Sara Ghashghaei, David A. Wood, Erfan Sadatshojaei, Mansooreh Jalilpoor
{"title":"Grayscale image statistics of COVID-19 patient CT scans characterize lung condition with machine and deep learning","authors":"Sara Ghashghaei, David A. Wood, Erfan Sadatshojaei, Mansooreh Jalilpoor","doi":"10.1002/cdt3.27","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Grayscale image attributes of computed tomography (CT) of pulmonary scans contain valuable information relating to patients with respiratory ailments. These attributes are used to evaluate the severity of lung conditions of patients confirmed to be with and without COVID-19.</p>\n </section>\n \n <section>\n \n <h3> Method</h3>\n \n <p>Five hundred thirteen CT images relating to 57 patients (49 with COVID-19; 8 free of COVID-19) were collected at Namazi Medical Centre (Shiraz, Iran) in 2020 and 2021. Five visual scores (VS: 0, 1, 2, 3, or 4) are clinically assigned to these images with the score increasing with the severity of COVID-19-related lung conditions. Eleven deep learning and machine learning techniques (DL/ML) are used to distinguish the VS class based on 12 grayscale image attributes.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>The convolutional neural network achieves 96.49% VS accuracy (18 errors from 513 images) successfully distinguishing VS Classes 0 and 1, outperforming clinicians’ visual inspections. An algorithmic score (AS), involving just five grayscale image attributes, is developed independently of clinicians’ assessments (99.81% AS accuracy; 1 error from 513 images).</p>\n </section>\n \n <section>\n \n <h3> Conclusion</h3>\n \n <p>Grayscale CT image attributes can be successfully used to distinguish the severity of COVID-19 lung damage. The AS technique developed provides a suitable basis for an automated system using ML/DL methods and 12 image attributes.</p>\n </section>\n </div>","PeriodicalId":32096,"journal":{"name":"Chronic Diseases and Translational Medicine","volume":"8 3","pages":"191-206"},"PeriodicalIF":0.0000,"publicationDate":"2022-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/de/a5/CDT3-8-191.PMC9347876.pdf","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Chronic Diseases and Translational Medicine","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/cdt3.27","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 2
Abstract
Background
Grayscale image attributes of computed tomography (CT) of pulmonary scans contain valuable information relating to patients with respiratory ailments. These attributes are used to evaluate the severity of lung conditions of patients confirmed to be with and without COVID-19.
Method
Five hundred thirteen CT images relating to 57 patients (49 with COVID-19; 8 free of COVID-19) were collected at Namazi Medical Centre (Shiraz, Iran) in 2020 and 2021. Five visual scores (VS: 0, 1, 2, 3, or 4) are clinically assigned to these images with the score increasing with the severity of COVID-19-related lung conditions. Eleven deep learning and machine learning techniques (DL/ML) are used to distinguish the VS class based on 12 grayscale image attributes.
Results
The convolutional neural network achieves 96.49% VS accuracy (18 errors from 513 images) successfully distinguishing VS Classes 0 and 1, outperforming clinicians’ visual inspections. An algorithmic score (AS), involving just five grayscale image attributes, is developed independently of clinicians’ assessments (99.81% AS accuracy; 1 error from 513 images).
Conclusion
Grayscale CT image attributes can be successfully used to distinguish the severity of COVID-19 lung damage. The AS technique developed provides a suitable basis for an automated system using ML/DL methods and 12 image attributes.
期刊介绍:
This journal aims to promote progress from basic research to clinical practice and to provide a forum for communication among basic, translational, and clinical research practitioners and physicians from all relevant disciplines. Chronic diseases such as cardiovascular diseases, cancer, diabetes, stroke, chronic respiratory diseases (such as asthma and COPD), chronic kidney diseases, and related translational research. Topics of interest for Chronic Diseases and Translational Medicine include Research and commentary on models of chronic diseases with significant implications for disease diagnosis and treatment Investigative studies of human biology with an emphasis on disease Perspectives and reviews on research topics that discuss the implications of findings from the viewpoints of basic science and clinical practic.