT) scanning are the essential imaging modalities for diagnosing COVID-19. All researchers focus their efforts on developing viable methods and rapid treatment procedures for this pandemic. Fast and accurate automated detection approaches have been devised to alleviate the need for medical professionals. Deep Learning (DL) technologies have successfully recognized COVID-19 situations. This paper proposes a developed set of nine deep learning models for diagnosing COVID-19 based on transfer learning and implementation in a novel architecture (SEL-COVIDNET). We include a global average pooling layer, flattening, and two dense layers that are fully connected. The model’s effectiveness is evaluated using balanced and unbalanced COVID-19 radiography datasets. After that, our model’s performance is analyzed using six evaluation measures: accuracy, sensitivity, specificity, precision, F1-score, and Matthew’s correlation coefficient (MCC). Experiments demonstrated that the proposed SEL-COVIDNET with tuned DenseNet121, InceptionResNetV2, and MobileNetV3Large models outperformed the results of comparative SOTA for multi-class classification (COVID-19 vs. No-finding vs. Pneumonia) in terms of accuracy (98.52%), specificity (98.5%), sensitivity (98.5%), precision (98.7%), F1-score (98.7%), and MCC (97.5%). For the COVID-19 vs. No-finding classification, our method had an accuracy of 99.77%, a specificity of 99.85%, a sensitivity of 99.85%, a precision of 99.55%, an F1-score of 99.7%, and an MCC of 99.4%. The proposed model offers an accurate approach for detecting COVID-19 patients, which aids in the containment of the COVID-19 pandemic.
Collapse
Affiliation(s)
- Ahmad Al Smadi
- School of Artificial Intelligence, Xidian University, No. 2 South Taibai Road, Xian, 710071, China.,College of Technological Innovation, Zayed University, Abu Dhabi Campus, UAE
| | - Ahed Abugabah
- College of Technological Innovation, Zayed University, Abu Dhabi Campus, UAE
| | - Ahmad Mohammad Al-Smadi
- Department of Computer Science, Al-Balqa Applied University, Ajloun University College, Jordan
| | - Sultan Almotairi
- Faculty of Community College, Majmaah University, Al Majma'ah, Saudi Arabia
| |
Collapse
|
247
|
Suri JS, Agarwal S, Saba L, Chabert GL, Carriero A, Paschè A, Danna P, Mehmedović A, Faa G, Jujaray T, Singh IM, Khanna NN, Laird JR, Sfikakis PP, Agarwal V, Teji JS, R Yadav R, Nagy F, Kincses ZT, Ruzsa Z, Viskovic K, Kalra MK. Multicenter Study on COVID-19 Lung Computed Tomography Segmentation with varying Glass Ground Opacities using Unseen Deep Learning Artificial Intelligence Paradigms: COVLIAS 1.0 Validation. J Med Syst 2022; 46:62. [PMID: 35988110 PMCID: PMC9392994 DOI: 10.1007/s10916-022-01850-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/15/2022] [Accepted: 08/02/2022] [Indexed: 11/09/2022]
Abstract
Variations in COVID-19 lesions such as glass ground opacities (GGO), consolidations, and crazy paving can compromise the ability of solo-deep learning (SDL) or hybrid-deep learning (HDL) artificial intelligence (AI) models in predicting automated COVID-19 lung segmentation in Computed Tomography (CT) from unseen data leading to poor clinical manifestations. As the first study of its kind, “COVLIAS 1.0-Unseen” proves two hypotheses, (i) contrast adjustment is vital for AI, and (ii) HDL is superior to SDL. In a multicenter study, 10,000 CT slices were collected from 72 Italian (ITA) patients with low-GGO, and 80 Croatian (CRO) patients with high-GGO. Hounsfield Units (HU) were automatically adjusted to train the AI models and predict from test data, leading to four combinations—two Unseen sets: (i) train-CRO:test-ITA, (ii) train-ITA:test-CRO, and two Seen sets: (iii) train-CRO:test-CRO, (iv) train-ITA:test-ITA. COVILAS used three SDL models: PSPNet, SegNet, UNet and six HDL models: VGG-PSPNet, VGG-SegNet, VGG-UNet, ResNet-PSPNet, ResNet-SegNet, and ResNet-UNet. Two trained, blinded senior radiologists conducted ground truth annotations. Five types of performance metrics were used to validate COVLIAS 1.0-Unseen which was further benchmarked against MedSeg, an open-source web-based system. After HU adjustment for DS and JI, HDL (Unseen AI) > SDL (Unseen AI) by 4% and 5%, respectively. For CC, HDL (Unseen AI) > SDL (Unseen AI) by 6%. The COVLIAS-MedSeg difference was < 5%, meeting regulatory guidelines.Unseen AI was successfully demonstrated using automated HU adjustment. HDL was found to be superior to SDL.
