1951
|
Hussain L, Nguyen T, Li H, Abbasi AA, Lone KJ, Zhao Z, Zaib M, Chen A, Duong TQ. Machine-learning classification of texture features of portable chest X-ray accurately classifies COVID-19 lung infection. Biomed Eng Online 2020; 19:88. [PMID: 33239006 PMCID: PMC7686836 DOI: 10.1186/s12938-020-00831-x] [Citation(s) in RCA: 39] [Impact Index Per Article: 9.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/19/2020] [Accepted: 11/17/2020] [Indexed: 12/21/2022] Open
Abstract
BACKGROUND The large volume and suboptimal image quality of portable chest X-rays (CXRs) as a result of the COVID-19 pandemic could post significant challenges for radiologists and frontline physicians. Deep-learning artificial intelligent (AI) methods have the potential to help improve diagnostic efficiency and accuracy for reading portable CXRs. PURPOSE The study aimed at developing an AI imaging analysis tool to classify COVID-19 lung infection based on portable CXRs. MATERIALS AND METHODS Public datasets of COVID-19 (N = 130), bacterial pneumonia (N = 145), non-COVID-19 viral pneumonia (N = 145), and normal (N = 138) CXRs were analyzed. Texture and morphological features were extracted. Five supervised machine-learning AI algorithms were used to classify COVID-19 from other conditions. Two-class and multi-class classification were performed. Statistical analysis was done using unpaired two-tailed t tests with unequal variance between groups. Performance of classification models used the receiver-operating characteristic (ROC) curve analysis. RESULTS For the two-class classification, the accuracy, sensitivity and specificity were, respectively, 100%, 100%, and 100% for COVID-19 vs normal; 96.34%, 95.35% and 97.44% for COVID-19 vs bacterial pneumonia; and 97.56%, 97.44% and 97.67% for COVID-19 vs non-COVID-19 viral pneumonia. For the multi-class classification, the combined accuracy and AUC were 79.52% and 0.87, respectively. CONCLUSION AI classification of texture and morphological features of portable CXRs accurately distinguishes COVID-19 lung infection in patients in multi-class datasets. Deep-learning methods have the potential to improve diagnostic efficiency and accuracy for portable CXRs.
Collapse
Affiliation(s)
- Lal Hussain
- Department of Computer Science and IT, King Abdullah Campus, University of Azad Jammu and Kashmir, Muzaffarabad, 13100, Azad Kashmir, Pakistan.
- Department of Computer Science and IT, Neelum Campus, University of Azad Jammu and Kashmir, Athmuqam, 13230, Azad Kashmir, Pakistan.
| | - Tony Nguyen
- Department of Radiology, Renaissance School of Medicine at Stony Brook University, 101 Nicolls Rd, Stony Brook, NY, 11794, USA
| | - Haifang Li
- Department of Radiology, Renaissance School of Medicine at Stony Brook University, 101 Nicolls Rd, Stony Brook, NY, 11794, USA
| | - Adeel A Abbasi
- Department of Computer Science and IT, King Abdullah Campus, University of Azad Jammu and Kashmir, Muzaffarabad, 13100, Azad Kashmir, Pakistan
| | - Kashif J Lone
- Department of Computer Science and IT, King Abdullah Campus, University of Azad Jammu and Kashmir, Muzaffarabad, 13100, Azad Kashmir, Pakistan
| | - Zirun Zhao
- Department of Radiology, Renaissance School of Medicine at Stony Brook University, 101 Nicolls Rd, Stony Brook, NY, 11794, USA
| | - Mahnoor Zaib
- Department of Computer Science and IT, Neelum Campus, University of Azad Jammu and Kashmir, Athmuqam, 13230, Azad Kashmir, Pakistan
| | - Anne Chen
- Department of Radiology, Renaissance School of Medicine at Stony Brook University, 101 Nicolls Rd, Stony Brook, NY, 11794, USA
| | - Tim Q Duong
- Department of Radiology, Renaissance School of Medicine at Stony Brook University, 101 Nicolls Rd, Stony Brook, NY, 11794, USA
| |
Collapse
|
1952
|
Albahli S, Albattah W. Deep Transfer Learning for COVID-19 Prediction: Case Study for Limited Data Problems. Curr Med Imaging 2020; 17:973-980. [PMID: 33231160 PMCID: PMC8653418 DOI: 10.2174/1573405616666201123120417] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/24/2020] [Revised: 09/24/2020] [Accepted: 10/06/2020] [Indexed: 11/22/2022]
Abstract
OBJECTIVE Automatic prediction of COVID-19 using deep convolution neural networks based pre-trained transfer models and Chest X-ray images. METHODS This research employs the advantages of computer vision and medical image analysis to develop an automated model that has the clinical potential for early detection of the disease. Using Deep Learning models, the research aims at evaluating the effectiveness and accuracy of different convolutional neural networks models in the automatic diagnosis of COVID-19 from X-ray images as compared to diagnosis performed by experts in the medical community. RESULTS Due to the fact that the dataset available for COVID-19 is still limited, the best model to use is the InceptionNetV3. Performance results show that the InceptionNetV3 model yielded the highest accuracy of 98.63% (with data augmentation) and 98.90% (without data augmentation) among the three models designed. However, as the dataset gets bigger, the Inception ResNetV2 and NASNetlarge will do a better job of classification. All the performed networks tend to over-fit when data augmentation is not used, this is due to the small amount of data used for training and validation. CONCLUSION A deep transfer learning is proposed to detecting the COVID-19 automatically from chest X-ray by training it with X-ray images gotten from both COVID-19 patients and people with normal chest X-rays. The study is aimed at helping doctors in making decisions in their clinical practice due its high performance and effectiveness, the study also gives an insight to how transfer learning was used to automatically detect the COVID-19.
Collapse
Affiliation(s)
- Saleh Albahli
- Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia
| | - Waleed Albattah
- Department of Information Technology, College of Computer, Qassim University, Buraydah, Saudi Arabia
| |
Collapse
|
1953
|
Rana S, Storey M, Manthala Padannayil N, Shamurailatpam DS, Bennouna J, George J, Chang J. Investigating the utilization of beam-specific apertures for the intensity-modulated proton therapy (IMPT) head and neck cancer plans. Med Dosim 2020; 46:e7-e11. [PMID: 33246881 DOI: 10.1016/j.meddos.2020.10.006] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/05/2020] [Revised: 10/11/2020] [Accepted: 10/28/2020] [Indexed: 12/16/2022]
Abstract
Intensity-modulated proton therapy (IMPT) planning for the head and neck (HN) cancer often requires the use of the range shifter, which can increase the lateral penumbrae of the pencil proton beam in the patient, thus leading to an increase in unnecessary dose to the organs at risks (OARs) in proximity to the target volumes. The primary goal of the current study was to investigate the dosimetric benefits of utilizing beam-specific apertures for the IMPT HN cancer plans. The current retrospective study included computed tomography datasets of 10 unilateral HN cancer patients. The clinical target volume (CTV) was divided into low-risk CTV1 and high-risk CTV2. Total dose prescriptions to the CTV1 and CTV2 were 54 Gy(RBE) and 70 Gy(RBE), respectively, with a fractional dose of 2 Gy(RBE). All treatment plans were robustly optimized (patient setup uncertainty = 3 mm; range uncertainty = 3.5%) on the CTVs. For each patient, 2 sets of plans were generated: (1) without beam-specific aperture (WOBSA), and (2) with beam-specific aperture (WBSA). Specifically, both the WOBSA and WBSA of the given patient used identical beam angles, air gap, optimization structures, optimization constraints, and optimization settings. Target coverage and homogeneity index were comparable in both the WOBSA and WBSA plans with no statistical significance (p > 0.05). On average, the mean dose in WBSA plans was reduced by 12.1%, 2.9%, 3.0%, 3.8%, and 5.2% for the larynx, oral cavity, parotids, superior pharyngeal constrictor muscle, and inferior pharyngeal constrictor muscle, respectively. The dosimetric results of the OARs were found to be statistically significant (p < 0.05). The use of the beam-specific apertures did not deteriorate the coverage and homogeneity in the target volume and allowed for a reduction in mean dose to the OARs with an average difference up to 12.1%.
Collapse
Affiliation(s)
- Suresh Rana
- Department of Medical Physics, Oklahoma Proton Center, Oklahoma City, OK 73142, USA; Department of Radiation Oncology, Miami Cancer Institute, Baptist Health South Florida, Miami, FL, USA; Department of Radiation Oncology, Herbert Wertheim College of Medicine, Florida International University, Miami, FL, USA.
| | - Mark Storey
- Department of Radiation Oncology, Oklahoma Proton Center, Oklahoma City, OK 73142, USA
| | | | | | - Jaafar Bennouna
- Department of Radiation Oncology, Miami Cancer Institute, Baptist Health South Florida, Miami, FL, USA
| | - Jerry George
- Department of Radiation Oncology, Miami Cancer Institute, Baptist Health South Florida, Miami, FL, USA
| | - John Chang
- Department of Radiation Oncology, Oklahoma Proton Center, Oklahoma City, OK 73142, USA
| |
Collapse
|
1954
|
Affiliation(s)
- M Sreepadmanabh
- Molecular Virology Laboratory, Indian Institute of Science Education and Research, Bhopal, India
| | - Amit Kumar Sahu
- Molecular Virology Laboratory, Indian Institute of Science Education and Research, Bhopal, India
| | - Ajit Chande
- Molecular Virology Laboratory, Indian Institute of Science Education and Research, Bhopal, India
| |
Collapse
|
1955
|
Chiroma H, Ezugwu AE, Jauro F, Al-Garadi MA, Abdullahi IN, Shuib L. Early survey with bibliometric analysis on machine learning approaches in controlling COVID-19 outbreaks. PeerJ Comput Sci 2020; 6:e313. [PMID: 33816964 PMCID: PMC7924648 DOI: 10.7717/peerj-cs.313] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/26/2020] [Accepted: 10/15/2020] [Indexed: 05/09/2023]
Abstract
BACKGROUND AND OBJECTIVE The COVID-19 pandemic has caused severe mortality across the globe, with the USA as the current epicenter of the COVID-19 epidemic even though the initial outbreak was in Wuhan, China. Many studies successfully applied machine learning to fight COVID-19 pandemic from a different perspective. To the best of the authors' knowledge, no comprehensive survey with bibliometric analysis has been conducted yet on the adoption of machine learning to fight COVID-19. Therefore, the main goal of this study is to bridge this gap by carrying out an in-depth survey with bibliometric analysis on the adoption of machine learning-based technologies to fight COVID-19 pandemic from a different perspective, including an extensive systematic literature review and bibliometric analysis. METHODS We applied a literature survey methodology to retrieved data from academic databases and subsequently employed a bibliometric technique to analyze the accessed records. Besides, the concise summary, sources of COVID-19 datasets, taxonomy, synthesis and analysis are presented in this study. It was found that the Convolutional Neural Network (CNN) is mainly utilized in developing COVID-19 diagnosis and prognosis tools, mostly from chest X-ray and chest CT scan images. Similarly, in this study, we performed a bibliometric analysis of machine learning-based COVID-19 related publications in the Scopus and Web of Science citation indexes. Finally, we propose a new perspective for solving the challenges identified as direction for future research. We believe the survey with bibliometric analysis can help researchers easily detect areas that require further development and identify potential collaborators. RESULTS The findings of the analysis presented in this article reveal that machine learning-based COVID-19 diagnose tools received the most considerable attention from researchers. Specifically, the analyses of results show that energy and resources are more dispenses towards COVID-19 automated diagnose tools while COVID-19 drugs and vaccine development remains grossly underexploited. Besides, the machine learning-based algorithm that is predominantly utilized by researchers in developing the diagnostic tool is CNN mainly from X-rays and CT scan images. CONCLUSIONS The challenges hindering practical work on the application of machine learning-based technologies to fight COVID-19 and new perspective to solve the identified problems are presented in this article. Furthermore, we believed that the presented survey with bibliometric analysis could make it easier for researchers to identify areas that need further development and possibly identify potential collaborators at author, country and institutional level, with the overall aim of furthering research in the focused area of machine learning application to disease control.
Collapse
Affiliation(s)
- Haruna Chiroma
- Future Technology Research Center, National Yunlin University of Science and Technology, Yulin, Taiwan
| | - Absalom E. Ezugwu
- School of Mathematics, Statistics, and Computer Science, University of KwaZulu-Natal, KwaZulu-Natal, South Africa
| | - Fatsuma Jauro
- Department of Computer Science, Faculty of Science, Ahmadu Bello University, Zaria, Nigeria
| | | | - Idris N. Abdullahi
- Department of Medical Laboratory Science, College of Medical Sciences, Ahmadu Bello University, Zaria, Nigeria
| | - Liyana Shuib
- Department of Information System, Universiti Malaya, Kuala Lumpur, Malaysia
| |
Collapse
|
1956
|
Abstract
Background and objectives Chest X-ray data have been found to be very promising for assessing COVID-19 patients, especially for resolving emergency-department and urgent-care-center overcapacity. Deep-learning (DL) methods in artificial intelligence (AI) play a dominant role as high-performance classifiers in the detection of the disease using chest X-rays. Given many new DL models have been being developed for this purpose, the objective of this study is to investigate the fine tuning of pretrained convolutional neural networks (CNNs) for the classification of COVID-19 using chest X-rays. If fine-tuned pre-trained CNNs can provide equivalent or better classification results than other more sophisticated CNNs, then the deployment of AI-based tools for detecting COVID-19 using chest X-ray data can be more rapid and cost-effective. Methods Three pretrained CNNs, which are AlexNet, GoogleNet, and SqueezeNet, were selected and fine-tuned without data augmentation to carry out 2-class and 3-class classification tasks using 3 public chest X-ray databases. Results In comparison with other recently developed DL models, the 3 pretrained CNNs achieved very high classification results in terms of accuracy, sensitivity, specificity, precision, F 1 score, and area under the receiver-operating-characteristic curve. Conclusion AlexNet, GoogleNet, and SqueezeNet require the least training time among pretrained DL models, but with suitable selection of training parameters, excellent classification results can be achieved without data augmentation by these networks. The findings contribute to the urgent need for harnessing the pandemic by facilitating the deployment of AI tools that are fully automated and readily available in the public domain for rapid implementation.
