Research on Feature Extraction of Tumor Image Based on Convolutional Neural Network
Open Access
- 4 February 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 24204-24213
Abstract
Medical images play a very important role in making the right diagnosis for the doctor and in the patient's treatment process. Using intelligent algorithms makes it possible to quickly distinguish the lesions of medical images, and it is especially important to extract features from images. Many studies have integrated various algorithms into medical images. For medical image feature extraction, a large amount of data is analyzed to obtain processing results, helping doctors to make more accurate case diagnosis. In view of this, this study takes tumor images as the research object, and firstly performs local binary pattern feature extraction of the tumor image by rotation invariance. As the image shifts and the rotation changes, the image is stationary relative to the coordinate system. The method can accurately describe the texture features of the shallow layer of the tumor image, thereby enhancing the robustness of the image region description. Focusing on image feature extraction based on convolutional neural network, the basic framework of convolutional neural network is built. In order to break the limitations of machine vision and human vision, the research is extended to multi-channel input convolutional neural network for image feature extraction. . Two convolution models of Xception and Dense Net are built to improve the accuracy of the convolutional neural network algorithm. It can be seen from the experimental results that the convolutional neural network algorithm shows high accuracy in tumor image feature extraction. In this study, the convolutional neural network algorithm is compared with several classical algorithms in the local binary mode. The convolutional neural network algorithm has more accurate feature extraction ability for tumor CT images on a larger data basis. Furthermore, the advantages of convolutional neural network algorithms in this field are demonstrated.Keywords
Funding Information
- National Natural Science Foundation of China (51674121)
- Natural Science Foundation of Hebei Province (E2017209178)
- Outstanding Youth Fund Project of North China University of Science and Technology (JQ201705)
This publication has 26 references indexed in Scilit:
- Distributed Signal Decorrelation and Detection in Multi View Camera Networks Using the Vector Sparse Matrix TransformIEEE Transactions on Image Processing, 2015
- A convolutional neural network cascade for face detection2015
- A survey of MRI-based brain tumor segmentation methodsTsinghua Science and Technology, 2014
- Deep Learning Face Representation from Predicting 10,000 Classes2014
- Fast, accurate, and fully automatic segmentation of the right ventricle in short-axis cardiac MRIComputerized Medical Imaging and Graphics, 2014
- Ultrasound Diagnosis of Breast CancerJournal of Medical Imaging and Health Informatics, 2013
- Tumour heterogeneity in oesophageal cancer assessed by CT texture analysis: Preliminary evidence of an association with tumour metabolism, stage, and survivalClinical Radiology, 2012
- Automated macular pathology diagnosis in retinal OCT images using multi-scale spatial pyramid and local binary patterns in texture and shape encodingMedical Image Analysis, 2011
- The Utility of Sonographic Features During Endobronchial Ultrasound-Guided Transbronchial Needle Aspiration for Lymph Node Staging in Patients With Lung CancerChest, 2010
- FDG-PET Prediction of Head and Neck Squamous Cell Cancer OutcomesJAMA Otolaryngology–Head & Neck Surgery, 2004