Microscopic segmentation and classification of COVID-19 infection with ensemble convolutional neural network,Microscopy Research and Technique

当前位置： X-MOL 学术 › Microsc. Res. Tech. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Microscopic segmentation and classification of COVID-19 infection with ensemble convolutional neural network
Microscopy Research and Technique ( IF 2.0 ) Pub Date : 2021-08-26 , DOI: 10.1002/jemt.23913
Javeria Amin ₁ , Muhammad Almas Anjum ₂ , Muhammad Sharif ₃ , Amjad Rehman ₄ , Tanzila Saba ₄ , Rida Zahra ₁

Affiliation

The detection of biological RNA from sputum has a comparatively poor positive rate in the initial/early stages of discovering COVID-19, as per the World Health Organization. It has a different morphological structure as compared to healthy images, manifested by computer tomography (CT). COVID-19 diagnosis at an early stage can aid in the timely cure of patients, lowering the mortality rate. In this reported research, three-phase model is proposed for COVID-19 detection. In Phase I, noise is removed from CT images using a denoise convolutional neural network (DnCNN). In the Phase II, the actual lesion region is segmented from the enhanced CT images by using deeplabv3 and ResNet-18. In Phase III, segmented images are passed to the stack sparse autoencoder (SSAE) deep learning model having two stack auto-encoders (SAE) with the selected hidden layers. The designed SSAE model is based on both SAE and softmax layers for COVID19 classification. The proposed method is evaluated on actual patient data of Pakistan Ordinance Factories and other public benchmark data sets with different scanners/mediums. The proposed method achieved global segmentation accuracy of 0.96 and 0.97 for classification.

中文翻译：

集成卷积神经网络对 COVID-19 感染的微观分割和分类

根据世界卫生组织的数据，在发现 COVID-19 的初始/早期阶段，从痰液中检测生物 RNA 的阳性率相对较低。与健康图像相比，它具有不同的形态结构，由计算机断层扫描 (CT) 显示。早期诊断 COVID-19 有助于及时治愈患者，降低死亡率。在这项报告的研究中，提出了用于 COVID-19 检测的三相模型。在第一阶段，使用去噪卷积神经网络 (DnCNN) 从 CT 图像中去除噪声。在第二阶段，实际病变区域是使用 deeplabv3 和 ResNet-18 从增强的 CT 图像中分割出来的。在阶段 III 中，分割图像被传递到堆栈稀疏自动编码器 (SSAE) 深度学习模型，该模型具有两个堆栈自动编码器 (SAE) 和选定的隐藏层。设计的 SSAE 模型基于用于 COVID19 分类的 SAE 和 softmax 层。所提出的方法在巴基斯坦法令工厂的实际患者数据和其他具有不同扫描仪/介质的公共基准数据集上进行了评估。所提出的方法在分类方面实现了 0.96 和 0.97 的全局分割精度。

更新日期：2021-08-26

点击分享查看原文

点击收藏

公开下载

阅读更多本刊最新论文本刊介绍/投稿指南11