Comparing Visual Scoring of Lung Injury with a Quantifying AI-Based Scoring in Patients with COVID-19.

IF 2 4区医学 Q4 Medicine

Journal of the Belgian Society of Radiology Pub Date : 2021-04-05 DOI:10.5334/jbsr.2330

Charlotte Biebau, Adriana Dubbeldam, Lesley Cockmartin, Walter Coudyze, Johan Coolen, Johny Verschakelen, Walter De Wever

{"title":"Comparing Visual Scoring of Lung Injury with a Quantifying AI-Based Scoring in Patients with COVID-19.","authors":"Charlotte Biebau, Adriana Dubbeldam, Lesley Cockmartin, Walter Coudyze, Johan Coolen, Johny Verschakelen, Walter De Wever","doi":"10.5334/jbsr.2330","DOIUrl":null,"url":null,"abstract":"Objectives: Fast diagnosis of Coronavirus Disease 2019 (COVID-19), and the detection of high-risk patients are crucial but challenging in the pandemic outbreak. The aim of this study was to evaluate if deep learning-based software correlates well with the generally accepted visual-based scoring for quantification of the lung injury to help radiologist in triage and monitoring of COVID-19 patients.Materials and methods: In this retrospective study, the lobar analysis of lung opacities (% opacities) by means of a prototype deep learning artificial intelligence (AI)-based software was compared to visual scoring. The visual scoring system used five categories (0: 0%, 1: 0-5%, 2: 5-25%, 3: 25-50%, 4: 50-75% and 5: >75% involvement). The total visual lung injury was obtained by the sum of the estimated grade of involvement of each lobe and divided by five.Results: The dataset consisted of 182 consecutive confirmed COVID-19 positive patients with a median age of 65 ± 16 years, including 110 (60%) men and 72 (40%) women. There was a correlation coefficient of 0.89 (p < 0.001) between the visual and the AI-based estimates of the severity of lung injury.Conclusion: The study indicates a very good correlation between the visual scoring and AI-based estimates of lung injury in COVID-19.","PeriodicalId":56282,"journal":{"name":"Journal of the Belgian Society of Radiology","volume":"105 1","pages":"16"},"PeriodicalIF":2.0000,"publicationDate":"2021-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8034398/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the Belgian Society of Radiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.5334/jbsr.2330","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Medicine","Score":null,"Total":0}

引用次数: 0

Abstract

Objectives: Fast diagnosis of Coronavirus Disease 2019 (COVID-19), and the detection of high-risk patients are crucial but challenging in the pandemic outbreak. The aim of this study was to evaluate if deep learning-based software correlates well with the generally accepted visual-based scoring for quantification of the lung injury to help radiologist in triage and monitoring of COVID-19 patients.

Materials and methods: In this retrospective study, the lobar analysis of lung opacities (% opacities) by means of a prototype deep learning artificial intelligence (AI)-based software was compared to visual scoring. The visual scoring system used five categories (0: 0%, 1: 0-5%, 2: 5-25%, 3: 25-50%, 4: 50-75% and 5: >75% involvement). The total visual lung injury was obtained by the sum of the estimated grade of involvement of each lobe and divided by five.

Results: The dataset consisted of 182 consecutive confirmed COVID-19 positive patients with a median age of 65 ± 16 years, including 110 (60%) men and 72 (40%) women. There was a correlation coefficient of 0.89 (p < 0.001) between the visual and the AI-based estimates of the severity of lung injury.

Conclusion: The study indicates a very good correlation between the visual scoring and AI-based estimates of lung injury in COVID-19.

Abstract Image

查看原文本刊更多论文

比较 COVID-19 患者肺损伤的目视评分与基于人工智能的量化评分。

目的：快速诊断冠状病毒病 2019 (COVID-19)和检测高危患者至关重要，但在大流行疫情中具有挑战性。本研究旨在评估基于深度学习的软件与公认的基于视觉的肺损伤量化评分是否具有良好的相关性，以帮助放射科医生分流和监测 COVID-19 患者：在这项回顾性研究中，通过基于深度学习人工智能（AI）的原型软件对肺部不透气度（不透气度百分比）进行了分析，并与视觉评分进行了比较。视觉评分系统分为五个类别（0：0%；1：0-5%；2：5-25%；3：25-50%；4：50-75%；5：>75%）。每个肺叶受累程度的估计值之和除以 5 即为目视肺损伤总值：数据集包括 182 名连续确诊的 COVID-19 阳性患者，中位年龄为 65 ± 16 岁，其中男性 110 人（60%），女性 72 人（40%）。对肺损伤严重程度的目测估计值和基于人工智能的估计值之间的相关系数为 0.89（P < 0.001）：研究表明，在 COVID-19 中，肺损伤的目测评分与基于人工智能的估计值之间存在很好的相关性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of the Belgian Society of Radiology Medicine-Radiology, Nuclear Medicine and Imaging

CiteScore

0.60

自引率

5.00%

发文量

审稿时长

6-12 weeks

期刊介绍： The purpose of the Journal of the Belgian Society of Radiology is the publication of articles dealing with diagnostic and interventional radiology, related imaging techniques, allied sciences, and continuing education.