Abstract
With the rapid development of detection technology, CT imaging technology has been widely used in the early clinical diagnosis of lung nodules. However, accurate assessment of the nature of the nodule remains a challenging task due to the subjective nature of the radiologist. With the increasing amount of publicly available lung image data, it has become possible to use convolutional neural networks for benign and malignant classification of lung nodules. However, as the network depth increases, network training methods based on gradient descent usually lead to gradient dispersion. Therefore, we propose a novel deep convolutional network approach to classify the benignity and malignancy of lung nodules. Firstly, we segmented, extracted, and performed zero-phase component analysis whitening on images of lung nodules. Then, a multilayer perceptron was introduced into the structure to construct a deep convolutional network. Finally, the minibatch stochastic gradient descent method with a momentum coefficient is used to fine-tune the deep convolutional network to avoid the gradient dispersion. The 750 lung nodules in the lung image database are used for experimental verification. Classification accuracy of the proposed method can reach 96.0%. The experimental results show that the proposed method can provide an objective and efficient aid to solve the problem of classifying benign and malignant lung nodules in medical images.
Highlights
Lung cancer is one of the most common cancers in the world
Radiologists may not be able to identify some nodules with diameters
Guided by the above studies and observations, we propose a novel deep convolutional network learning (DCN) method to obtain better performance in classifying benign and malignant lung nodules. e central idea is as follows: firstly, segment the lung nodule region from the lung CT images to obtain the lung nodule images and perform zero-phase component analysis (ZCA) whitening on the image data so that all features in the images have the same variance and low feature-to-feature correlation. en, add a multilayer perceptron layer after each convolutional layer of the constructed DCN to achieve cross-channel information interaction and integration
Summary
Lung cancer is one of the most common cancers in the world. Compared with other cancers, there are no obvious symptoms at an early stage. The classification of benign and malignant lung nodules in the CAD system is mainly performed by extracting the underlying features of the CT image of lung nodules, such as the shape, position, texture, and density, through machine learning methods [5]. This classification method based on the underlying features has obtained good results in improving the accuracy of lung nodule diagnosis and reducing the labor intensity of doctors. The extraction of the underlying features is generally based on manual design, failing to fully describe these real nodules, resulting in a low correct rate of overall detection results [6]. erefore, how to perform automatic feature extraction and selection on CT images of lung nodules has become a hot topic of research
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
