[论文解读] Early Screening of SARS-CoV-2 by Intelligent Analysis of X-Ray Images

Débora Gil, Katerine Díaz-Chito+2 more|arXiv (Cornell University)|May 28, 2020

COVID-19 diagnosis using AI参考文献 27被引用 10

一句话总结

本研究提出一种基于直方图梯度（HoG）与降维的经典机器学习方法，用于从X光片中早期筛查SARS-CoV-2。该方法在区分COVID-19、正常、肺炎及非COVID-19浸润病例方面实现了96%的准确率（accuracy）和98%的召回率（recall），优于深度学习方法，并发现非COVID-19浸润与COVID-19在影像学上最为相似，因此需要结合临床数据以提高特异性。

ABSTRACT

Future SARS-CoV-2 virus outbreak COVID-XX might possibly occur during the next years. However the pathology in humans is so recent that many clinical aspects, like early detection of complications, side effects after recovery or early screening, are currently unknown. In spite of the number of cases of COVID-19, its rapid spread putting many sanitary systems in the edge of collapse has hindered proper collection and analysis of the data related to COVID-19 clinical aspects. We describe an interdisciplinary initiative that integrates clinical research, with image diagnostics and the use of new technologies such as artificial intelligence and radiomics with the aim of clarifying some of SARS-CoV-2 open questions. The whole initiative addresses 3 main points: 1) collection of standardize data including images, clinical data and analytics; 2) COVID-19 screening for its early diagnosis at primary care centers; 3) define radiomic signatures of COVID-19 evolution and associated pathologies for the early treatment of complications. In particular, in this paper we present a general overview of the project, the experimental design and first results of X-ray COVID-19 detection using a classic approach based on HoG and feature selection. Our experiments include a comparison to some recent methods for COVID-19 screening in X-Ray and an exploratory analysis of the feasibility of X-Ray COVID-19 screening. Results show that classic approaches can outperform deep-learning methods in this experimental setting, indicate the feasibility of early COVID-19 screening and that non-COVID infiltration is the group of patients most similar to COVID-19 in terms of radiological description of X-ray. Therefore, an efficient COVID-19 screening should be complemented with other clinical data to better discriminate these cases.

研究动机与目标

• 开发一种基于经典计算机视觉技术的智能、低成本X光筛查系统，用于SARS-CoV-2的早期检测。
• 评估在初级医疗环境中使用标准X光成像进行早期COVID-19检测的可行性。
• 识别影响诊断准确性的影像组学特征与临床混淆因素，特别是非COVID-19浸润的影响。
• 比较经典机器学习方法（HoG + 特征选择）与最先进的深度学习方法在COVID-19检测中的表现。
• 评估模型在疾病进展不同阶段（早期、中期、晚期）的表现，以评估其早期诊断潜力。

提出的方法

• 该方法采用直方图梯度（HoG）从前后位后前位X光片中提取纹理与边缘特征。
• 通过DCV（判别成分变量）及其他技术进行降维，以优化分类的特征空间。
• 采用两阶段分类流程：第一阶段区分COVID-19、非COVID-19肺炎、浸润与正常病例；第二阶段评估模型在疾病各阶段的表现。
• 通过分类性能的统计分析，对模型超参数（包括HoG单元大小与降维方法）进行调优。
• 该方法基于来自公开数据仓库的数据库进行评估，采样过程确保各类别间表示均衡。
• 使用标准指标（准确率、敏感度（召回率）、特异性与精确率）与最先进的深度学习方法进行性能基准对比。

实验结果

研究问题

• RQ1 基于HoG与降维的经典机器学习方法是否能在从X光片检测SARS-CoV-2方面优于深度学习模型？
• RQ2 该模型在区分早期COVID-19与其他肺部病变（特别是非COVID-19浸润）方面表现如何？
• RQ3 临床数据在减少因非COVID-19浸润与COVID-19影像学相似性导致的假阳性结果方面起到何种作用？
• RQ4 在COVID-19肺炎的早期、中期与晚期阶段，检测性能是否存在显著差异？
• RQ5 在训练中将非COVID-19浸润作为独立类别是否能提升模型的特异性和临床相关性？

主要发现

• 基于HoG的方法在区分COVID-19与正常、肺炎及非COVID-19浸润病例方面，实现了96%的准确率、98%的召回率与96%的精确率。
• 在二分类（COVID-19 vs. 非COVID-19）与三分类（COVID-19、肺炎、正常）设置下，该模型在特异性和精确率方面优于多个最先进的深度学习方法。
• 非COVID-19浸润被确定为与COVID-19影像学上最相似的组别，系统中超过20%的假阳性结果可能归因于该类别。
• 在疾病早期（89%）、中期（93%）与晚期（94%）阶段的检测率之间无统计学显著差异，表明模型在疾病进展各阶段均表现稳定。
• 本研究证实，结合临床变量后，使用X光进行早期COVID-19筛查具有临床可行性，尤其有助于排除非COVID-19浸润。
• 基于统计评估，采用DCV进行降维与16×16像素的HoG单元大小可获得最优模型配置。