Collapse
Affiliation(s)
- Tuan D. Pham
- Center for Artificial Intelligence, Prince Mohammad Bin Fahd University, Khobar, 31952 Saudi Arabia
| |
Collapse
|
1957
|
Wang D, Mo J, Zhou G, Xu L, Liu Y. An efficient mixture of deep and machine learning models for COVID-19 diagnosis in chest X-ray images. PLoS One 2020; 15:e0242535. [PMID: 33201919 PMCID: PMC7671547 DOI: 10.1371/journal.pone.0242535] [Citation(s) in RCA: 44] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/10/2020] [Accepted: 11/05/2020] [Indexed: 11/24/2022] Open
Abstract
A newly emerged coronavirus (COVID-19) seriously threatens human life and health worldwide. In coping and fighting against COVID-19, the most critical step is to effectively screen and diagnose infected patients. Among them, chest X-ray imaging technology is a valuable imaging diagnosis method. The use of computer-aided diagnosis to screen X-ray images of COVID-19 cases can provide experts with auxiliary diagnosis suggestions, which can reduce the burden of experts to a certain extent. In this study, we first used conventional transfer learning methods, using five pre-trained deep learning models, which the Xception model showed a relatively ideal effect, and the diagnostic accuracy reached 96.75%. In order to further improve the diagnostic accuracy, we propose an efficient diagnostic method that uses a combination of deep features and machine learning classification. It implements an end-to-end diagnostic model. The proposed method was tested on two datasets and performed exceptionally well on both of them. We first evaluated the model on 1102 chest X-ray images. The experimental results show that the diagnostic accuracy of Xception + SVM is as high as 99.33%. Compared with the baseline Xception model, the diagnostic accuracy is improved by 2.58%. The sensitivity, specificity and AUC of this model reached 99.27%, 99.38% and 99.32%, respectively. To further illustrate the robustness of our method, we also tested our proposed model on another dataset. Finally also achieved good results. Compared with related research, our proposed method has higher classification accuracy and efficient diagnostic performance. Overall, the proposed method substantially advances the current radiology based methodology, it can be very helpful tool for clinical practitioners and radiologists to aid them in diagnosis and follow-up of COVID-19 cases.
Collapse
Affiliation(s)
- Dingding Wang
- Key Laboratory of Signal Detection and Processing, College of Information Science and Engineering, Xinjiang University, Urumqi, China
| | - Jiaqing Mo
- Key Laboratory of Signal Detection and Processing, College of Information Science and Engineering, Xinjiang University, Urumqi, China
| | - Gang Zhou
- Key Laboratory of Signal Detection and Processing, College of Information Science and Engineering, Xinjiang University, Urumqi, China
| | - Liang Xu
- School of Electrical and Electronic Engineering, Tianjin University of Technology, Tianjin, China
| | - Yajun Liu
- Key Laboratory of Signal Detection and Processing, College of Information Science and Engineering, Xinjiang University, Urumqi, China
| |
Collapse
|
1958
|
Gianchandani N, Jaiswal A, Singh D, Kumar V, Kaur M. Rapid COVID-19 diagnosis using ensemble deep transfer learning models from chest radiographic images. J Ambient Intell Humaniz Comput 2020; 14:5541-5553. [PMID: 33224307 PMCID: PMC7667280 DOI: 10.1007/s12652-020-02669-6] [Citation(s) in RCA: 29] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/11/2020] [Accepted: 11/03/2020] [Indexed: 05/02/2023]
Abstract
The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causes novel coronavirus disease (COVID-19) outbreak in more than 200 countries around the world. The early diagnosis of infected patients is needed to discontinue this outbreak. The diagnosis of coronavirus infection from radiography images is the fastest method. In this paper, two different ensemble deep transfer learning models have been designed for COVID-19 diagnosis utilizing the chest X-rays. Both models have utilized pre-trained models for better performance. They are able to differentiate COVID-19, viral pneumonia, and bacterial pneumonia. Both models have been developed to improve the generalization capability of the classifier for binary and multi-class problems. The proposed models have been tested on two well-known datasets. Experimental results reveal that the proposed framework outperforms the existing techniques in terms of sensitivity, specificity, and accuracy.
Collapse
Affiliation(s)
- Neha Gianchandani
- Department of Computer Science and Engineering, School of Computing and Information Technology, Manipal University Jaipur, Jaipur, Rajasthan 303007 India
| | - Aayush Jaiswal
- Department of Computer Science and Engineering, School of Computing and Information Technology, Manipal University Jaipur, Jaipur, Rajasthan 303007 India
| | - Dilbag Singh
- Computer Science Engineering, School of Engineering and Applied Sciences, Bennett University, Greater Noida, 201310 India
| | - Vijay Kumar
- Department of Computer Science and Engineering, National Institute of Technology Hamirpur, Hamirpur, Himachal Pradesh 177005 India
| | - Manjit Kaur
- Computer Science Engineering, School of Engineering and Applied Sciences, Bennett University, Greater Noida, 201310 India
| |
Collapse
|
1959
|
Huang Z, Liu X, Wang R, Zhang M, Zeng X, Liu J, Yang Y, Liu X, Zheng H, Liang D, Hu Z. FaNet: fast assessment network for the novel coronavirus (COVID-19) pneumonia based on 3D CT imaging and clinical symptoms. APPL INTELL 2020; 51:2838-2849. [PMID: 34764567 PMCID: PMC7665967 DOI: 10.1007/s10489-020-01965-0] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 09/19/2020] [Indexed: 01/15/2023]
Abstract
The novel coronavirus (COVID-19) pneumonia has become a serious health challenge in countries worldwide. Many radiological findings have shown that X-ray and CT imaging scans are an effective solution to assess disease severity during the early stage of COVID-19. Many artificial intelligence (AI)-assisted diagnosis works have rapidly been proposed to focus on solving this classification problem and determine whether a patient is infected with COVID-19. Most of these works have designed networks and applied a single CT image to perform classification; however, this approach ignores prior information such as the patient’s clinical symptoms. Second, making a more specific diagnosis of clinical severity, such as slight or severe, is worthy of attention and is conducive to determining better follow-up treatments. In this paper, we propose a deep learning (DL) based dual-tasks network, named FaNet, that can perform rapid both diagnosis and severity assessments for COVID-19 based on the combination of 3D CT imaging and clinical symptoms. Generally, 3D CT image sequences provide more spatial information than do single CT images. In addition, the clinical symptoms can be considered as prior information to improve the assessment accuracy; these symptoms are typically quickly and easily accessible to radiologists. Therefore, we designed a network that considers both CT image information and existing clinical symptom information and conducted experiments on 416 patient data, including 207 normal chest CT cases and 209 COVID-19 confirmed ones. The experimental results demonstrate the effectiveness of the additional symptom prior information as well as the network architecture designing. The proposed FaNet achieved an accuracy of 98.28% on diagnosis assessment and 94.83% on severity assessment for test datasets. In the future, we will collect more covid-CT patient data and seek further improvement.
Collapse
Affiliation(s)
- Zhenxing Huang
- Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055 China.,Chinese Academy of Sciences Key Laboratory of Health Informatics, Shenzhen, 518055 China
| | - Xinfeng Liu
- Department of Radiology, Guizhou Provincial People's Hospital, Guiyang, 550002 China
| | - Rongpin Wang
- Department of Radiology, Guizhou Provincial People's Hospital, Guiyang, 550002 China
| | - Mudan Zhang
- Department of Radiology, Guizhou Provincial People's Hospital, Guiyang, 550002 China
| | - Xianchun Zeng
- Department of Radiology, Guizhou Provincial People's Hospital, Guiyang, 550002 China
| | - Jun Liu
- Department of Radiology, The Second Xiangya Hospital, Central South University, Changsha, 410011 China
| | - Yongfeng Yang
- Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055 China.,Chinese Academy of Sciences Key Laboratory of Health Informatics, Shenzhen, 518055 China
| | - Xin Liu
- Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055 China.,Chinese Academy of Sciences Key Laboratory of Health Informatics, Shenzhen, 518055 China
| | - Hairong Zheng
- Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055 China.,Chinese Academy of Sciences Key Laboratory of Health Informatics, Shenzhen, 518055 China
| | - Dong Liang
- Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055 China.,Chinese Academy of Sciences Key Laboratory of Health Informatics, Shenzhen, 518055 China
| | - Zhanli Hu
- Lauterbur Research Center for Biomedical Imaging, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055 China.,Chinese Academy of Sciences Key Laboratory of Health Informatics, Shenzhen, 518055 China
| |
Collapse
|
1960
|
Wang L, Lin ZQ, Wong A. COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images. Sci Rep 2020; 10:19549. [PMID: 33177550 PMCID: PMC7658227 DOI: 10.1038/s41598-020-76550-z] [Citation(s) in RCA: 870] [Impact Index Per Article: 217.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/20/2020] [Accepted: 10/26/2020] [Indexed: 02/06/2023] Open
Abstract
The Coronavirus Disease 2019 (COVID-19) pandemic continues to have a devastating effect on the health and well-being of the global population. A critical step in the fight against COVID-19 is effective screening of infected patients, with one of the key screening approaches being radiology examination using chest radiography. It was found in early studies that patients present abnormalities in chest radiography images that are characteristic of those infected with COVID-19. Motivated by this and inspired by the open source efforts of the research community, in this study we introduce COVID-Net, a deep convolutional neural network design tailored for the detection of COVID-19 cases from chest X-ray (CXR) images that is open source and available to the general public. To the best of the authors' knowledge, COVID-Net is one of the first open source network designs for COVID-19 detection from CXR images at the time of initial release. We also introduce COVIDx, an open access benchmark dataset that we generated comprising of 13,975 CXR images across 13,870 patient patient cases, with the largest number of publicly available COVID-19 positive cases to the best of the authors' knowledge. Furthermore, we investigate how COVID-Net makes predictions using an explainability method in an attempt to not only gain deeper insights into critical factors associated with COVID cases, which can aid clinicians in improved screening, but also audit COVID-Net in a responsible and transparent manner to validate that it is making decisions based on relevant information from the CXR images. By no means a production-ready solution, the hope is that the open access COVID-Net, along with the description on constructing the open source COVIDx dataset, will be leveraged and build upon by both researchers and citizen data scientists alike to accelerate the development of highly accurate yet practical deep learning solutions for detecting COVID-19 cases and accelerate treatment of those who need it the most.
Collapse
Affiliation(s)
- Linda Wang
- Department of Systems Design Engineering, University of Waterloo, Waterloo, Canada.
- Waterloo Artificial Intelligence Institute, Waterloo, Canada.
- DarwinAI Corp., Waterloo, Canada.
| | - Zhong Qiu Lin
- Department of Systems Design Engineering, University of Waterloo, Waterloo, Canada
- Waterloo Artificial Intelligence Institute, Waterloo, Canada
- DarwinAI Corp., Waterloo, Canada
| | - Alexander Wong
- Department of Systems Design Engineering, University of Waterloo, Waterloo, Canada
- Waterloo Artificial Intelligence Institute, Waterloo, Canada
- DarwinAI Corp., Waterloo, Canada
| |
Collapse
|
1961
|
Trapp JV. Citations equals research quality? If you agree then don't cite this stupid, totally terrible article. Phys Eng Sci Med 2020; 43:1149. [PMID: 33165821 DOI: 10.1007/s13246-020-00942-8] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 10/25/2020] [Indexed: 11/29/2022]
Affiliation(s)
- Jamie V Trapp
- Queensland University of Technology, Brisbane, Australia.
| |
Collapse
|
1962
|
Affiliation(s)
- Martin Caon
- , Clarence Park (retired), Adelaide, Australia
| | - Jamie Trapp
- School of Chemistry, Physics and Mechanical Engineering, Queensland University of Technology, Level 4 O Block, Garden's Point, Brisbane, QLD, 4001, Australia
| | - Clive Baldock
- Research and Innovation Division, University of Wollongong, Wollongong, NSW, 2522, Australia.
| |
Collapse
|
1963
|
Berraih SA, Baakek YNE, Debbal SMEA. Pathological discrimination of the phonocardiogram signal using the bispectral technique. Phys Eng Sci Med 2020; 43:1371-85. [PMID: 33165819 DOI: 10.1007/s13246-020-00943-7] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2020] [Accepted: 10/27/2020] [Indexed: 10/23/2022]
Abstract
Phonocardiography is a dynamic non-invasive and relatively low-cost technique used to monitor the state of the mechanical activity of the heart. The recordings generated by such a technique is called phonocardiogram (PCG) signals. When shown visually, PCG signals can provide more insights of heart sounds for medical doctors. Thus, several approaches have been proposed to analyse these sounds through PCG recordings. However, due to the complexity and the high nonlinear nature of these recordings, a computer-assisted technique based on higher-order statistics HOS is shown to be, among these techniques, an important tool in PCG signal processing. The third-order spectra technique is one of these techniques; known as bispectrum, it can provide significant information to support physicians with an accurate and objective interpretation of heart condition. This technique is implemented and discussed in this paper. The implemented technique is used for the analysis of heart severity on nine different PCG recordings. These are normal, innocent murmur, coarctation of the aorta, ejection click, atrial gallop, opening snap, aortic stenosis, drum rumble, and aortic regurgitation. A unique bispectrum representation is generated for each type of heart sounds signal. Then, based on the bispectrum analysis, fifteen higher-order spectra HOS features such as the bispectral amplitude, the entropies, the moments, and the weighted center are extracted from each PCG record. The obtained HOS-features showed a well-correlated evolution with the increasing importance of heart severity leading therefore to a high potential in discriminating pathological PCG signals. One should know that, generally, classification of pathological PCG signals refers to the distinction between the presence of a pathology from its absence (binary response) while the discrimination considered in this paper provides an analogue response (value) which can vary from one pathology to another in an increasing or decreasing way.
