Tallapragada V V Satyanarayana, Manga N Alivelu, Kumar G V Pradeep
Department of ECE, Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College), Tirupati, 517102 India.
Synopsys (India) Private Ltd., Hyderabad, India.
Multimed Tools Appl. 2023 Jan 21:1-42. doi: 10.1007/s11042-023-14367-4.
Recently, the Covid-19 pandemic has affected several lives of people globally, and there is a need for a massive number of screening tests to diagnose the existence of coronavirus. For the medical specialist, detecting COVID-19 cases is a difficult task. There is a need for fast, cheap and accurate diagnostic tools. The chest X-ray and the computerized tomography (CT) play a significant role in the COVID-19 diagnosis. The advancement of deep learning (DL) approaches helps to introduce a COVID diagnosis system to achieve maximum detection rate with minimum time complexity. This research proposed a discrete wavelet optimized network model for COVID-19 diagnosis and feature extraction to overcome these problems. It consists of three stages pre-processing, feature extraction and classification. The raw images are filtered in the pre-processing phase to eliminate unnecessary noises and improve the image quality using the MMG hybrid filtering technique. The next phase is feature extraction, in this stage, the features are extracted, and the dimensionality of the features is diminished with the aid of a modified discrete wavelet based Mobile Net model. The third stage is the classification here, the convolutional Aquila COVID detection network model is developed to classify normal and COVID-19 positive cases from the collected images of the COVID-CT and chest X-ray dataset. Finally, the performance of the proposed model is compared with some of the existing models in terms of accuracy, specificity, sensitivity, precision, f-score, negative predictive value (NPV) and positive predictive value (PPV), respectively. The proposed model achieves the performance of 99%, 100%, 98.5%, and 99.5% for the CT dataset, and the accomplished accuracy, specificity, sensitivity, and precision values of the proposed model for the X-ray dataset are 98%, 99%, 98% and 97% respectively. In addition, the statistical and cross validation analysis is conducted to validate the effectiveness of the proposed model.
最近，新冠疫情影响了全球许多人的生活，因此需要进行大量的筛查测试来诊断冠状病毒的存在。对于医学专家来说，检测新冠病例是一项艰巨的任务。需要快速、廉价且准确的诊断工具。胸部X光和计算机断层扫描（CT）在新冠诊断中发挥着重要作用。深度学习（DL）方法的进步有助于引入一个新冠诊断系统，以实现最高的检测率和最低的时间复杂度。本研究提出了一种用于新冠诊断和特征提取的离散小波优化网络模型，以克服这些问题。它由预处理、特征提取和分类三个阶段组成。在预处理阶段，使用MMG混合滤波技术对原始图像进行滤波，以消除不必要的噪声并提高图像质量。下一阶段是特征提取，在此阶段，借助基于改进离散小波的Mobile Net模型提取特征并降低特征维度。第三阶段是分类，在这里，开发卷积Aquila新冠检测网络模型，从收集的新冠CT和胸部X光数据集中对正常病例和新冠阳性病例进行分类。最后，将所提出模型的性能与一些现有模型在准确性、特异性、敏感性、精确性、F分数、阴性预测值（NPV）和阳性预测值（PPV）方面进行了比较。所提出的模型在CT数据集上的性能分别达到了99%、100%、98.5%和99.5%，所提出模型在X光数据集上的准确率、特异性、敏感性和精确性分别为98%、99%、98%和97%。此外，还进行了统计和交叉验证分析，以验证所提出模型的有效性。
