Objective: The aim of this study is to develop a high-performance model and web-based clinical decision making method to successfully distinguish and classify COVID19 from bacterial pneumonia, viral pneumonia and healthy controls with lung ultrasound (LUS) videos using appropriate video processing techniques and artificial intelligence (AI) methods development of the support system. Material and Methods: In this study, the open source LUS video dataset at https://github.com/jannisborn/covid19_ultrasound was used. The dataset includes 32 healthy controls, 24 COVID-19, 24 bacterial pneumonia and 12 viral pneumonia class videos. In the video processing stage, 300 image frames were taken from the videos in each class. The images were divided into 80% (960) training and 20% (240) test datasets. In the modeling phase, the convolutional neural network (CNN) method, one of the deep neural network architectures in the keras library, was used. Accuracy, sensitivity, specificity, precision, Matthews' correlation coefficient and F1 score criteria are given to evaluate the performance of the model. A web-based system has been developed that can successfully detect COVID-19 using the, with the help of the AI-based model, Python Flask Library. Results: The accuracy in the test dataset was calculated as 93.39% for healthy control, COVID-19 and viral pneumonia, and 95.07% for bacterial pneumonia. Conclusion: According to the performance criteria values obtained with the video processing-based CNN model, it can be said that the developed system gives very successful predictions in the diagnosis of COVID-19, bacterial pneumonia and viral pneumonia.
Keywords: COVID-19; deep learning; video processing; image processing; convolutional neural networks
Amaç: Bu çalışmanın amacı, uygun video işleme teknikleri ve yapay zekâ yöntemleri kullanılarak akciğer ultrason videoları ile COVID19'u bakteriyel pnömoni, viral pnömoni ve sağlıklı kontrollerden başarılı bir şekilde ayırt ederek sınıflandırmak için yüksek performansa sahip bir modelin ve web tabanlı klinik karar destek sisteminin geliştirilmesidir. Gereç ve Yöntemler: Bu çalışmada, https://github.com/jannisborn/covid19_ultrasound adresindeki açık kaynaklı akciğer ultrason video veri seti kullanılmıştır. Veri setinde bulunan videoların 32'si sağlıklı kontrol, 24'ü COVID-19, 24'ü bakteriyel pnömoni ve 12'si viral pnömoni şeklinde klinik olarak sınıflandırılmıştır. Video işleme aşamasında, her bir sınıftaki videolardan 300 görüntü karesi alınmıştır. Görüntülerin %80'i (960) eğitim ve %20'si (240) test veri seti olarak bölünmüştür. Modelleme aşamasında, keras kütüphanesinde bulunan derin sinir ağları mimarilerinden evrişimli sinir ağları CNN yöntemi kullanılmıştır. Oluşturulan modelin performansını değerlendirmek için doğruluk, duyarlılık, seçicilik, kesinlik, Matthews'in korelasyon katsayısı ve F1 skoru ölçütleri verilmiştir. Bunlara ek olarak oluşturulan yapay zekâ tabanlı model ile, Python Flask Kütüphanesi kullanılarak COVID-19'U başarılı bir şekilde tespit edebilen web tabanlı bir sistem geliştirilmiştir. Bulgular: Test veri setinde doğruluk sağlıklı kontrol, COVID-19 ve viral pnömoni için %93,39 ve bakteriyel pnömoni için ise %95,07 olarak hesaplanmıştır. Sonuç: Önerilen video işleme tabanlı CNN modeli ile elde edilen performans ölçütlerine göre geliştirilen sistemin COVID-19, bakteriyel pnömoni ve viral pnömoni tanısında oldukça başarılı tahminler verdiği ve klinik karar destek amacıyla kullanılabileceği söylenebilir.