Collapse
|
1964
|
Wang H, Gu H, Qin P, Wang J. CheXLocNet: Automatic localization of pneumothorax in chest radiographs using deep convolutional neural networks. PLoS One 2020; 15:e0242013. [PMID: 33166371 PMCID: PMC7652331 DOI: 10.1371/journal.pone.0242013] [Citation(s) in RCA: 18] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/16/2020] [Accepted: 10/24/2020] [Indexed: 01/18/2023] Open
Abstract
BACKGROUND Pneumothorax can lead to a life-threatening emergency. The experienced radiologists can offer precise diagnosis according to the chest radiographs. The localization of the pneumothorax lesions will help to quickly diagnose, which will be benefit for the patients in the underdevelopment areas lack of the experienced radiologists. In recent years, with the development of large neural network architectures and medical imaging datasets, deep learning methods have become a methodology of choice for analyzing medical images. The objective of this study was to the construct convolutional neural networks to localize the pneumothorax lesions in chest radiographs. METHODS AND FINDINGS We developed a convolutional neural network, called CheXLocNet, for the segmentation of pneumothorax lesions. The SIIM-ACR Pneumothorax Segmentation dataset was used to train and validate CheXLocNets. The training dataset contained 2079 radiographs with the annotated lesion areas. We trained six CheXLocNets with various hyperparameters. Another 300 annotated radiographs were used to select parameters of these CheXLocNets as the validation set. We determined the optimal parameters by the AP50 (average precision at the intersection over union (IoU) equal to 0.50), a segmentation evaluation metric used by several well-known competitions. Then CheXLocNets were evaluated by a test set (1082 normal radiographs and 290 disease radiographs), based on the classification metrics: area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value (PPV); segmentation metrics: IoU and Dice score. For the classification, CheXLocNet with best sensitivity produced an AUC of 0.87, sensitivity of 0.78 (95% CI 0.73-0.83), and specificity of 0.78 (95% CI 0.76-0.81). CheXLocNet with best specificity produced an AUC of 0.79, sensitivity of 0.46 (95% CI 0.40-0.52), and specificity of 0.92 (95% CI 0.90-0.94). For the segmentation, CheXLocNet with best sensitivity produced an IoU of 0.69 and Dice score of 0.72. CheXLocNet with best specificity produced an IoU of 0.77 and Dice score of 0.79. We combined them to form an ensemble CheXLocNet. The ensemble CheXLocNet produced an IoU of 0.81 and Dice score of 0.82. Our CheXLocNet succeeded in automatically detecting pneumothorax lesions, without any human guidance. CONCLUSIONS In this study, we proposed a deep learning network, called, CheXLocNet, for the automatic segmentation of chest radiographs to detect pneumothorax. Our CheXLocNets generated accurate classification results and high-quality segmentation masks for the pneumothorax at the same time. This technology has the potential to improve healthcare delivery and increase access to chest radiograph expertise for the detection of diseases. Furthermore, the segmentation results can offer comprehensive geometric information of lesions, which can benefit monitoring the sequential development of lesions with high accuracy. Thus, CheXLocNets can be further extended to be a reliable clinical decision support tool. Although we used transfer learning in training CheXLocNet, the parameters of CheXLocNet was still large for the radiograph dataset. Further work is necessary to prune CheXLocNet suitable for the radiograph dataset.
Collapse
Affiliation(s)
- Hongyu Wang
- Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, Liaoning, China
| | - Hong Gu
- Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, Liaoning, China
| | - Pan Qin
- Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, Liaoning, China
| | - Jia Wang
- Department of Surgery, Second Hospital of Dalian Medical University, Dalian, Liaoning, China
| |
Collapse
|
1965
|
Al-Bawi A, Al-Kaabi K, Jeryo M, Al-Fatlawi A. CCBlock: an effective use of deep learning for automatic diagnosis of COVID-19 using X-ray images. ACTA ACUST UNITED AC 2020. [PMCID: PMC7648896 DOI: 10.1007/s42600-020-00110-7] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/07/2023]
Abstract
Propose Troubling countries one after another, the COVID-19 pandemic has dramatically affected the health and well-being of the world’s population. The disease may continue to persist more extensively due to the increasing number of new cases daily, the rapid spread of the virus, and delay in the PCR analysis results. Therefore, it is necessary to consider developing assistive methods for detecting and diagnosing the COVID-19 to eradicate the spread of the novel coronavirus among people. Based on convolutional neural networks (CNNs), automated detection systems have shown promising results of diagnosing patients with the COVID-19 through radiography; thus, they are introduced as a workable solution to the COVID-19 diagnosis. Materials and methods Based on the enhancement of the classical visual geometry group (VGG) network with the convolutional COVID block (CCBlock), an efficient screening model was proposed in this study to diagnose and distinguish patients with the COVID-19 from those with pneumonia and the healthy people through radiography. The model testing dataset included 1828 X-ray images available on public platforms. Three hundred and ten images were showing confirmed COVID-19 cases, 864 images indicating pneumonia cases, and 654 images showing healthy people. Results According to the test results, enhancing the classical VGG network with radiography provided the highest diagnosis performance and overall accuracy of 98.52% for two classes as well as accuracy of 95.34% for three classes. Conclusions According to the results, using the enhanced VGG deep neural network can help radiologists automatically diagnose the COVID-19 through radiography.
Collapse
|
1966
|
Lee KS, Kim JY, Jeon ET, Choi WS, Kim NH, Lee KY. Evaluation of Scalability and Degree of Fine-Tuning of Deep Convolutional Neural Networks for COVID-19 Screening on Chest X-ray Images Using Explainable Deep-Learning Algorithm. J Pers Med 2020; 10:E213. [PMID: 33171723 PMCID: PMC7711996 DOI: 10.3390/jpm10040213] [Citation(s) in RCA: 23] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2020] [Revised: 10/29/2020] [Accepted: 10/30/2020] [Indexed: 12/18/2022] Open
Abstract
According to recent studies, patients with COVID-19 have different feature characteristics on chest X-ray (CXR) than those with other lung diseases. This study aimed at evaluating the layer depths and degree of fine-tuning on transfer learning with a deep convolutional neural network (CNN)-based COVID-19 screening in CXR to identify efficient transfer learning strategies. The CXR images used in this study were collected from publicly available repositories, and the collected images were classified into three classes: COVID-19, pneumonia, and normal. To evaluate the effect of layer depths of the same CNN architecture, CNNs called VGG-16 and VGG-19 were used as backbone networks. Then, each backbone network was trained with different degrees of fine-tuning and comparatively evaluated. The experimental results showed the highest AUC value to be 0.950 concerning COVID-19 classification in the experimental group of a fine-tuned with only 2/5 blocks of the VGG16 backbone network. In conclusion, in the classification of medical images with a limited number of data, a deeper layer depth may not guarantee better results. In addition, even if the same pre-trained CNN architecture is used, an appropriate degree of fine-tuning can help to build an efficient deep learning model.
Collapse
Affiliation(s)
- Ki-Sun Lee
- Medical Science Research Center, Ansan Hospital, Korea University College of Medicine, Ansan si 15355, Korea; (J.Y.K.); (E.-t.J.)
| | - Jae Young Kim
- Medical Science Research Center, Ansan Hospital, Korea University College of Medicine, Ansan si 15355, Korea; (J.Y.K.); (E.-t.J.)
| | - Eun-tae Jeon
- Medical Science Research Center, Ansan Hospital, Korea University College of Medicine, Ansan si 15355, Korea; (J.Y.K.); (E.-t.J.)
| | - Won Suk Choi
- Division of Infectious Diseases, Department of Internal Medicine, Ansan Hospital, Korea University College of Medicine, Ansan si 15355, Korea;
| | - Nan Hee Kim
- Division of Endocrinology and Metabolism, Department of Internal Medicine, Ansan Hospital, Korea University College of Medicine, Ansan si 15355, Korea;
| | - Ki Yeol Lee
- Department of Radiology, Ansan Hospital, Korea University College of Medicine, Ansan si 15355, Korea;
| |
Collapse
|
1967
|
Chen ST, Ku LC, Chen SJ, Shen TW. The Changes of qEEG Approximate Entropy during Test of Variables of Attention as a Predictor of Major Depressive Disorder. Brain Sci 2020; 10:brainsci10110828. [PMID: 33171848 PMCID: PMC7695214 DOI: 10.3390/brainsci10110828] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2020] [Revised: 10/30/2020] [Accepted: 11/05/2020] [Indexed: 01/30/2023] Open
Abstract
Evaluating brain function through biosignals remains challenging. Quantitative electroencephalography (qEEG) outcomes have emerged as a potential intermediate biomarker for diagnostic clarification in psychological disorders. The Test of Variables of Attention (TOVA) was combined with qEEG to evaluate biomarkers such as absolute power, relative power, cordance, and approximate entropy from covariance matrix images to predict major depressive disorder (MDD). EEG data from 18 healthy control and 18 MDD patients were monitored during the resting state and TOVA. TOVA was found to provide aspects for the evaluation of MDD beyond resting electroencephalography. The results showed that the prefrontal qEEG theta cordance of the control and MDD groups were significantly different. For comparison, the changes in qEEG approximate entropy (ApEn) patterns observed during TOVA provided features to distinguish between participants with or without MDD. Moreover, ApEn scores during TOVA were a strong predictor of MDD, and the ApEn scores correlated with the Beck Depression Inventory (BDI) scores. Between-group differences in ApEn were more significant for the testing state than for the resting state. Our results provide further understanding for MDD treatment selection and response prediction during TOVA.
Collapse
Affiliation(s)
- Shao-Tsu Chen
- Department of Psychiatry, Hualien Tzu Chi Hospital, Buddhist Tzu-Chi Medical Foundation, Hualien 970, Taiwan;
- Department of Psychiatry, Tzu Chi University, Hualien 970, Taiwan
| | - Li-Chi Ku
- Department of Medical Informatics, Tzu Chi University, Hualien 970, Taiwan;
| | - Shaw-Ji Chen
- Department of Psychiatry, Taitung MacKay Memorial Hospital, Taitung County 950, Taiwan;
- Department of Medicine, MacKay Medical College, New Taipei City 252, Taiwan
| | - Tsu-Wang Shen
- Department of Automatic Control Engineering, Feng Chia University, Taichung 40724, Taiwan
- Master’s Program Biomedical Informatics and Biomedical Engineering, Feng Chia University, Taichung 40724, Taiwan
- Correspondence: ; Tel.: +886-4-24517250 (ext. 3937)
| |
Collapse
|
1968
|
Kikkisetti S, Zhu J, Shen B, Li H, Duong TQ. Deep-learning convolutional neural networks with transfer learning accurately classify COVID-19 lung infection on portable chest radiographs. PeerJ 2020; 8:e10309. [PMID: 33194447 PMCID: PMC7649013 DOI: 10.7717/peerj.10309] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2020] [Accepted: 10/15/2020] [Indexed: 12/13/2022] Open
Abstract
Portable chest X-ray (pCXR) has become an indispensable tool in the management of Coronavirus Disease 2019 (COVID-19) lung infection. This study employed deep-learning convolutional neural networks to classify COVID-19 lung infections on pCXR from normal and related lung infections to potentially enable more timely and accurate diagnosis. This retrospect study employed deep-learning convolutional neural network (CNN) with transfer learning to classify based on pCXRs COVID-19 pneumonia (N = 455) on pCXR from normal (N = 532), bacterial pneumonia (N = 492), and non-COVID viral pneumonia (N = 552). The data was randomly split into 75% training and 25% testing, randomly. A five-fold cross-validation was used for the testing set separately. Performance was evaluated using receiver-operating curve analysis. Comparison was made with CNN operated on the whole pCXR and segmented lungs. CNN accurately classified COVID-19 pCXR from those of normal, bacterial pneumonia, and non-COVID-19 viral pneumonia patients in a multiclass model. The overall sensitivity, specificity, accuracy, and AUC were 0.79, 0.93, and 0.79, 0.85 respectively (whole pCXR), and were 0.91, 0.93, 0.88, and 0.89 (CXR of segmented lung). The performance was generally better using segmented lungs. Heatmaps showed that CNN accurately localized areas of hazy appearance, ground glass opacity and/or consolidation on the pCXR. Deep-learning convolutional neural network with transfer learning accurately classifies COVID-19 on portable chest X-ray against normal, bacterial pneumonia or non-COVID viral pneumonia. This approach has the potential to help radiologists and frontline physicians by providing more timely and accurate diagnosis.
Collapse
Affiliation(s)
- Shreeja Kikkisetti
- Radiology, Montefiore Medical Center and Albert Einstein College of Medicine, Bronx, NY, USA
| | - Jocelyn Zhu
- Radiology, Montefiore Medical Center and Albert Einstein College of Medicine, Bronx, NY, USA
| | - Beiyi Shen
- Radiology, State University of New York at Stony Brook, Stony Brook, NY, USA
| | - Haifang Li
- Radiology, State University of New York at Stony Brook, Stony Brook, NY, USA
| | - Tim Q Duong
- Radiology, Montefiore Medical Center and Albert Einstein College of Medicine, Bronx, NY, USA
| |
Collapse
|
1969
|
Lam SE, Noor NM, Bradley DA, Mahmud R, Pawanchek M, Abdul Rashid HA. Small-field output ratio determination using 6 mol% Ge-doped silica fibre dosimeters. Biomed Phys Eng Express 2020; 6. [PMID: 35042836 DOI: 10.1088/2057-1976/abc2a4] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2020] [Accepted: 10/19/2020] [Indexed: 11/12/2022]
Abstract
This work investigates the suitability of locally fabricated 6 mol% Ge-doped optical fibres as dosimeters for small-field output ratio measurements. Two fabrications of fibre, cylindrical (CF) and flat (FF) fibres, were used to measure doses in small photon fields, from 4 to 15 mm. The findings were compared to those of commercial Ge-doped fibre (COMM), EBT3 film and an IBA CC01 ionization chamber. Irradiations were carried out using a 6 MV SRS photon beam operating at a dose rate of 1000 cGy min-1, delivering a dose of 16 Gy. To minimise the possibility of the fibres failing to be exposed to the intended dose in small fields, the fibres were accommodated in a custom-made Perspex phantom. For the 4 mm cone the CF and FF measured output ratios were found to be smaller than obtained with EBT3 film by 32% and 13% respectively. Conversely, while for the 6 to 15 mm cone fields the FF output ratios were consistently greater than those obtained using EBT3 film, the CF output ratios differed from those of EBT3 film by at most 3.2%, at 6 mm, otherwise essentially agreeing with EBT3 values at the other field sizes. For the 4 to 7.5 mm cones, all output ratios obtained from Ge-doped optical fibre measurements were greater than those of IBA CC01 ionization chamber. The measured FF and CF output ratios for the 7.5 to 15 mm cones agreed with published MC estimates to within 15% and 13%, respectively. Down to 6 mm cone field, present measurements point to the potential of CF as a small-field dosimeter, its use recommended to be complemented by the use of EBT3 film for small-field dosimetry.
