[论文解读] Exploring the Effect of Image Enhancement Techniques on COVID-19 Detection using Chest X-rays Images

Tawsifur Rahman, Amith Khandakar+9 more|arXiv (Cornell University)|Nov 25, 2020

COVID-19 diagnosis using AI被引用 13

一句话总结

本研究调查了五种图像增强技术——直方图均衡化、对比度受限自适应直方图均衡化（CLAHE）、图像补全、伽马校正和B-CET——在使用新型大规模数据集（COVQU-20，共18,479张图像）进行新冠感染检测时的影响。伽马校正表现最佳，使用六种CNN模型在标准和分割后的X光胸片上均达到96.29%的准确率、96.28%的精确率和96.29%的敏感度。

ABSTRACT

The use of computer-aided diagnosis in the reliable and fast detection of coronavirus disease (COVID-19) has become a necessity to prevent the spread of the virus during the pandemic to ease the burden on the medical infrastructure. Chest X-ray (CXR) imaging has several advantages over other imaging techniques as it is cheap, easily accessible, fast and portable. This paper explores the effect of various popular image enhancement techniques and states the effect of each of them on the detection performance. We have compiled the largest X-ray dataset called COVQU-20, consisting of 18,479 normal, non-COVID lung opacity and COVID-19 CXR images. To the best of our knowledge, this is the largest public COVID positive database. Ground glass opacity is the common symptom reported in COVID-19 pneumonia patients and so a mixture of 3616 COVID-19, 6012 non-COVID lung opacity, and 8851 normal chest X-ray images were used to create this dataset. Five different image enhancement techniques: histogram equalization, contrast limited adaptive histogram equalization, image complement, gamma correction, and Balance Contrast Enhancement Technique were used to improve COVID-19 detection accuracy. Six different Convolutional Neural Networks (CNNs) were investigated in this study. Gamma correction technique outperforms other enhancement techniques in detecting COVID-19 from standard and segmented lung CXR images. The accuracy, precision, sensitivity, f1-score, and specificity in the detection of COVID-19 with gamma correction on CXR images were 96.29%, 96.28%, 96.29%, 96.28% and 96.27% respectively. The accuracy, precision, sensitivity, F1-score, and specificity were 95.11 %, 94.55 %, 94.56 %, 94.53 % and 95.59 % respectively for segmented lung images. The proposed approach with very high and comparable performance will boost the fast and robust COVID-19 detection using chest X-ray images.

研究动机与目标

• 评估不同图像增强技术对提升新冠感染胸片（CXR）检测准确率的影响。
• 开发并发布目前公开可用的最大新冠感染胸片数据集COVQU-20，包含18,479张图像，涵盖正常、非新冠肺部浸润和新冠感染三类。
• 比较六种不同卷积神经网络（CNN）架构在结合图像增强技术时，对新冠感染进行鲁棒且快速检测的性能表现。
• 识别出能最大化检测指标（如准确率、敏感度、精确率、F1分数和特异度）的最优图像增强方法。

提出的方法

• 作者整理了COVQU-20数据集，包含18,479张胸片，其中正常8,851张，非新冠肺部浸润6,012张，新冠感染3,616张，以支持大规模训练与评估。
• 应用了五种图像增强技术：直方图均衡化、对比度受限自适应直方图均衡化（CLAHE）、图像补全、伽马校正和平衡对比度增强技术（B-CET）。
• 对六种预训练的卷积神经网络（CNN）在原始和增强后的胸片上进行了微调与评估，以衡量检测性能。
• 采用标准指标（准确率、精确率、敏感度、F1分数和特异度）对标准和肺部分割后的胸片进行性能评估。
• 应用肺部分割以隔离肺部区域，提升特征提取效果，并减少周围解剖结构带来的噪声影响。

实验结果

研究问题

• RQ1 哪种图像增强技术在胸片中对新冠感染检测的准确率最高？
• RQ2 图像增强与深度学习模型结合后，对新冠感染检测的敏感度和特异度有何影响？
• RQ3 在COVQU-20数据集上，不同CNN架构与各种增强技术结合后的性能表现如何比较？
• RQ4 伽马校正在标准和分割后的胸片上是否始终优于其他增强方法？

主要发现

• 在标准胸片上，伽马校正实现了96.29%的最高检测准确率，精确率为96.28%，敏感度为96.29%，F1分数为96.28%，特异度为95.27%。
• 在肺部分割图像上，伽马校正实现了95.11%的准确率，94.55%的精确率，94.56%的敏感度，94.53%的F1分数，以及95.59%的特异度。
• COVQU-20数据集包含18,479张图像，是目前同类中规模最大的公开数据库，涵盖正常、非新冠肺部浸润和新冠感染胸片的多样化病例。
• 在五种增强技术中，伽马校正在所有评估指标上均持续优于直方图均衡化、CLAHE、图像补全和B-CET。
• 伽马校正与深度学习模型的结合实现了最先进性能，展现出在自动化新冠感染检测中高度的鲁棒性与泛化能力。