Collapse
|
248
|
Maia R, Carvalho V, Faria B, Miranda I, Catarino S, Teixeira S, Lima R, Minas G, Ribeiro J. Diagnosis Methods for COVID-19: A Systematic Review. MICROMACHINES 2022; 13:1349. [PMID: 36014271 PMCID: PMC9415914 DOI: 10.3390/mi13081349] [Citation(s) in RCA: 20] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/02/2022] [Revised: 08/11/2022] [Accepted: 08/16/2022] [Indexed: 05/15/2023]
Abstract
At the end of 2019, the coronavirus appeared and spread extremely rapidly, causing millions of infections and deaths worldwide, and becoming a global pandemic. For this reason, it became urgent and essential to find adequate tests for an accurate and fast diagnosis of this disease. In the present study, a systematic review was performed in order to provide an overview of the COVID-19 diagnosis methods and tests already available, as well as their evolution in recent months. For this purpose, the Science Direct, PubMed, and Scopus databases were used to collect the data and three authors independently screened the references, extracted the main information, and assessed the quality of the included studies. After the analysis of the collected data, 34 studies reporting new methods to diagnose COVID-19 were selected. Although RT-PCR is the gold-standard method for COVID-19 diagnosis, it cannot fulfill all the requirements of this pandemic, being limited by the need for highly specialized equipment and personnel to perform the assays, as well as the long time to get the test results. To fulfill the limitations of this method, other alternatives, including biological and imaging analysis methods, also became commonly reported. The comparison of the different diagnosis tests allowed to understand the importance and potential of combining different techniques, not only to improve diagnosis but also for a further understanding of the virus, the disease, and their implications in humans.
Collapse
Affiliation(s)
- Renata Maia
- Microelectromechanical Systems Research Unit (CMEMS-UMinho), School of Engineering, Campus de Azurém, University of Minho, Guimarães, Portugal
- LABBELS-Associate Laboratory, Braga/Guimarães, Portugal
| | - Violeta Carvalho
- Microelectromechanical Systems Research Unit (CMEMS-UMinho), School of Engineering, Campus de Azurém, University of Minho, Guimarães, Portugal
- LABBELS-Associate Laboratory, Braga/Guimarães, Portugal
- MEtRICs, Mechanical Engineering Department, Campus de Azurém, University of Minho, 4800-058 Guimarães, Portugal
- ALGORITMI, Production and Systems Department, School of Engineering, Campus de Azurém, University of Minho, 4800-058 Guimarães, Portugal
| | - Bernardo Faria
- Microelectromechanical Systems Research Unit (CMEMS-UMinho), School of Engineering, Campus de Azurém, University of Minho, Guimarães, Portugal
- LABBELS-Associate Laboratory, Braga/Guimarães, Portugal
| | - Inês Miranda
- Microelectromechanical Systems Research Unit (CMEMS-UMinho), School of Engineering, Campus de Azurém, University of Minho, Guimarães, Portugal
- LABBELS-Associate Laboratory, Braga/Guimarães, Portugal
| | - Susana Catarino
- Microelectromechanical Systems Research Unit (CMEMS-UMinho), School of Engineering, Campus de Azurém, University of Minho, Guimarães, Portugal
- LABBELS-Associate Laboratory, Braga/Guimarães, Portugal
| | - Senhorinha Teixeira
- ALGORITMI, Production and Systems Department, School of Engineering, Campus de Azurém, University of Minho, 4800-058 Guimarães, Portugal
| | - Rui Lima
- MEtRICs, Mechanical Engineering Department, Campus de Azurém, University of Minho, 4800-058 Guimarães, Portugal
- CEFT, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal
- ALiCE, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal
| | - Graça Minas
- Microelectromechanical Systems Research Unit (CMEMS-UMinho), School of Engineering, Campus de Azurém, University of Minho, Guimarães, Portugal
- LABBELS-Associate Laboratory, Braga/Guimarães, Portugal
| | - João Ribeiro
- ALiCE, Faculty of Engineering, University of Porto, 4200-465 Porto, Portugal
- Campus de Santa Apolónia, Instituto Politécnico de Bragança, 5300-253 Bragança, Portugal
- Centro de Investigação de Montanha (CIMO), Campus de Santa Apolónia, Instituto Politécnico de Bragança, 5300-253 Bragança, Portugal
- Laboratório Associado para a Sustentabilidade e Tecnologia em Regiões de Montanha (SusTEC), Campus de Santa Apolónia, Instituto Politécnico de Bragança, 5300-253 Bragança, Portugal
| |
Collapse
|
249
|