Collapse
Affiliation(s)
- S E Lam
- Centre for Biomedical Physics, School of Healthcare and Medical Sciences, Sunway University, 47500 Petaling Jaya, Selangor, Malaysia.,Department of Radiology, Faculty of Medicine and Health Sciences, Universiti Putra Malaysia, 43400 Serdang, Selangor, Malaysia
| | - N Mohd Noor
- Department of Radiology, Faculty of Medicine and Health Sciences, Universiti Putra Malaysia, 43400 Serdang, Selangor, Malaysia.,Department of Radiology, Teaching Hospital Universiti Putra Malaysia, 43400 Serdang, Selangor, Malaysia
| | - D A Bradley
- Centre for Biomedical Physics, School of Healthcare and Medical Sciences, Sunway University, 47500 Petaling Jaya, Selangor, Malaysia.,Department of Physics, University of Surrey, Guildford, Surrey GU2 7XH, United Kingdom
| | - R Mahmud
- Department of Radiology, Faculty of Medicine and Health Sciences, Universiti Putra Malaysia, 43400 Serdang, Selangor, Malaysia.,Centre for Diagnostic Nuclear Imaging, Universiti Putra Malaysia, 43400 Serdang, Selangor, Malaysia
| | - M Pawanchek
- Department of Radiotherapy and Oncology, National Cancer Institute, 62250 W.P. Putrajaya, Malaysia
| | - H A Abdul Rashid
- Faculty of Engineering, Multimedia University, 63100 Cyberjaya, Selangor, Malaysia
| |
Collapse
|
1970
|
Zhang P, Zhong Y, Deng Y, Tang X, Li X. CoSinGAN: Learning COVID-19 Infection Segmentation from a Single Radiological Image. Diagnostics (Basel) 2020; 10:E901. [PMID: 33153105 PMCID: PMC7693680 DOI: 10.3390/diagnostics10110901] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2020] [Revised: 10/29/2020] [Accepted: 10/30/2020] [Indexed: 01/17/2023] Open
Abstract
Computed tomography (CT) images are currently being adopted as the visual evidence for COVID-19 diagnosis in clinical practice. Automated detection of COVID-19 infection from CT images based on deep models is important for faster examination. Unfortunately, collecting large-scale training data systematically in the early stage is difficult. To address this problem, we explore the feasibility of learning deep models for lung and COVID-19 infection segmentation from a single radiological image by resorting to synthesizing diverse radiological images. Specifically, we propose a novel conditional generative model, called CoSinGAN, which can be learned from a single radiological image with a given condition, i.e., the annotation mask of the lungs and infected regions. Our CoSinGAN is able to capture the conditional distribution of the single radiological image, and further synthesize high-resolution (512 × 512) and diverse radiological images that match the input conditions precisely. We evaluate the efficacy of CoSinGAN in learning lung and infection segmentation from very few radiological images by performing 5-fold cross validation on COVID-19-CT-Seg dataset (20 CT cases) and an independent testing on the MosMed dataset (50 CT cases). Both 2D U-Net and 3D U-Net, learned from four CT slices by using our CoSinGAN, have achieved notable infection segmentation performance, surpassing the COVID-19-CT-Seg-Benchmark, i.e., the counterparts trained on an average of 704 CT slices, by a large margin. Such results strongly confirm that our method has the potential to learn COVID-19 infection segmentation from few radiological images in the early stage of COVID-19 pandemic.
Collapse
Affiliation(s)
- Pengyi Zhang
- School of Life Science, Beijing Institute of Technology, Haidian District, Beijing 100081, China; (P.Z.); (Y.Z.); (Y.D.); (X.T.)
- Key Laboratory of Convergence Medical Engineering System and Healthcare Technology, Ministry of Industry and Information Technology, Haidian District, Beijing 100081, China
| | - Yunxin Zhong
- School of Life Science, Beijing Institute of Technology, Haidian District, Beijing 100081, China; (P.Z.); (Y.Z.); (Y.D.); (X.T.)
- Key Laboratory of Convergence Medical Engineering System and Healthcare Technology, Ministry of Industry and Information Technology, Haidian District, Beijing 100081, China
| | - Yulin Deng
- School of Life Science, Beijing Institute of Technology, Haidian District, Beijing 100081, China; (P.Z.); (Y.Z.); (Y.D.); (X.T.)
- Key Laboratory of Convergence Medical Engineering System and Healthcare Technology, Ministry of Industry and Information Technology, Haidian District, Beijing 100081, China
| | - Xiaoying Tang
- School of Life Science, Beijing Institute of Technology, Haidian District, Beijing 100081, China; (P.Z.); (Y.Z.); (Y.D.); (X.T.)
- Key Laboratory of Convergence Medical Engineering System and Healthcare Technology, Ministry of Industry and Information Technology, Haidian District, Beijing 100081, China
| | - Xiaoqiong Li
- School of Life Science, Beijing Institute of Technology, Haidian District, Beijing 100081, China; (P.Z.); (Y.Z.); (Y.D.); (X.T.)
- Key Laboratory of Convergence Medical Engineering System and Healthcare Technology, Ministry of Industry and Information Technology, Haidian District, Beijing 100081, China
| |
Collapse
|
1971
|
Ouchicha C, Ammor O, Meknassi M. CVDNet: A novel deep learning architecture for detection of coronavirus (Covid-19) from chest x-ray images. Chaos Solitons Fractals 2020; 140:110245. [PMID: 32921934 PMCID: PMC7472981 DOI: 10.1016/j.chaos.2020.110245] [Citation(s) in RCA: 89] [Impact Index Per Article: 22.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/02/2020] [Accepted: 08/23/2020] [Indexed: 05/02/2023]
Abstract
The COVID-19 pandemic is an emerging respiratory infectious disease, also known as coronavirus 2019. It appears in November 2019 in Hubei province (in China), and more specifically in the city of Wuhan, then spreads in the whole world. As the number of cases increases with unprecedented speed, many parts of the world are facing a shortage of resources and testing. Faced with this problem, physicians, scientists and engineers, including specialists in Artificial Intelligence (AI), have encouraged the development of a Deep Learning model to help healthcare professionals to detect COVID-19 from chest X-ray images and to determine the severity of the infection in a very short time, with low cost. In this paper, we propose CVDNet, a Deep Convolutional Neural Network (CNN) model to classify COVID-19 infection from normal and other pneumonia cases using chest X-ray images. The proposed architecture is based on the residual neural network and it is constructed by using two parallel levels with different kernel sizes to capture local and global features of the inputs. This model is trained on a dataset publically available containing a combination of 219 COVID-19, 1341 normal and 1345 viral pneumonia chest x-ray images. The experimental results reveal that our CVDNet. These results represent a promising classification performance on a small dataset which can be further achieve better results with more training data. Overall, our CVDNet model can be an interesting tool to help radiologists in the diagnosis and early detection of COVID-19 cases.
Collapse
Affiliation(s)
- Chaimae Ouchicha
- Department of Mathematics, Faculty of Science and Technology of Fez S.M.B. Abdellah University, P.O. Box 2202, Morocco
| | - Ouafae Ammor
- Department of Mathematics, Faculty of Science and Technology of Fez S.M.B. Abdellah University, P.O. Box 2202, Morocco
| | - Mohammed Meknassi
- Department of informatics, Faculty of Sciences Dhar El Mehraz S.M.B. Abdellah University, P.O. Box 1796 Atlas Fez, Morocco
| |
Collapse
|
1972
|
Brunese L, Mercaldo F, Reginelli A, Santone A. Explainable Deep Learning for Pulmonary Disease and Coronavirus COVID-19 Detection from X-rays. Comput Methods Programs Biomed 2020; 196:105608. [PMID: 32599338 PMCID: PMC7831868 DOI: 10.1016/j.cmpb.2020.105608] [Citation(s) in RCA: 233] [Impact Index Per Article: 58.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/09/2020] [Accepted: 06/09/2020] [Indexed: 05/03/2023]
Abstract
BACKGROUND AND OBJECTIVE Coronavirus disease (COVID-19) is an infectious disease caused by a new virus never identified before in humans. This virus causes respiratory disease (for instance, flu) with symptoms such as cough, fever and, in severe cases, pneumonia. The test to detect the presence of this virus in humans is performed on sputum or blood samples and the outcome is generally available within a few hours or, at most, days. Analysing biomedical imaging the patient shows signs of pneumonia. In this paper, with the aim of providing a fully automatic and faster diagnosis, we propose the adoption of deep learning for COVID-19 detection from X-rays. METHOD In particular, we propose an approach composed by three phases: the first one to detect if in a chest X-ray there is the presence of a pneumonia. The second one to discern between COVID-19 and pneumonia. The last step is aimed to localise the areas in the X-ray symptomatic of the COVID-19 presence. RESULTS AND CONCLUSION Experimental analysis on 6,523 chest X-rays belonging to different institutions demonstrated the effectiveness of the proposed approach, with an average time for COVID-19 detection of approximately 2.5 seconds and an average accuracy equal to 0.97.
Collapse
Affiliation(s)
- Luca Brunese
- Department of Medicine and Health Sciences "Vincenzo Tiberio", University of Molise, Campobasso, Italy
| | - Francesco Mercaldo
- Department of Medicine and Health Sciences "Vincenzo Tiberio", University of Molise, Campobasso, Italy; Institute for Informatics and Telematics, National Research Council of Italy (CNR), Pisa, Italy
| | - Alfonso Reginelli
- Department of Precision Medicine, University of Campania "Luigi Vanvitelli", Napoli, Italy
| | - Antonella Santone
- Department of Biosciences and Territory, University of Molise, Pesche (IS), Italy
| |
Collapse
|
1973
|
Trivizakis E, Tsiknakis N, Vassalou EE, Papadakis GZ, Spandidos DA, Sarigiannis D, Tsatsakis A, Papanikolaou N, Karantanas AH, Marias K. Advancing COVID-19 differentiation with a robust preprocessing and integration of multi-institutional open-repository computer tomography datasets for deep learning analysis. Exp Ther Med 2020; 20:78. [PMID: 32968435 PMCID: PMC7500043 DOI: 10.3892/etm.2020.9210] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2020] [Accepted: 09/11/2020] [Indexed: 12/15/2022] Open
Abstract
The coronavirus pandemic and its unprecedented consequences globally has spurred the interest of the artificial intelligence research community. A plethora of published studies have investigated the role of imaging such as chest X-rays and computer tomography in coronavirus disease 2019 (COVID-19) automated diagnosis. Οpen repositories of medical imaging data can play a significant role by promoting cooperation among institutes in a world-wide scale. However, they may induce limitations related to variable data quality and intrinsic differences due to the wide variety of scanner vendors and imaging parameters. In this study, a state-of-the-art custom U-Net model is presented with a dice similarity coefficient performance of 99.6% along with a transfer learning VGG-19 based model for COVID-19 versus pneumonia differentiation exhibiting an area under curve of 96.1%. The above was significantly improved over the baseline model trained with no segmentation in selected tomographic slices of the same dataset. The presented study highlights the importance of a robust preprocessing protocol for image analysis within a heterogeneous imaging dataset and assesses the potential diagnostic value of the presented COVID-19 model by comparing its performance to the state of the art.
