Description
Liver Tumor Detection using Neural Networks and Matlab
Abstract
The liver cancer rate is increasing year by year. Generally, liver cancer’s death rate is very high because the disease causes no symptoms, so it’s often not caught until it’s in its final stages. We propose methods for liver cancer detection which is based on concepts of neural network. Wavelet and glam features were extracted from the input image. These glam features classify to the dataset and then get a result in normal or abnormal states. Many techniques have been developed for the detection of liver tumors utilizing the aberrant lesion size and shape. A novel methodology for the detection and diagnosis of liver tumors is additionally proposed in this paper for the detection and diagnosis of liver tumors.
Introduction
Early diagnosis is vital in treating a disease. Diagnosis relies on the skills, experience, and knowledge of the practicing physicians, although human errors may sometimes occur. Recently, various artificial intelligence-based methods are being increasingly used for liver disorder diagnosis to assist doctors in the diagnosis of patients. Extended cirrhosis and statuses of liver disease may cause the appearance of malignant or benign tumors in the liver. Any abnormality in the liver adversely affects the rest of the body, as well as the general health of the patient Fatty liver disease (FLD) occurs when the human body produces a considerable amount of fat or does not efficiently metabolize fat. This excess fat is stored in the liver cells, where it accumulates triglycerides in the blood, causing FLD It is believed that FLD involves the pathogenesis of various common disorders, such as Type II diabetes and cardiovascular diseases. The liver cancer rate is increasing year by year. Generally, liver cancer’s death rate is very high because the disease causes no symptoms, so it’s often not caught until it’s in its final stages. We propose methods for liver cancer detection which is based on concepts of neural network. Wavelet and glam features were extracted from the input image. These glam features classify to the dataset and then get a result is normal or abnormal stages
Existing Systems
- Principal Component Analysis
- DCT ? and shape features
- KNN and SVM classifier
Drawbacks of Existing System
- High Computational load and poor discriminatory power.
- SVM is slow training for large feature sets.
- Less accuracy in classification
Proposed Method
- DTCWT and GLCM Features
- NN Classifier
- K-means Clustering
Advantages
- The segmentation algorithm Proves to be simple and effective
- The greyscale Co-occurrence matrix performed well in NN
- Better texture and edge representation
- Segmentation provides better clustering efficiency
Block Diagram
Hardware Requirement
- system
- 4 GB of RAM
- 500 GB of Hard disk
Software Requirement
- MATLAB 2014a
REFERENCES
[1] Upadhyay, Y. and Wasson, V. 2014. “Analysis of Liver MR Images for Cancer Detection using Genetic Algorithm”. International Journal of Engineering Research and General Science. Vol.2, No.4, PP: 730-737.
?[2] Kumar, P. Bhalerao, S. 2014. “Detection of Tumor in Liver Using Image Segmentation and Registration Technique”. IOSR Journal of Electronics and Communication Engineering (IOSR-JECE). Vo.9, No.2, PP: 110-115.
?[3] Selle, D.; Spindler, W.; Preim, B. and Peitgen, H. O. 2000. “Mathematical Methods in Medical Imaging: Analysis of Vascular Structures for Liver Surgery Planning”. PP: 1-21.
[4] Zimmer, C. and Olivo-Marin, J. C. 2005. “Coupled Parametric Active Contours”. Transactions on Pattern Analysis and Machine Intelligence. Vol.27, No.11, PP: 1838-1841.
?[5] Chitra, S. and Balakrishnan, G. 2012. “Comparative Study for Two-Color Spaces HSCbCr and YCbCr in Skin Color Detection”. Applied Mathematical Sciences. Vol.6, No.85, PP: 4229? 4238.
Customer Reviews
There are no reviews yet.