Open AccessAutomatic Liver Cancer Segmentation using active contour model and RF Classifier
Author(s) -
T.K.R. Agita*,
M. Moorthi
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.j9031.0981119
Subject(s) - random forest , artificial intelligence , segmentation , computer science , classifier (uml) , active contour model , liver cancer , pattern recognition (psychology) , word error rate , computed tomography , image segmentation , computer vision , radiology , cancer , medicine
In this paper, we presented the new method for liver cancer detection. Computed Tomography (CT) has becomes important tool for diagnosis of liver cancer. The proposed method used in this paper is Random Forest (RF) classifier algorithm for the detection of cancer in the liver. For the automatic segmentation, here we use active contour method to segment the liver and liver cancer to rectify the manual segmentation problem. It is fully automatic and the proposed classifier will successfully classifies whether it is malignant or benign liver cancer tumor. Manual identification is not accurate and also time consuming task. The new method proposed in this paper will segment the liver cancer from the CT image of liver automatically. It is highly accurate and less computation time. The experiment results show the accuracy of the proposed method. Random Forest classifier has 91% accuracy rate and less error rate and achieved excellent test result