Collapse
Affiliation(s)
- Eleftherios Trivizakis
- Computational Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece
- Department of Radiology, Medical School, University of Crete, 71003 Heraklion, Greece
| | - Nikos Tsiknakis
- Computational Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece
| | - Evangelia E. Vassalou
- Department of Medical Imaging, University Hospital of Heraklion, 71110 Heraklion, Greece
- Department of Radiology, Sitia District Hospital, 72300 Lasithi, Greece
| | - Georgios Z. Papadakis
- Computational Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece
- Department of Radiology, Medical School, University of Crete, 71003 Heraklion, Greece
| | - Demetrios A. Spandidos
- Laboratory of Clinical Virology, Medical School, University of Crete, 71003 Heraklion, Greece
| | - Dimosthenis Sarigiannis
- HERACLES Research Center on the Exposome and Health, Centre for Interdisciplinary Research and Innovation, Aristotle University of Thessaloniki, 57001 Thermi, Greece
- University School for Advanced Studies IUSS, I-27100 Pavia, Italy
| | - Aristidis Tsatsakis
- Department of Forensic Sciences and Toxicology, Medical School, University of Crete, 71003 Heraklion, Greece
| | - Nikolaos Papanikolaou
- Computational Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece
- Computational Clinical Imaging Group, Centre for the Unknown, Champalimaud Foundation, 1400-038 Lisbon, Portugal
| | - Apostolos H. Karantanas
- Computational Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece
- Department of Radiology, Medical School, University of Crete, 71003 Heraklion, Greece
- Department of Medical Imaging, University Hospital of Heraklion, 71110 Heraklion, Greece
| | - Kostas Marias
- Computational Biomedicine Laboratory (CBML), Foundation for Research and Technology Hellas (FORTH), 70013 Heraklion, Greece
- Department of Electrical and Computer Engineering, Hellenic Mediterranean University, 71410 Heraklion, Greece
| |
Collapse
|
1974
|
Tseng VS, Jia-Ching Ying J, Wong ST, Cook DJ, Liu J. Computational Intelligence Techniques for Combating COVID-19: A Survey. IEEE COMPUT INTELL M 2020. [DOI: 10.1109/mci.2020.3019873] [Citation(s) in RCA: 17] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022]
|
1975
|
Castillo O, Melin P. Forecasting of COVID-19 time series for countries in the world based on a hybrid approach combining the fractal dimension and fuzzy logic. Chaos Solitons Fractals 2020; 140:110242. [PMID: 32863616 PMCID: PMC7444908 DOI: 10.1016/j.chaos.2020.110242] [Citation(s) in RCA: 58] [Impact Index Per Article: 14.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/10/2020] [Revised: 08/10/2020] [Accepted: 08/22/2020] [Indexed: 05/09/2023]
Abstract
We describe in this paper a hybrid intelligent approach for forecasting COVID-19 time series combining fractal theory and fuzzy logic. The mathematical concept of the fractal dimension is used to measure the complexity of the dynamics in the time series of the countries in the world. Fuzzy Logic is used to represent the uncertainty in the process of making a forecast. The hybrid approach consists on a fuzzy model formed by a set of fuzzy rules that use as input values the linear and nonlinear fractal dimensions of the time series and as outputs the forecast for the countries based on the COVID-19 time series of confirmed cases and deaths. The main contribution is the proposed hybrid approach combining the fractal dimension and fuzzy logic for enabling an efficient and accurate forecasting of COVID-19 time series. Publicly available data sets of 10 countries in the world have been used to build the fuzzy model with time series in a fixed period. After that, other periods of time were used to verify the effectiveness of the proposed approach for the forecasted values of the 10 countries. Forecasting windows of 10 and 30 days ahead were used to test the proposed approach. Forecasting average accuracy is 98%, which can be considered good considering the complexity of the COVID problem. The proposed approach can help people in charge of decision making to fight the pandemic can use the information of a short window to decide immediate actions and also the longer window (like 30 days) can be beneficial in long term decisions.
Collapse
|
1976
|
Hassantabar S, Ahmadi M, Sharifi A. Diagnosis and detection of infected tissue of COVID-19 patients based on lung x-ray image using convolutional neural network approaches. Chaos Solitons Fractals 2020; 140:110170. [PMID: 32834651 PMCID: PMC7388764 DOI: 10.1016/j.chaos.2020.110170] [Citation(s) in RCA: 103] [Impact Index Per Article: 25.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/09/2020] [Accepted: 07/27/2020] [Indexed: 05/02/2023]
Abstract
COVID-19 pandemic has challenged the world science. The international community tries to find, apply, or design novel methods for diagnosis and treatment of COVID-19 patients as soon as possible. Currently, a reliable method for the diagnosis of infected patients is a reverse transcription-polymerase chain reaction. The method is expensive and time-consuming. Therefore, designing novel methods is important. In this paper, we used three deep learning-based methods for the detection and diagnosis of COVID-19 patients with the use of X-Ray images of lungs. For the diagnosis of the disease, we presented two algorithms include deep neural network (DNN) on the fractal feature of images and convolutional neural network (CNN) methods with the use of the lung images, directly. Results classification shows that the presented CNN architecture with higher accuracy (93.2%) and sensitivity (96.1%) is outperforming than the DNN method with an accuracy of 83.4% and sensitivity of 86%. In the segmentation process, we presented a CNN architecture to find infected tissue in lung images. Results show that the presented method can almost detect infected regions with high accuracy of 83.84%. This finding also can be used to monitor and control patients from infected region growth.
Collapse
Affiliation(s)
- Shayan Hassantabar
- Department of Electrical Engineering, Princeton University, Princeton, NJ, USA
| | - Mohsen Ahmadi
- Department of Industrial Engineering, Urmia University of Technology, Urmia, Iran
| | - Abbas Sharifi
- Department of Mechanical Engineering, Urmia University of Technology, Urmia, Iran
| |
Collapse
|
1977
|
Panwar H, Gupta PK, Siddiqui MK, Morales-Menendez R, Bhardwaj P, Singh V. A deep learning and grad-CAM based color visualization approach for fast detection of COVID-19 cases using chest X-ray and CT-Scan images. Chaos Solitons Fractals 2020; 140:110190. [PMID: 32836918 PMCID: PMC7413068 DOI: 10.1016/j.chaos.2020.110190] [Citation(s) in RCA: 155] [Impact Index Per Article: 38.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/30/2020] [Accepted: 08/04/2020] [Indexed: 05/17/2023]
Abstract
The world is suffering from an existential global health crisis known as the COVID-19 pandemic. Countries like India, Bangladesh, and other developing countries are still having a slow pace in the detection of COVID-19 cases. Therefore, there is an urgent need for fast detection with clear visualization of infection is required using which a suspected patient of COVID-19 could be saved. In the recent technological advancements, the fusion of deep learning classifiers and medical images provides more promising results corresponding to traditional RT-PCR testing while making detection and predictions about COVID-19 cases with increased accuracy. In this paper, we have proposed a deep transfer learning algorithm that accelerates the detection of COVID-19 cases by using X-ray and CT-Scan images of the chest. It is because, in COVID-19, initial screening of chest X-ray (CXR) may provide significant information in the detection of suspected COVID-19 cases. We have considered three datasets known as 1) COVID-chest X-ray, 2) SARS-COV-2 CT-scan, and 3) Chest X-Ray Images (Pneumonia). In the obtained results, the proposed deep learning model can detect the COVID-19 positive cases in ≤ 2 seconds which is faster than RT-PCR tests currently being used for detection of COVID-19 cases. We have also established a relationship between COVID-19 patients along with the Pneumonia patients which explores the pattern between Pneumonia and COVID-19 radiology images. In all the experiments, we have used the Grad-CAM based color visualization approach in order to clearly interpretate the detection of radiology images and taking further course of action.
Collapse
Affiliation(s)
- Harsh Panwar
- Department of Computer Science and Engineering, Jaypee University of Information Technology, Waknaghat, Solan, HP, 173 234, India
| | - P K Gupta
- Department of Computer Science and Engineering, Jaypee University of Information Technology, Waknaghat, Solan, HP, 173 234, India
| | - Mohammad Khubeb Siddiqui
- School of Engineering and Sciences, Tecnologico de Monterrey, Av. E. Garza Sada 2501, Monterrey, N.L, 64,489, Mexico
| | - Ruben Morales-Menendez
- School of Engineering and Sciences, Tecnologico de Monterrey, Av. E. Garza Sada 2501, Monterrey, N.L, 64,489, Mexico
| | - Prakhar Bhardwaj
- Department of Computer Science and Engineering, Jaypee University of Information Technology, Waknaghat, Solan, HP, 173 234, India
| | - Vaishnavi Singh
- Department of Computer Science and Engineering, Jaypee University of Information Technology, Waknaghat, Solan, HP, 173 234, India
| |
Collapse
|
1978
|
Khan AI, Shah JL, Bhat MM. CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images. Comput Methods Programs Biomed 2020; 196:105581. [PMID: 32534344 PMCID: PMC7274128 DOI: 10.1016/j.cmpb.2020.105581] [Citation(s) in RCA: 474] [Impact Index Per Article: 118.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/10/2020] [Accepted: 05/30/2020] [Indexed: 05/18/2023]
Abstract
BACKGROUND AND OBJECTIVE The novel Coronavirus also called COVID-19 originated in Wuhan, China in December 2019 and has now spread across the world. It has so far infected around 1.8 million people and claimed approximately 114,698 lives overall. As the number of cases are rapidly increasing, most of the countries are facing shortage of testing kits and resources. The limited quantity of testing kits and increasing number of daily cases encouraged us to come up with a Deep Learning model that can aid radiologists and clinicians in detecting COVID-19 cases using chest X-rays. METHODS In this study, we propose CoroNet, a Deep Convolutional Neural Network model to automatically detect COVID-19 infection from chest X-ray images. The proposed model is based on Xception architecture pre-trained on ImageNet dataset and trained end-to-end on a dataset prepared by collecting COVID-19 and other chest pneumonia X-ray images from two different publically available databases. RESULTS CoroNet has been trained and tested on the prepared dataset and the experimental results show that our proposed model achieved an overall accuracy of 89.6%, and more importantly the precision and recall rate for COVID-19 cases are 93% and 98.2% for 4-class cases (COVID vs Pneumonia bacterial vs pneumonia viral vs normal). For 3-class classification (COVID vs Pneumonia vs normal), the proposed model produced a classification accuracy of 95%. The preliminary results of this study look promising which can be further improved as more training data becomes available. CONCLUSION CoroNet achieved promising results on a small prepared dataset which indicates that given more data, the proposed model can achieve better results with minimum pre-processing of data. Overall, the proposed model substantially advances the current radiology based methodology and during COVID-19 pandemic, it can be very helpful tool for clinical practitioners and radiologists to aid them in diagnosis, quantification and follow-up of COVID-19 cases.
Collapse
Affiliation(s)
- Asif Iqbal Khan
- Department of Computer Science, Jamia Millia Islamia, New Delhi, India.
| | | | | |
Collapse
|
1979
|
Toraman S, Alakus TB, Turkoglu I. Convolutional capsnet: A novel artificial neural network approach to detect COVID-19 disease from X-ray images using capsule networks. Chaos Solitons Fractals 2020; 140:110122. [PMID: 32834634 PMCID: PMC7357532 DOI: 10.1016/j.chaos.2020.110122] [Citation(s) in RCA: 103] [Impact Index Per Article: 25.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/23/2020] [Accepted: 07/10/2020] [Indexed: 05/17/2023]
Abstract
Coronavirus is an epidemic that spreads very quickly. For this reason, it has very devastating effects in many areas worldwide. It is vital to detect COVID-19 diseases as quickly as possible to restrain the spread of the disease. The similarity of COVID-19 disease with other lung infections makes the diagnosis difficult. In addition, the high spreading rate of COVID-19 increased the need for a fast system for the diagnosis of cases. For this purpose, interest in various computer-aided (such as CNN, DNN, etc.) deep learning models has been increased. In these models, mostly radiology images are applied to determine the positive cases. Recent studies show that, radiological images contain important information in the detection of coronavirus. In this study, a novel artificial neural network, Convolutional CapsNet for the detection of COVID-19 disease is proposed by using chest X-ray images with capsule networks. The proposed approach is designed to provide fast and accurate diagnostics for COVID-19 diseases with binary classification (COVID-19, and No-Findings), and multi-class classification (COVID-19, and No-Findings, and Pneumonia). The proposed method achieved an accuracy of 97.24%, and 84.22% for binary class, and multi-class, respectively. It is thought that the proposed method may help physicians to diagnose COVID-19 disease and increase the diagnostic performance. In addition, we believe that the proposed method may be an alternative method to diagnose COVID-19 by providing fast screening.
Collapse
Affiliation(s)
- Suat Toraman
- Department of Informatics, Firat University, 23119, Elazig, Turkey
| | - Talha Burak Alakus
- Department of Software Engineering, Kirklareli University, 39000, Kirklareli, Turkey
| | - Ibrahim Turkoglu
- Department of Software Engineering, Firat University, 23119, Elazig, Turkey
| |
Collapse
|
1980
|
Marques G, Agarwal D, de la Torre Díez I. Automated medical diagnosis of COVID-19 through EfficientNet convolutional neural network. Appl Soft Comput 2020; 96:106691. [PMID: 33519327 PMCID: PMC7836808 DOI: 10.1016/j.asoc.2020.106691] [Citation(s) in RCA: 109] [Impact Index Per Article: 27.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2020] [Revised: 08/22/2020] [Accepted: 08/26/2020] [Indexed: 01/18/2023]
Abstract
COVID-19 infection was reported in December 2019 at Wuhan, China. This virus critically affects several countries such as the USA, Brazil, India and Italy. Numerous research units are working at their higher level of effort to develop novel methods to prevent and control this pandemic scenario. The main objective of this paper is to propose a medical decision support system using the implementation of a convolutional neural network (CNN). This CNN has been developed using EfficientNet architecture. To the best of the authors' knowledge, there is no similar study that proposes an automated method for COVID-19 diagnosis using EfficientNet. Therefore, the main contribution is to present the results of a CNN developed using EfficientNet and 10-fold stratified cross-validation. This paper presents two main experiments. First, the binary classification results using images from COVID-19 patients and normal patients are shown. Second, the multi-class results using images from COVID-19, pneumonia and normal patients are discussed. The results show average accuracy values for binary and multi-class of 99.62% and 96.70%, respectively. On the one hand, the proposed CNN model using EfficientNet presents an average recall value of 99.63% and 96.69% concerning binary and multi-class, respectively. On the other hand, 99.64% is the average precision value reported by binary classification, and 97.54% is presented in multi-class. Finally, the average F1-score for multi-class is 97.11%, and 99.62% is presented for binary classification. In conclusion, the proposed architecture can provide an automated medical diagnostics system to support healthcare specialists for enhanced decision making during this pandemic scenario.
