Saha Priyanka, Neogy Sarmistha
Depatment of Computer Science and Engineering, Jadavpur University, Kolkata, 700032 India.
SN Comput Sci. 2022;3(4):305. doi: 10.1007/s42979-022-01182-1. Epub 2022 May 23.
COVID-19 is creating havoc on the lives of human beings all around the world. It continues to affect the normal lives of people. As number of cases are high, a cost effective and fast system is required to detect COVID-19 at appropriate time to provide the necessary healthcare. Chest X-rays have emerged as an easiest way to detect COVID-19 in no time as RT-PCR takes time to detect the infection. In this paper we propose a concatenation-based CNN model that will detect COVID-19 from chest X-rays. We have developed a multiclass classification problem which can detect and classify a chest X-ray image as either COVID + ve, or viral pneumonia, or normal. We have used chest X-rays collected from different open sources. To maintain class balancing, we took 500 images of COVID, 500 normal images, and 500 pneumonia images. We divided our dataset in training, validation, and test set in 70:10:20 ratio respectively. We used four CNNs as feature extractors from the images and concatenated their feature maps to get better efficiency of the network. After training our model for 5 folds, we have obtained around 96.31% accuracy, 95.8% precision, 92.99% recall, and 98.02% AUC. We have compared our work with state-of-the-art pretrained transfer learning algorithms and other state-of-the-art CNN models referred in different research papers. The proposed model (Concat_CNN) exhibits better accuracy than the state-of-the-art models. We hope our proposed model will help to classify chest X-rays effectively and help medical professionals with their treatment.
新型冠状病毒肺炎正在对全世界人类的生活造成严重破坏。它继续影响着人们的正常生活。由于病例数量众多，需要一个经济高效且快速的系统，以便在适当的时候检测出新型冠状病毒肺炎，从而提供必要的医疗保健。胸部X光已成为一种能立即检测出新型冠状病毒肺炎的最简单方法，因为逆转录聚合酶链反应检测感染需要时间。在本文中，我们提出了一种基于拼接的卷积神经网络模型，该模型将从胸部X光片中检测新型冠状病毒肺炎。我们开发了一个多类分类问题，它可以将胸部X光图像检测并分类为新型冠状病毒肺炎阳性、病毒性肺炎或正常。我们使用了从不同开源渠道收集的胸部X光片。为了保持类别平衡，我们选取了500张新型冠状病毒肺炎图像、500张正常图像和500张肺炎图像。我们将数据集分别按照70:10:20的比例划分为训练集、验证集和测试集。我们使用四个卷积神经网络作为图像的特征提取器，并将它们的特征图拼接起来，以提高网络的效率。在对我们的模型进行5次折叠训练后，我们获得了约96.31%的准确率、95.8%的精确率、92.99%的召回率和98.02%的曲线下面积。我们将我们的工作与最先进的预训练迁移学习算法以及不同研究论文中提到的其他最先进的卷积神经网络模型进行了比较。所提出的模型（Concat_CNN）比最先进的模型表现出更好的准确率。我们希望我们提出的模型将有助于有效地对胸部X光片进行分类，并帮助医学专业人员进行治疗。