Anahtar Kelimeler: COVID-19; derin öğrenme; video işleme; görüntü işleme; evrişimli sinir ağları
- Yağın FH, Güldoğan E, Ucuzal H, Çolak C. A Computer-assisted diagnosis tool for classifying COVID-19 based on chest X-Ray images. Konuralp Medical Journal. 2021;13(S1):438-45. [Crossref]
- Muhammad G, Shamim Hossain M. COVID-19 and non-COVID-19 classification using multi-layers fusion from lung ultrasound images. Inf Fusion. 2021;72:80-8. [Crossref] [PubMed] [PMC]
- Hassantabar S, Stefano N, Ghanakota V, Ferrari A, Nicola GN, Bruno R, et al. Coviddeep: Sars-cov-2/covid-19 test based on wearable medical sensors and efficient neural networks. arXiv preprint arXiv. 2020;200710497. [Crossref]
- Ai T, Yang Z, Hou H, Zhan C, Chen C, Lv W, et al. Correlation of chest CT and RT-PCR testing for coronavirus disease 2019 (COVID-19) in China: A report of 1014 cases. Radiology. 2020;296(2):E32-E40. [Crossref] [PubMed] [PMC]
- Chung M, Bernheim A, Mei X, Zhang N, Huang M, Zeng X, et al. CT imaging features of 2019 novel coronavirus (2019-nCoV). Radiology. 2020;295(1):202-7. [Crossref] [PubMed] [PMC]
- Roy S, Menapace W, Oei S, Luijten B, Fini E, Saltori C, et al. Deep learning for classification and localization of COVID-19 markers in point-of-care lung ultrasound. IEEE Trans Med Imaging. 2020;39(8):2676-87. [Crossref] [PubMed]
- Mahmud T, Rahman MA, Fattah SA. CovXNet: A multi-dilation convolutional neural network for automatic COVID-19 and other pneumonia detection from chest X-ray images with transferable multi-receptive feature optimization. Comput Biol Med. 2020;122:103869. [Crossref] [PubMed] [PMC]
- Fan L, Li D, Xue H, Zhang L, Liu Z, Zhang B, et al. Progress and prospect on imaging diagnosis of COVID-19. Chin J Acad Radiol. 2020:1-10. [Crossref] [PubMed] [PMC]
- Amatya Y, Rupp J, Russell FM, Saunders J, Bales B, House DR. Diagnostic use of lung ultrasound compared to chest radiograph for suspected pneumonia in a resource-limited setting. Int J Emerg Med. 2018;11(1):8. [Crossref] [PubMed] [PMC]
- Born J, Wiedemann N, Brändle G, Buhre C, Rieck B, Borgwardt K. Accelerating covid-19 differential diagnosis with explainable ultrasound image analysis. arXiv preprint arXiv. 2020;200906116. [Crossref]
- Yağın FH, Güldoğan E, Çolak C. A web-based software for the calculation of theoretical probability distributions. The Journal of Cognitive Systems. 2021;6(1):44-50. [Crossref]
- Yağın B, Yağın FH, Gözükara Bag HG, Çolak C. A web-based software for reporting guidelines of scientific researches. The Journal of Cognitive Systems. 2021;6(1):39-43. [Crossref]
- Yağın FH, Yağın B, Çolak C. An interactive web-based software for epidemiological research designs. Middle Black Sea Journal of Health Science. 2021;7(1):122-31. [Crossref]
- Yılmaz R, Yağın FH. Early detection of coronary heart disease based on machine learning methods. Medical Records. 2022;4(1):1-6. [Link]
- Yılmaz R, Yağın FH. A comparative study for the prediction of heart attack risk and associated factors using MLP and RBF neural networks. The Journal of Cognitive Systems. 2021;6(2):51-4. [Link]
- Perçin İ, Yağın FH, Güldoğan E, Yoloğlu S. ARM: An interactive web software for association rules mining and an application in medicine. 2019 International Artificial Intelligence and Data Processing Symposium (IDAP); IEEE. 2019. [Crossref]
- Perçin İ, Yağın FH, Arslan AK, Çolak C. An interactive web tool for classification problems based on machine learning algorithms using java programming language: data classification software. 2019 3rd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT); IEEE. 2019. [Crossref]
- Yagin FH, Kucukkakcali Z, Cicek IB, Gozukara Bag HG. The effects of variable selection and dimension reduction methods on the classification model in the small round blue cell tumor dataset. Middle Black Sea Journal of Health Science. 2021;7(3):390-6. [Crossref]
- Yagin FH, Cicek IB, Kucukakcali Z. Classification of stroke with gradient boosting tree using smote-based oversampling method. Medicine. 2021;10(4):1510-5. [Crossref]
- Kang Z, Li X, Zhou S. Recommendation of low-dose CT in the detection and management of COVID-2019. Eur Radiol. 2020;30(8):4356-7. [Crossref] [PubMed] [PMC]
- Ahmad F, Farooq A, Ghani MU. Deep ensemble model for classification of novel coronavirus in chest X-ray images. Comput Intell Neurosci. 2021;2021:8890226. [Crossref] [PubMed] [PMC]
- Ismael AM, Şengür A. Deep learning approaches for COVID-19 detection based on chest X-ray images. Expert Syst Appl. 2021;164:114054. [Crossref] [PubMed] [PMC]
- Abbas A, Abdelsamea MM, Gaber MM. Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network. Appl Intell (Dordr). 2020:1-11. [Crossref] [PubMed] [PMC]
- Hu Z, Liu Z, Dong Y, Liu J, Huang B, Liu A, et al. Evaluation of lung involvement in COVID-19 pneumonia based on ultrasound images. Biomed Eng Online. 2021;20(1):27. [Crossref] [PubMed] [PMC]
- Born J, Brändle G, Cossio M, Disdier M, Goulet J, Roulin J, et al. POCOVID-Net: automatic detection of COVID-19 from a new lung ultrasound imaging dataset (POCUS). arXiv preprint arXiv. 2020;200412084. [Link]
.: İşlem Listesi