Collapse
Affiliation(s)
- Gonçalo Marques
- Department of Signal Theory and Communications, and Telematics Engineering University of Valladolid, Paseo de Belén, 15, 47011 Valladolid, Spain
| | - Deevyankar Agarwal
- Department of Signal Theory and Communications, and Telematics Engineering University of Valladolid, Paseo de Belén, 15, 47011 Valladolid, Spain
| | - Isabel de la Torre Díez
- Department of Signal Theory and Communications, and Telematics Engineering University of Valladolid, Paseo de Belén, 15, 47011 Valladolid, Spain
| |
Collapse
|
1981
|
Stephens H, Deans C, Schlect D, Kairn T. Development of a method for treating lower-eyelid carcinomas using superficial high dose rate brachytherapy. Phys Eng Sci Med 2020; 43:1317-1325. [PMID: 33123861 DOI: 10.1007/s13246-020-00935-7] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2020] [Accepted: 10/03/2020] [Indexed: 11/26/2022]
Abstract
In this study, a method was developed for delivering high dose rate (HDR) brachytherapy treatments to basal cell carcinomas (BCCs) as well as squamous cell carcinomas (SCCs) of the lower eyelid via superficial catheters. Clinically-realistic BCC/SCC treatment areas were marked in the lower-eyelid region on a head phantom and several arrangements of catheters and bolus were trialled for treating those areas. The use of one or two catheters of different types was evaluated, and sources of dosimetric uncertainty (including air gaps) were evaluated and mitigated. Test treatments were planned for delivery with an iridium-192 source, using the Oncentra Brachy treatment planning system (Elekta AB, Stockholm, Sweden). Dose distributions were evaluated using radiochromic film. The proposed method was shown to be clinically viable, for using superficial HDR brachytherapy to overcome anatomical difficulties and create non-surgical treatments for BCC and SCC of the lower eyelid.
Collapse
Affiliation(s)
- H Stephens
- Chermside Medical Complex, Ground Floor, 956 Gympie Road, Chermside, Qld, 4032, Australia.
- School of Physical Sciences, University of Adelaide, North Terrace, Adelaide, SA, 5005, Australia.
| | - C Deans
- Chermside Medical Complex, Ground Floor, 956 Gympie Road, Chermside, Qld, 4032, Australia
- Icon Integrated Cancer Centre, 9 McLennan Ct, North Lakes, Qld, 4509, Australia
| | - D Schlect
- Chermside Medical Complex, Ground Floor, 956 Gympie Road, Chermside, Qld, 4032, Australia
| | - T Kairn
- Cancer Care Services, Royal Brisbane and Women's Hospital, Herston, Qld, 4029, Australia
- Science and Engineering Faculty, Queensland University of Technology, Gardens Point, Qld, 4001, Australia
| |
Collapse
|
1982
|
Casiraghi E, Malchiodi D, Trucco G, Frasca M, Cappelletti L, Fontana T, Esposito AA, Avola E, Jachetti A, Reese J, Rizzi A, Robinson PN, Valentini G. Explainable Machine Learning for Early Assessment of COVID-19 Risk Prediction in Emergency Departments. IEEE Access 2020; 8:196299-196325. [PMID: 34812365 PMCID: PMC8545262 DOI: 10.1109/access.2020.3034032] [Citation(s) in RCA: 31] [Impact Index Per Article: 7.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/16/2020] [Accepted: 10/19/2020] [Indexed: 05/06/2023]
Abstract
Between January and October of 2020, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) virus has infected more than 34 million persons in a worldwide pandemic leading to over one million deaths worldwide (data from the Johns Hopkins University). Since the virus begun to spread, emergency departments were busy with COVID-19 patients for whom a quick decision regarding in- or outpatient care was required. The virus can cause characteristic abnormalities in chest radiographs (CXR), but, due to the low sensitivity of CXR, additional variables and criteria are needed to accurately predict risk. Here, we describe a computerized system primarily aimed at extracting the most relevant radiological, clinical, and laboratory variables for improving patient risk prediction, and secondarily at presenting an explainable machine learning system, which may provide simple decision criteria to be used by clinicians as a support for assessing patient risk. To achieve robust and reliable variable selection, Boruta and Random Forest (RF) are combined in a 10-fold cross-validation scheme to produce a variable importance estimate not biased by the presence of surrogates. The most important variables are then selected to train a RF classifier, whose rules may be extracted, simplified, and pruned to finally build an associative tree, particularly appealing for its simplicity. Results show that the radiological score automatically computed through a neural network is highly correlated with the score computed by radiologists, and that laboratory variables, together with the number of comorbidities, aid risk prediction. The prediction performance of our approach was compared to that that of generalized linear models and shown to be effective and robust. The proposed machine learning-based computational system can be easily deployed and used in emergency departments for rapid and accurate risk prediction in COVID-19 patients.
Collapse
Affiliation(s)
- Elena Casiraghi
- Department of Computer Science “Giovanni degli Antoni,”Università degli Studi di Milano20133MilanItaly
- CINI National Laboratory of Artificial Intelligence and Intelligent Systems (AIIS)Università di Roma00185RomaItaly
| | - Dario Malchiodi
- Department of Computer Science “Giovanni degli Antoni,”Università degli Studi di Milano20133MilanItaly
- CINI National Laboratory of Artificial Intelligence and Intelligent Systems (AIIS)Università di Roma00185RomaItaly
- Data Science Research CenterUniversità degli Studi di Milano20133MilanItaly
| | - Gabriella Trucco
- Department of Computer Science “Giovanni degli Antoni,”Università degli Studi di Milano20133MilanItaly
| | - Marco Frasca
- Department of Computer Science “Giovanni degli Antoni,”Università degli Studi di Milano20133MilanItaly
| | - Luca Cappelletti
- Department of Computer Science “Giovanni degli Antoni,”Università degli Studi di Milano20133MilanItaly
| | - Tommaso Fontana
- Dipartimento di ElettronicaInformazione e BioingegneriaPolitecnico di Milano20133MilanItaly
| | | | - Emanuele Avola
- Postgraduate School in RadiodiagnosticsUniversità degli Studi di Milano20122MilanItaly
| | - Alessandro Jachetti
- Accident and Emergency DepartmentFondazione IRCCS Ca Granda Ospedale Maggiore Policlinico20122MilanItaly
| | - Justin Reese
- Division of Environmental Genomics and Systems BiologyLawrence Berkeley National LaboratoryBerkeleyCA94720USA
| | - Alessandro Rizzi
- Department of Computer Science “Giovanni degli Antoni,”Università degli Studi di Milano20133MilanItaly
| | | | - Giorgio Valentini
- Department of Computer Science “Giovanni degli Antoni,”Università degli Studi di Milano20133MilanItaly
- CINI National Laboratory of Artificial Intelligence and Intelligent Systems (AIIS)Università di Roma00185RomaItaly
- Data Science Research CenterUniversità degli Studi di Milano20133MilanItaly
| |
Collapse
|
1983
|
Kim S, Lee S, Jeong W. EMG Measurement with Textile-Based Electrodes in Different Electrode Sizes and Clothing Pressures for Smart Clothing Design Optimization. Polymers (Basel) 2020; 12:polym12102406. [PMID: 33086662 PMCID: PMC7603359 DOI: 10.3390/polym12102406] [Citation(s) in RCA: 14] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2020] [Revised: 10/15/2020] [Accepted: 10/17/2020] [Indexed: 02/07/2023] Open
Abstract
The surface electromyography (SEMG) is one of the most popular bio-signals that can be applied in health monitoring systems, fitness training, and rehabilitation devices. Commercial clothing embedded with textile electrodes has already been released onto the market, but there is insufficient information on the performance of textile SEMG electrodes because the required configuration may differ according to the electrode material. The current study analyzed the influence of electrode size and pattern reduction rate (PRR), and hence the clothing pressure (Pc) based on in vivo SEMG signal acquisition. Bipolar SEMG electrodes were made in different electrode diameters Ø 5–30 mm, and the clothing pressure ranged from 6.1 to 12.6 mmHg. The results supported the larger electrodes, and Pc showed better SEMG signal quality by showing lower baseline noise and a gradual increase in the signal to noise ratio (SNR). In particular, electrodes, Ø ≥ 20 mm, and Pc ≥ 10 mmHg showed comparable performance to Ag-Ag/Cl electrodes in current textile-based electrodes. The current study emphasizes and discusses design factors that are particularly required in the designing and manufacturing process of smart clothing with SEMG electrodes, especially as an aspect of clothing design.
Collapse
|
1984
|
Abstract
The novel coronavirus 2019 (COVID-19) is a respiratory syndrome that resembles pneumonia. The current diagnostic procedure of COVID-19 follows reverse-transcriptase polymerase chain reaction (RT-PCR) based approach which however is less sensitive to identify the virus at the initial stage. Hence, a more robust and alternate diagnosis technique is desirable. Recently, with the release of publicly available datasets of corona positive patients comprising of computed tomography (CT) and chest X-ray (CXR) imaging; scientists, researchers and healthcare experts are contributing for faster and automated diagnosis of COVID-19 by identifying pulmonary infections using deep learning approaches to achieve better cure and treatment. These datasets have limited samples concerned with the positive COVID-19 cases, which raise the challenge for unbiased learning. Following from this context, this article presents the random oversampling and weighted class loss function approach for unbiased fine-tuned learning (transfer learning) in various state-of-the-art deep learning approaches such as baseline ResNet, Inception-v3, Inception ResNet-v2, DenseNet169, and NASNetLarge to perform binary classification (as normal and COVID-19 cases) and also multi-class classification (as COVID-19, pneumonia, and normal case) of posteroanterior CXR images. Accuracy, precision, recall, loss, and area under the curve (AUC) are utilized to evaluate the performance of the models. Considering the experimental results, the performance of each model is scenario dependent; however, NASNetLarge displayed better scores in contrast to other architectures, which is further compared with other recently proposed approaches. This article also added the visual explanation to illustrate the basis of model classification and perception of COVID-19 in CXR images.
Collapse
|
1985
|
Kairn T, Livingstone AG, Crowe SB. Monte Carlo calculations of radiotherapy dose in "homogeneous" anatomy. Phys Med 2020; 78:156-165. [PMID: 33035927 DOI: 10.1016/j.ejmp.2020.09.019] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/30/2020] [Revised: 09/05/2020] [Accepted: 09/21/2020] [Indexed: 01/27/2023] Open
Abstract
Given the substantial literature on the use of Monte Carlo (MC) simulations to verify treatment planning system (TPS) calculations of radiotherapy dose in heterogeneous regions, such as head and neck and lung, this study investigated the potential value of running MC simulations of radiotherapy treatments of nominally homogeneous pelvic anatomy. A pre-existing in-house MC job submission and analysis system, built around BEAMnrc and DOSXYZnrc, was used to evaluate the dosimetric accuracy of a sample of 12 pelvic volumetric arc therapy (VMAT) treatments, planned using the Varian Eclipse TPS, where dose was calculated with both the Analytical Anisotropic Algorithm (AAA) and the Acuros (AXB) algorithm. In-house TADA (Treatment And Dose Assessor) software was used to evaluate treatment plan complexity, in terms of the small aperture score (SAS), modulation index (MI) and a novel exposed leaf score (ELS/ELA). Results showed that the TPS generally achieved closer agreement with the MC dose distribution when treatments were planned for smaller (single-organ) targets rather than larger targets that included nodes or metastases. Analysis of these MC results with reference to the complexity metrics indicated that while AXB was useful for reducing dosimetric uncertainties associated with density heterogeneity, the residual TPS dose calculation uncertainties resulted from treatment plan complexity and TPS model simplicity. The results of this study demonstrate the value of using MC methods to recalculate and check the dose calculations provided by commercial radiotherapy TPSs, even when the treated anatomy is assumed to be comparatively homogeneous, such as in the pelvic region.
Collapse
Affiliation(s)
- Tanya Kairn
- Royal Brisbane and Women's Hospital, Butterfield Street, Herston, QLD 4029, Australia; Queensland University of Technology, 2 George Street, Brisbane, QLD 4000, Australia.
| | | | - Scott B Crowe
- Royal Brisbane and Women's Hospital, Butterfield Street, Herston, QLD 4029, Australia; Queensland University of Technology, 2 George Street, Brisbane, QLD 4000, Australia
| |
Collapse
|
1986
|
Peet SC, Yu L, Maxwell S, Crowe SB, Trapp JV, Kairn T. Exploring the gamma surface: A new method for visualising modulated radiotherapy quality assurance results. Phys Med 2020; 78:166-172. [PMID: 33035928 DOI: 10.1016/j.ejmp.2020.09.021] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/23/2020] [Revised: 09/23/2020] [Accepted: 09/24/2020] [Indexed: 11/16/2022] Open
Abstract
PURPOSE This work presents a novel method of visualising the results of patient-specific quality assurance (QA) for modulated radiotherapy treatment plans, using a three-dimensional distribution of gamma pass rates, referred to as the "gamma surface". The method was developed to aid in comparing borderline and failing QA plans, and to better compare patient-specific QA results between departments. METHODS Gamma surface plots were created for a representative sample of situations encountered during patient-specific QA. To produce a gamma surface plot, for each QA result, gamma pass rates were plotted as a heat map, with dose difference on one axis and distance-to-agreement on the other. This involved the calculation of 100 × 100 gamma pass rates over a dose difference and distance-to-agreement grid. As examples, five 220 × 680 arrays of dose points from radiotherapy treatment plans were compared against measurement data consisting of 21 × 66 arrays of dose points spaced 10 mm apart. RESULTS The gamma surface plots facilitated the rapid evaluation of criteria combinations for each plan, clearly highlighting the difference between plans that are modelled and delivered well, and those that are not. Large scale features were also evident in each surface, hinting at potential over-modulation, systematic dose errors, and small or large scale areas of disagreement in the distributions. CONCLUSIONS Gamma surface plots are a useful tool for investigating QA failures and borderline results, and have the capacity to grant insights into treatment plan QA performance that may otherwise be missed.
