Study On Recognition Of Cancer Liver In MR Images

Magnetic resonance imaging, computer tomography CT angiography, ultrasound imaging and nuclear medicine imaging are known as the four modern medical imaging technologies. Magnetic resonance imaging is widely used in clinical diagnosis and treatment because of its speed, non-invasive, no radiation, and high-resolution of soft tissue. In the diagnosis of liver disease, magnetic resonance imaging is often used.Liver disease is a higher prevalence in our country, with the greatest danger of liver cancer, which usually comes from the development of liver cirrhosis. Diagnosing liver cancer or cirrhosis through magnetic resonance imaging on clinical is mainly by doctors based on experience with the naked eye for observation and diagnosis. So misdiagnosis would occurs, which would delays the treatment of patients, lead to developing treatment programs incorrectly or increasing the unnecessary spirit of burden. In this paper, magnetic resonance images of the liver are analyzed by using digital image processing method in the texture analysis to extract features to classify the images into liver cirrhosis images and liver cancer images. Furthermore, an automatic human tissues extraction system is designed in the paper.At present, many of the images of the liver for liver disease identification techniques are based on ultrasound imaging or CT angiography. Because of the different imaging principle, the extracted texture features are different and therefore can not be used in magnetic resonance images properly. In order to achieve the purpose of this paper, the regions of interest of the images are texturally analyzed in both of spatial domain and frequency domain. In the spatial domain, the second-order statistics of a gray level co-occurrence matrix are used as the features. In the frequency domain, Gabor filters are used for image filtering, and then textural features are extracted. Finally, a BP neural network is used to classify the feature vector extracted.In order to provide abundant image resource and scientific evaluation warranty for results, the animal model experiment is made in Dalian Medical University's Experiment Animal Center. After getting the liver cancer animal model, the examination with MRI is done, and then getting these animal models' livers to do the pathological analysis. These pathological analysis results will be used to provide the impersonal warranty for accuracy of the result of recognition.