The Evaluation of Diagnostic Values of Clinical Symptoms for COVID-19 Hospitalized Patients in Northern Iran: The Syndromic Surveillance System Data. ARCHIVES OF CLINICAL INFECTIOUS DISEASES 2022. [DOI: 10.5812/archcid-117465] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
Background: A novel coronavirus led to a rapidly spreading outbreak of COVID-19, which caused morbidity and mortality worldwide. Appropriate case definitions can help diagnose COVID-19. Objectives: This study aimed to evaluate the COVID-19 clinical symptoms and their potential patterns using latent class analysis (LCA) for identifying confirmed COVID-19 cases among hospitalized patients in northern Iran according to the syndromic surveillance system data. Methods: This cross-sectional study was conducted on patients with COVID-19 admitted to hospitals in Mazandaran Province, Iran. Respiratory specimens were collected by nasopharyngeal swabs from the patients and tested for COVID-¬19 using reverse transcription polymerase chain reaction (RT-PCR). Latent class analysis was used to identify patterns of the symptoms. The sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC) of each symptom pattern were compared and plotted. Also, multiple logistic regression was used to determine the odds ratio for each symptom pattern for predicting COVID-19 infection by adjusting for gender and age groups. Results: Among 13,724 hospitalized patients tested for COVID-19 and included in the analyses, 4,836 (35, 2%) had RT-PCR confirmed COVID-19. The symptoms of fever, chills, cough, shortness of breath, fatigue, myalgia, sore throat, diarrhea, nausea or vomiting, headache, and arthralgia were significantly more common in patients positive for COVID-19 than in other patients and were used in LCA. Latent class analysis suggested six classes (patterns) of clinical symptoms. The AUC of symptom patterns was poor, being 0.43 for class 5, comprising patients without any symptoms, and 0.53 for class 3, comprising patients with fever, chills, and cough. Also, multiple logistic regression showed that class 1, comprising patients with fever, chills, cough, shortness of breath, sore throat, and arthralgia, had an odds ratio of 2.87 (1.39, 3.43) relative to class 5 (patients without any symptoms) for positive COVID-19. Conclusions: This study showed that the clinical symptoms might help diagnose COVID-19. However, the defined clinical symptoms suggested in the surveillance system of COVID-19 in Iran during this time were not appropriate for identifying COVID-19 cases.
Collapse
|
250
|
Jha R, Bhattacharjee V, Mustafi A, Sahana SK. Improved disease diagnosis system for COVID-19 with data refactoring and handling methods. Front Psychol 2022; 13:951027. [PMID: 36033018 PMCID: PMC9416861 DOI: 10.3389/fpsyg.2022.951027] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/23/2022] [Accepted: 07/19/2022] [Indexed: 12/15/2022] Open
Abstract
The novel coronavirus illness (COVID-19) outbreak, which began in a seafood market in Wuhan, Hubei Province, China, in mid-December 2019, has spread to almost all countries, territories, and places throughout the world. And since the fault in diagnosis of a disease causes a psychological impact, this was very much visible in the spread of COVID-19. This research aims to address this issue by providing a better solution for diagnosis of the COVID-19 disease. The paper also addresses a very important issue of having less data for disease prediction models by elaborating on data handling techniques. Thus, special focus has been given on data processing and handling, with an aim to develop an improved machine learning model for diagnosis of COVID-19. Random Forest (RF), Decision tree (DT), K-Nearest Neighbor (KNN), Logistic Regression (LR), Support vector machine, and Deep Neural network (DNN) models are developed using the Hospital Israelita Albert Einstein (in São Paulo, Brazil) dataset to diagnose COVID-19. The dataset is pre-processed and distributed DT is applied to rank the features. Data augmentation has been applied to generate datasets for improving classification accuracy. The DNN model dominates overall techniques giving the highest accuracy of 96.99%, recall of 96.98%, and precision of 96.94%, which is better than or comparable to other research work. All the algorithms are implemented in a distributed environment on the Spark platform.
Collapse
Affiliation(s)
| | | | | | - Sudip Kumar Sahana
- Department of Computer Science and Engineering, Birla Institute of Technology, Mesra, Ranchi, India
| |
Collapse
|