Collapse
Affiliation(s)
- Samuel C Peet
- Royal Brisbane and Women's Hospital, Herston, QLD 4029, Australia; Queensland University of Technology, Brisbane, QLD 4001, Australia.
| | - Liting Yu
- Royal Brisbane and Women's Hospital, Herston, QLD 4029, Australia; Queensland University of Technology, Brisbane, QLD 4001, Australia
| | - Sarah Maxwell
- Royal Brisbane and Women's Hospital, Herston, QLD 4029, Australia
| | - Scott B Crowe
- Royal Brisbane and Women's Hospital, Herston, QLD 4029, Australia; Queensland University of Technology, Brisbane, QLD 4001, Australia
| | - Jamie V Trapp
- Queensland University of Technology, Brisbane, QLD 4001, Australia
| | - Tanya Kairn
- Royal Brisbane and Women's Hospital, Herston, QLD 4029, Australia; Queensland University of Technology, Brisbane, QLD 4001, Australia
| |
Collapse
|
1987
|
Abstract
Covid-19 is a rapidly spreading viral disease that infects not only humans, but animals are also infected because of this disease. The daily life of human beings, their health, and the economy of a country are affected due to this deadly viral disease. Covid-19 is a common spreading disease, and till now, not a single country can prepare a vaccine for COVID-19. A clinical study of COVID-19 infected patients has shown that these types of patients are mostly infected from a lung infection after coming in contact with this disease. Chest x-ray (i.e., radiography) and chest CT are a more effective imaging technique for diagnosing lunge related problems. Still, a substantial chest x-ray is a lower cost process in comparison to chest CT. Deep learning is the most successful technique of machine learning, which provides useful analysis to study a large amount of chest x-ray images that can critically impact on screening of Covid-19. In this work, we have taken the PA view of chest x-ray scans for covid-19 affected patients as well as healthy patients. After cleaning up the images and applying data augmentation, we have used deep learning-based CNN models and compared their performance. We have compared Inception V3, Xception, and ResNeXt models and examined their accuracy. To analyze the model performance, 6432 chest x-ray scans samples have been collected from the Kaggle repository, out of which 5467 were used for training and 965 for validation. In result analysis, the Xception model gives the highest accuracy (i.e., 97.97%) for detecting Chest X-rays images as compared to other models. This work only focuses on possible methods of classifying covid-19 infected patients and does not claim any medical accuracy.
Collapse
|
1988
|
Kimura R, Teramoto A, Ohno T, Saito K, Fujita H. Virtual digital subtraction angiography using multizone patch-based U-Net. Phys Eng Sci Med 2020; 43:1305-1315. [PMID: 33026591 DOI: 10.1007/s13246-020-00933-9] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2020] [Accepted: 09/25/2020] [Indexed: 01/20/2023]
Abstract
Digital subtraction angiography (DSA) is a powerful technique for visualizing blood vessels from X-ray images. However, the subtraction images obtained with this technique suffer from artifacts caused by patient motion. To avoid these artifacts, a new method called "Virtual DSA" is proposed, which generates DSA images directly from a single live image without using a mask image. The proposed Virtual DSA method was developed using the U-Net deep learning architecture. In the proposed method, a virtual DSA image only containing the extracted blood vessels was generated by inputting a single live image into U-Net. To extract the blood vessels more accurately, U-Net operates on each small area via a patch-based process. In addition, a different network was used for each zone to use the local information. The evaluation of the live images of the head confirmed accurate blood vessel extraction without artifacts in the virtual DSA image generated with the proposed method. In this study, the NMSE, PSNR, and SSIM indices were 8.58%, 33.86 dB, and 0.829, respectively. These results indicate that the proposed method can visualize blood vessels without motion artifacts from a single live image.
Collapse
Affiliation(s)
- Ryusei Kimura
- Graduate School of Health Sciences, Fujita Health University, 1-98 Dengakugakubo, Kutsukake-cho, Toyoake-city, Aichi, 470-1192, Japan
| | - Atsushi Teramoto
- Graduate School of Health Sciences, Fujita Health University, 1-98 Dengakugakubo, Kutsukake-cho, Toyoake-city, Aichi, 470-1192, Japan.
| | - Tomoyuki Ohno
- Fujita Health University Bantane Hospital, 3-6-10 Otobashi Nakagawa-ku, Nagoya-city, Aichi, 454-8509, Japan
| | - Kuniaki Saito
- Graduate School of Health Sciences, Fujita Health University, 1-98 Dengakugakubo, Kutsukake-cho, Toyoake-city, Aichi, 470-1192, Japan
| | - Hiroshi Fujita
- Faculty of Engineering, Gifu University, 1-1 Yanagido, Gifu-city, Gifu, 501-1194, Japan
| |
Collapse
|
1989
|
Canayaz M. MH-COVIDNet: Diagnosis of COVID-19 using deep neural networks and meta-heuristic-based feature selection on X-ray images. Biomed Signal Process Control 2020; 64:102257. [PMID: 33042210 PMCID: PMC7538100 DOI: 10.1016/j.bspc.2020.102257] [Citation(s) in RCA: 50] [Impact Index Per Article: 12.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/17/2020] [Revised: 09/29/2020] [Accepted: 10/04/2020] [Indexed: 12/24/2022]
Abstract
COVID-19 is a disease that causes symptoms in the lungs and causes deaths around the world. Studies are ongoing for the diagnosis and treatment of this disease, which is defined as a pandemic. Early diagnosis of this disease is important for human life. This process is progressing rapidly with diagnostic studies based on deep learning. Therefore, to contribute to this field, a deep learning-based approach that can be used for early diagnosis of the disease is proposed in our study. In this approach, a data set consisting of 3 classes of COVID19, normal and pneumonia lung X-ray images was created, with each class containing 364 images. Pre-processing was performed using the image contrast enhancement algorithm on the prepared data set and a new data set was obtained. Feature extraction was completed from this data set with deep learning models such as AlexNet, VGG19, GoogleNet, and ResNet. For the selection of the best potential features, two metaheuristic algorithms of binary particle swarm optimization and binary gray wolf optimization were used. After combining the features obtained in the feature selection of the enhancement data set, they were classified using SVM. The overall accuracy of the proposed approach was obtained as 99.38%. The results obtained by verification with two different metaheuristic algorithms proved that the approach we propose can help experts during COVID-19 diagnostic studies.
Collapse
Affiliation(s)
- Murat Canayaz
- Computer Engineering Department, Engineering Faculty, Van Yuzuncu Yil University, 65000, Van, Turkey
| |
Collapse
|
1990
|
Majeed T, Rashid R, Ali D, Asaad A. Issues associated with deploying CNN transfer learning to detect COVID-19 from chest X-rays. Phys Eng Sci Med 2020; 43:1289-1303. [PMID: 33025386 PMCID: PMC7537970 DOI: 10.1007/s13246-020-00934-8] [Citation(s) in RCA: 26] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2020] [Accepted: 09/25/2020] [Indexed: 12/28/2022]
Abstract
Covid-19 first occurred in Wuhan, China in December 2019. Subsequently, the virus spread throughout the world and as of June 2020 the total number of confirmed cases are above 4.7 million with over 315,000 deaths. Machine learning algorithms built on radiography images can be used as a decision support mechanism to aid radiologists to speed up the diagnostic process. The aim of this work is to conduct a critical analysis to investigate the applicability of convolutional neural networks (CNNs) for the purpose of COVID-19 detection in chest X-ray images and highlight the issues of using CNN directly on the whole image. To accomplish this task, we use 12-off-the-shelf CNN architectures in transfer learning mode on 3 publicly available chest X-ray databases together with proposing a shallow CNN architecture in which we train it from scratch. Chest X-ray images are fed into CNN models without any preprocessing to replicate researches used chest X-rays in this manner. Then a qualitative investigation performed to inspect the decisions made by CNNs using a technique known as class activation maps (CAM). Using CAMs, one can map the activations contributed to the decision of CNNs back to the original image to visualize the most discriminating region(s) on the input image. We conclude that CNN decisions should not be taken into consideration, despite their high classification accuracy, until clinicians can visually inspect and approve the region(s) of the input image used by CNNs that lead to its prediction.
Collapse
Affiliation(s)
- Taban Majeed
- Department of Computer Science and Information Technology, College of Science, Salahaddin University, Erbil, Kurdistan Region, Iraq
| | - Rasber Rashid
- Department of Software Engineering, Faculty of Engineering, Koya University, Koya KOY45, Kurdistan Region, Iraq
| | - Dashti Ali
- Independent Researcher, Toronto, ON Canada
| | - Aras Asaad
- Oxford Drug Design, Oxford Centre for Innovation, New Road, Oxford, OX1 1BY UK
| |
Collapse
|
1991
|
Abstract
The outbreak of Corona Virus Disease 2019 (COVID-19) in Wuhan has significantly impacted the economy and society globally. Countries are in a strict state of prevention and control of this pandemic. In this study, the development trend analysis of the cumulative confirmed cases, cumulative deaths, and cumulative cured cases was conducted based on data from Wuhan, Hubei Province, China from January 23, 2020 to April 6, 2020 using an Elman neural network, long short-term memory (LSTM), and support vector machine (SVM). A SVM with fuzzy granulation was used to predict the growth range of confirmed new cases, new deaths, and new cured cases. The experimental results showed that the Elman neural network and SVM used in this study can predict the development trend of cumulative confirmed cases, deaths, and cured cases, whereas LSTM is more suitable for the prediction of the cumulative confirmed cases. The SVM with fuzzy granulation can successfully predict the growth range of confirmed new cases and new cured cases, although the average predicted values are slightly large. Currently, the United States is the epicenter of the COVID-19 pandemic. We also used data modeling from the United States to further verify the validity of the proposed models.
Collapse
Affiliation(s)
- Yan Hao
- School of Information and Communication Engineering, North University of China, Taiyuan, China
| | - Ting Xu
- Department of Mathematics, School of Science, North University of China, Taiyuan, China
| | - Hongping Hu
- Department of Mathematics, School of Science, North University of China, Taiyuan, China
| | - Peng Wang
- Department of Mathematics, School of Science, North University of China, Taiyuan, China
| | - Yanping Bai
- Department of Mathematics, School of Science, North University of China, Taiyuan, China
- * E-mail:
| |
Collapse
|
1992
|
Yahyaiee Bavil A, Rouhi G. The biomechanical performance of the night-time Providence brace: experimental and finite element investigations. Heliyon 2020; 6:e05210. [PMID: 33102843 PMCID: PMC7575799 DOI: 10.1016/j.heliyon.2020.e05210] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2020] [Revised: 07/20/2020] [Accepted: 10/07/2020] [Indexed: 11/18/2022] Open
Abstract
The main goal of this study was to investigate the performance of a night-time Providence brace, which alters stress distribution in the growth plates and ultimately result in a reduced Cobb angle, from a biomechanical standpoint, using experimental and in-silico tools. A patient with a mild scoliosis (Cobb angle = 17) was chosen for this study. Applied forces from the Providence brace on the patient's rib cage and pelvis were measured using flexible force pads, and the measured forces were then imported to the generated FE model, and their effects on both curvature and stress distribution were observed. The measured mean forces applied by the brace were 29.4 N, 24.7 N, 22.4 N, and 37.6 N in the posterior pelvis, anterior pelvis, superior thorax, and inferior thorax, respectively, in the supine position. Results of the FE model showed that there is curvature overcorrection, and also Cobb angle was reduced from 17°, in the initial configuration, to 3.4° right after using the brace. The stress distribution, resulted from the FE model, in the patient's growth plate with the brace in the supine position, deviates from that of a scoliotic individual without the brace, and was in favor of reducing the Cobb angle. It was observed that by wearing the night time brace, unbalanced stress distribution on the lumbar vertebrae caused by the scoliotic spine's curvatures, can be somehow compensated. The method developed in this study can be employed to optimize existing scoliosis braces from the biomechanical standpoint.
Collapse
|
1993
|
Pang N, Jia P, Liu P, Yin F, Zhou L, Wang L, Yun F, Wang X. A Fuzzy Markov Model for Risk and Reliability Prediction of Engineering Systems: A Case Study of a Subsea Wellhead Connector. Applied Sciences 2020; 10:6902. [DOI: 10.3390/app10196902] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
In production environments, failure data of a complex system are difficult to obtain due to the high cost of experiments; furthermore, using a single model to analyze risk, reliability, availability and uncertainty is a big challenge. Based on the fault tree, fuzzy comprehensive evaluation and Markov method, this paper proposed a fuzzy Markov method that takes the full advantages of the three methods and makes the analysis of risk, reliability, availability and uncertainty all in one. This method uses the fault tree and fuzzy theory to preprocess the input failure data to improve the reliability of the input failure data, and then input the preprocessed failure data into the Markov model; after that iterate and adjust the model when uncertainty events occur, until the data of all events have been processed by the model and the updated model obtained, which best reflects the system state. The wellhead connector of a subsea production system was used as a case study to demonstrate the above method. The obtained reliability index (mean time to failure) of the connector is basically consistent with the failure statistical data from the offshore and onshore reliability database, which verified the accuracy of the proposed method.
Collapse
|
1994
|
R M, M S, H G, A A R, R R. Transfer Learning-Based Automatic Detection of Coronavirus Disease 2019 (COVID-19) from Chest X-ray Images. J Biomed Phys Eng 2020; 10:559-568. [PMID: 33134214 PMCID: PMC7557468 DOI: 10.31661/jbpe.v0i0.2008-1153] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2020] [Accepted: 09/08/2020] [Indexed: 12/20/2022]
Abstract
Background: Coronavirus disease 2019 (COVID-19) is an emerging infectious disease and global health crisis. Although real-time reverse transcription polymerase chain reaction (RT-PCR) is known as the most widely laboratory method to detect the COVID-19 from respiratory specimens. It suffers from several main drawbacks such as time-consuming, high false-negative results, and limited availability. Therefore, the automatically detect of COVID-19 will be required. Objective: This study aimed to use an automated deep convolution neural network based pre-trained transfer models for detection of COVID-19 infection in chest X-rays. Material and Methods: In a retrospective study, we have applied Visual Geometry Group (VGG)-16, VGG-19, MobileNet, and InceptionResNetV2 pre-trained models for detection COVID-19 infection from 348 chest X-ray images. Results: Our proposed models have been trained and tested on a dataset which previously prepared. The all proposed models provide accuracy greater than 90.0%. The pre-trained MobileNet model provides the highest classification performance of automated COVID-19 classification with 99.1% accuracy in comparison with other three proposed models. The plotted area under curve (AUC) of receiver operating characteristics (ROC) of VGG16, VGG19, MobileNet, and InceptionResNetV2 models are 0.92, 0.91, 0.99, and 0.97, respectively. Conclusion: The all proposed models were able to perform binary classification with the accuracy more than 90.0% for COVID-19 diagnosis. Our data indicated that the MobileNet can be considered as a promising model to detect COVID-19 cases. In the future, by increasing the number of samples of COVID-19 chest X-rays to the training dataset, the accuracy and robustness of our proposed models increase further.
