Detection of Lung Nodules on X-ray Using Transfer Learning and Manual Features

作     者：Imran Arshad Choudhry Adnan N.Qureshi 

作者机构：Faculty of Information TechnologyUniversity of Central PunjabLahorePakistan 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第72卷第7期

页      面：1445-1463页

核心收录：

学科分类：1002[医学-临床医学] 100214[医学-肿瘤学] 10[医学] 

主　　题：Lungs cancer convolutional neural network hand-crafted feature extraction deep learning classification 

摘      要：The well-established mortality rates due to lung cancers,scarcity of radiology experts and inter-observer variability underpin the dire need for robust and accurate computer aided diagnostics to provide a second *** this end,we propose a feature grafting approach to classify lung cancer images from publicly available National Institute of Health(NIH)chest X-Ray dataset comprised of 30,805 unique *** performance of transfer learning with pre-trained VGG and Inception models is evaluated in comparison against manually extracted radiomics features added to convolutional neural network using custom *** classification with both approaches,Support VectorsMachines(SVM)are *** results from the 5-fold cross validation report Area Under Curve(AUC)of 0.92 and accuracy of 96.87%in detecting lung nodules with the proposed *** is a plausible improvement against the observed accuracy of transfer learning using Inception(79.87%).The specificity of allmethods is99%,however,the sensitivity of the proposed method(97.24%)surpasses that of transfer learning approaches(67%).Furthermore,it is observed that the true positive rate with SVM is highest at the same false-positive rate in experiments amongst Random Forests,Decision Trees,and K-Nearest Neighbor ***,the proposed approach can be used in clinical and research environments to provide second opinions very close to the experts’intuition.