The main purpose of this study is to develop a pipeline for COVID-19 detection from a big and challenging database of Computed Tomography (CT) images. The proposed pipeline includes a segmentation part, a lung extraction part, and a classifier part. Optional slice removal techniques after UNet-based segmentation of slices were also tried. The methodologies tried in the segmentation part are traditional segmentation methods as well as UNet-based methods. In the classification part, a Convolutional Neural Network (CNN) was used to take the final diagnosis decisions. In terms of the results: in the segmentation part, the proposed segmentation methods show high dice scores on a publicly available dataset. In the classification part, the results were compared at slice-level and at patient-level as well. At slice-level, methods were compared and showed high validation accuracy indicating efficiency in predicting 2D slices. At patient level, the proposed methods were also compared in terms of validation accuracy and macro F1 score on the validation set. The dataset used for classification is COV-19CT Database. The method proposed here showed improvement from our precious results on the same dataset. In Conclusion, the improved work in this paper has potential clinical usages for COVID-19 detection and diagnosis via CT images. The code is on github at https://github.com/IDU-CVLab/COV19D_3rd
翻译:本文的主要目的是开发一种用于从大量具有挑战性的计算机断层扫描(CT)影像数据库中检测 COVID-19 的管道。该提出的管道包括分割部分、肺部提取部分和分类器部分。为了提高精度,也尝试了 UNet 分割之后的可选切面移除技术。在分割部分,所尝试的方法既包括传统的分割方法,也包括基于 UNet 的方法。在分类部分,使用卷积神经网络(CNN)进行最终的诊断决策。在结果方面:在分割部分,所提出的分割方法在公开可用数据集上表现出较高的 Dice 得分。在分类部分,结果在切片级别和患者级别进行了比较。在切片级别,所尝试的方法进行比较,结果显示出预测 2D 切片的有效性和高验证准确性。在患者级别,所提出的方法也在验证集上进行了验证准确性和宏 F1 分数的比较。用于分类的数据集是 COV-19CT 数据库。本文提出的方法在相同数据集上相比于之前的结果有所改进。总之,本文的改进工作具有潜在的临床用途,可用于通过 CT 影像检测和诊断 COVID-19。代码在 github 上的位置是 https://github.com/IDU-CVLab/COV19D_3rd