Collapse
Affiliation(s)
- Mohammadi R
- MSc, Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Salehi M
- MSc, Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Ghaffari H
- MSc, Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Rohani A A
- MSc, Department of Medical Physics, Tehran University of Medical Sciences, Tehran, Iran
| | - Reiazi R
- PhD, Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
- PhD, Princess Margaret Cancer Centre, University of Toronto, Toronto, Canada
- PhD, Department of Medical Biophysics, University of Toronto, Toronto, Canada
| |
Collapse
|
1995
|
Jain G, Mittal D, Thakur D, Mittal MK. A deep learning approach to detect Covid-19 coronavirus with X-Ray images. Biocybern Biomed Eng 2020; 40:1391-1405. [PMID: 32921862 PMCID: PMC7476608 DOI: 10.1016/j.bbe.2020.08.008] [Citation(s) in RCA: 99] [Impact Index Per Article: 24.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2020] [Revised: 08/26/2020] [Accepted: 08/30/2020] [Indexed: 01/20/2023]
Abstract
Rapid and accurate detection of COVID-19 coronavirus is necessity of time to prevent and control of this pandemic by timely quarantine and medical treatment in absence of any vaccine. Daily increase in cases of COVID-19 patients worldwide and limited number of available detection kits pose difficulty in identifying the presence of disease. Therefore, at this point of time, necessity arises to look for other alternatives. Among already existing, widely available and low-cost resources, X-ray is frequently used imaging modality and on the other hand, deep learning techniques have achieved state-of-the-art performances in computer-aided medical diagnosis. Therefore, an alternative diagnostic tool to detect COVID-19 cases utilizing available resources and advanced deep learning techniques is proposed in this work. The proposed method is implemented in four phases, viz., data augmentation, preprocessing, stage-I and stage-II deep network model designing. This study is performed with online available resources of 1215 images and further strengthen by utilizing data augmentation techniques to provide better generalization of the model and to prevent the model overfitting by increasing the overall length of dataset to 1832 images. Deep network implementation in two stages is designed to differentiate COVID-19 induced pneumonia from healthy cases, bacterial and other virus induced pneumonia on X-ray images of chest. Comprehensive evaluations have been performed to demonstrate the effectiveness of the proposed method with both (i) training-validation-testing and (ii) 5-fold cross validation procedures. High classification accuracy as 97.77%, recall as 97.14% and precision as 97.14% in case of COVID-19 detection shows the efficacy of proposed method in present need of time. Further, the deep network architecture showing averaged accuracy/sensitivity/specificity/precision/F1-score of 98.93/98.93/98.66/96.39/98.15 with 5-fold cross validation makes a promising outcome in COVID-19 detection using X-ray images.
Collapse
Affiliation(s)
- Govardhan Jain
- Department of Electrical Engineering, Medical Engineering and Computer Science (EMI), Hochschule Offenburg, Offenburg, Germany
| | - Deepti Mittal
- Department of Electrical and Instrumentation Engineering, Thapar Institute of Engineering & Technology, Patiala, Punjab, India
| | - Daksh Thakur
- Department of Electrical Engineering, Medical Engineering and Computer Science (EMI), Hochschule Offenburg, Offenburg, Germany
| | - Madhup K Mittal
- Department of Mechanical Engineering, Thapar Institute of Engineering & Technology, Patiala, Punjab, India
| |
Collapse
|
1996
|
Abstract
INTRODUCTION COVID-19 is a recent emerging pandemic whose prognosis is still unclear. Diagnostic tools are the main players that not only indicate a possible infection but can further restrict the transmission and can determine the extent to which disease progression would occur. AREAS COVERED In this paper, we have performed a narrative and critical review on different technology-based diagnostic strategies such as molecular approaches including real-time reverse transcriptase PCR, serological testing through enzyme-linked immunosorbent assay, laboratory and point of care devices, radiology-based detection through computed tomography and chest X-ray, and viral cell cultures on Vero E6 cell lines are discussed in detail to address COVID-19. This review further provides an overview of emergency use authorized immunodiagnostic and molecular diagnostic kits and POC devices by FDA for timely and efficient conduction of diagnostic tests. The majority of the literature cited in this paper is collected from guidelines on protocols and other considerations on diagnostic strategies of COVID-19 issued by WHO, CDC, and FDA under emergency authorization. EXPERT OPINION Such information holds importance to the health professionals in conducting error-free diagnostic tests and researches in producing better clinical strategies by addressing the limitations associated with the available methods.
Collapse
Affiliation(s)
- Purva Asrani
- Division of Biochemistry, Indian Agricultural Research Institute , New Delhi, India
| | - Mathew Suji Eapen
- Respiratory Translational Research Group, Department of Laboratory Medicine, School of Health Sciences, College of Health and Medicine, University of Tasmania , Launceston, Australia
| | - Collin Chia
- Respiratory Translational Research Group, Department of Laboratory Medicine, School of Health Sciences, College of Health and Medicine, University of Tasmania , Launceston, Australia.,Department of Respiratory Medicine, Launceston General Hospital , Launceston, Australia
| | - Greg Haug
- Respiratory Translational Research Group, Department of Laboratory Medicine, School of Health Sciences, College of Health and Medicine, University of Tasmania , Launceston, Australia.,Department of Respiratory Medicine, Launceston General Hospital , Launceston, Australia
| | - Heinrich C Weber
- Respiratory Translational Research Group, Department of Laboratory Medicine, School of Health Sciences, College of Health and Medicine, University of Tasmania , Launceston, Australia.,Department of Respiratory Medicine, Tasmanian Health Services (THS), North West Hospital , Burnie, Australia
| | - Md Imtaiyaz Hassan
- Centre for Interdisciplinary Research in Basic Sciences, Jamia Millia Islamia , New Delhi, India
| | - Sukhwinder Singh Sohal
- Respiratory Translational Research Group, Department of Laboratory Medicine, School of Health Sciences, College of Health and Medicine, University of Tasmania , Launceston, Australia
| |
Collapse
|
1997
|
Ulhaq A, Born J, Khan A, Gomes DPS, Chakraborty S, Paul M. COVID-19 Control by Computer Vision Approaches: A Survey. IEEE Access 2020; 8:179437-179456. [PMID: 34812357 PMCID: PMC8545281 DOI: 10.1109/access.2020.3027685] [Citation(s) in RCA: 30] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/22/2020] [Accepted: 09/26/2020] [Indexed: 05/03/2023]
Abstract
The COVID-19 pandemic has triggered an urgent call to contribute to the fight against an immense threat to the human population. Computer Vision, as a subfield of artificial intelligence, has enjoyed recent success in solving various complex problems in health care and has the potential to contribute to the fight of controlling COVID-19. In response to this call, computer vision researchers are putting their knowledge base at test to devise effective ways to counter COVID-19 challenge and serve the global community. New contributions are being shared with every passing day. It motivated us to review the recent work, collect information about available research resources, and an indication of future research directions. We want to make it possible for computer vision researchers to find existing and future research directions. This survey article presents a preliminary review of the literature on research community efforts against COVID-19 pandemic.
Collapse
Affiliation(s)
- Anwaar Ulhaq
- School of Computing and MathematicsCharles Sturt UniversityPort MacquarieNSW2795Australia
| | - Jannis Born
- Department for Biosystems Science and EngineeringETH Zurich4058BaselSwitzerland
| | - Asim Khan
- College of Engineering and ScienceVictoria UniversityMelbourneVIC3011Australia
| | | | - Subrata Chakraborty
- Faculty of Engineering and Information TechnologyUniversity of Technology SydneySydneyNSW2007Australia
| | - Manoranjan Paul
- School of Computing and MathematicsCharles Sturt UniversityPort MacquarieNSW2795Australia
| |
Collapse
|
1998
|
Chakraborty S, Choudhary AK, Sarma M, Hazarika MK. Reaction order and neural network approaches for the simulation of COVID-19 spreading kinetic in India. Infect Dis Model 2020; 5:737-747. [PMID: 32989426 PMCID: PMC7511200 DOI: 10.1016/j.idm.2020.09.002] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/29/2020] [Revised: 09/01/2020] [Accepted: 09/20/2020] [Indexed: 11/29/2022] Open
Abstract
COVID-19 has created a pandemic situation in the whole world. Controlling of COVID-19 spreading rate in the social environment is a challenge for all individuals. In the present study, simulation of the lockdown effect on the COVID-19 spreading rate in India and mapping of its recovery percentage (until May 2020) were investigated. Investigation of the lockdown impact dependent on first order reaction kinetics demonstrated higher effect of lockdown 1 on controlling the COVID-19 spreading rate when contrasted with lockdown 2 and 3. Although decreasing trend was followed for the reaction rate constant of different lockdown stages, the distinction between the lockdown 2 and 3 was minimal. Mathematical and feed forward neural network (FFNN) approaches were applied for the simulation of COVID-19 spreading rate. In case of mathematical approach, exponential model indicated adequate performance for the prediction of the spreading rate behavior. For the FFNN based modeling, 1-5-1 was selected as the best architecture so as to predict adequate spreading rate for all the cases. The architecture also showed effective performance in order to forecast number of cases for next 14 days. The recovery percentage was modeled as a function of number of days with the assistance of polynomial fitting. Therefore, the investigation recommends proper social distancing and efficient management of corona virus in order to achieve higher decreasing trend of reaction rate constant and required recovery percentage for the stabilization of India.
Collapse
Affiliation(s)
- Sourav Chakraborty
- Department of Food Engineering and Technology, Tezpur University, Assam, 784028, India
| | - Arun Kumar Choudhary
- Department of Agricultural Engineering, North Eastern Regional Institute of Science and Technology (NERIST), Arunachal Pradesh, 791109, India
| | - Mausumi Sarma
- Department of Food Engineering and Technology, Tezpur University, Assam, 784028, India
| | - Manuj Kumar Hazarika
- Department of Food Engineering and Technology, Tezpur University, Assam, 784028, India
| |
Collapse
|
1999
|
Tartaglione E, Barbano CA, Berzovini C, Calandri M, Grangetto M. Unveiling COVID-19 from CHEST X-Ray with Deep Learning: A Hurdles Race with Small Data. Int J Environ Res Public Health 2020; 17:E6933. [PMID: 32971995 PMCID: PMC7557723 DOI: 10.3390/ijerph17186933] [Citation(s) in RCA: 91] [Impact Index Per Article: 22.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/11/2020] [Revised: 09/11/2020] [Accepted: 09/14/2020] [Indexed: 12/19/2022]
Abstract
The possibility to use widespread and simple chest X-ray (CXR) imaging for early screening of COVID-19 patients is attracting much interest from both the clinical and the AI community. In this study we provide insights and also raise warnings on what is reasonable to expect by applying deep learning to COVID classification of CXR images. We provide a methodological guide and critical reading of an extensive set of statistical results that can be obtained using currently available datasets. In particular, we take the challenge posed by current small size COVID data and show how significant can be the bias introduced by transfer-learning using larger public non-COVID CXR datasets. We also contribute by providing results on a medium size COVID CXR dataset, just collected by one of the major emergency hospitals in Northern Italy during the peak of the COVID pandemic. These novel data allow us to contribute to validate the generalization capacity of preliminary results circulating in the scientific community. Our conclusions shed some light into the possibility to effectively discriminate COVID using CXR.
Collapse
Affiliation(s)
- Enzo Tartaglione
- Computer Science Department, University of Turin, 10149 Torino, Italy; (C.A.B.); (M.G.)
| | - Carlo Alberto Barbano
- Computer Science Department, University of Turin, 10149 Torino, Italy; (C.A.B.); (M.G.)
| | - Claudio Berzovini
- Azienda Ospedaliera Città della Salute e della Scienza Presidio Molinette, 10126 Torino, Italy;
| | - Marco Calandri
- Oncology Department, University of Turin, AOU San Luigi Gonzaga, 10043 Orbassano, Italy;
| | - Marco Grangetto
- Computer Science Department, University of Turin, 10149 Torino, Italy; (C.A.B.); (M.G.)
| |
Collapse
|
2000
|
Abstract
Deep Learning has improved multi-fold in recent years and it has been playing a great role in image classification which also includes medical imaging. Convolutional Neural Networks (CNNs) have been performing well in detecting many diseases including coronary artery disease, malaria, Alzheimer’s disease, different dental diseases, and Parkinson’s disease. Like other cases, CNN has a substantial prospect in detecting COVID-19 patients with medical images like chest X-rays and CTs. Coronavirus or COVID-19 has been declared a global pandemic by the World Health Organization (WHO). As of 8 August 2020, the total COVID-19 confirmed cases are 19.18 M and deaths are 0.716 M worldwide. Detecting Coronavirus positive patients is very important in preventing the spread of this virus. On this conquest, a CNN model is proposed to detect COVID-19 patients from chest X-ray images. Two more CNN models with different number of convolution layers and three other models based on pretrained ResNet50, VGG-16 and VGG-19 are evaluated with comparative analytical analysis. All six models are trained and validated with Dataset 1 and Dataset 2. Dataset 1 has 201 normal and 201 COVID-19 chest X-rays whereas Dataset 2 is comparatively larger with 659 normal and 295 COVID-19 chest X-ray images. The proposed model performs with an accuracy of 98.3% and a precision of 96.72% with Dataset 2. This model gives the Receiver Operating Characteristic (ROC) curve area of 0.983 and F1-score of 98.3 with Dataset 2. Moreover, this work shows a comparative analysis of how change in convolutional layers and increase in dataset affect classifying performances.
Collapse
|