Automatic Segmentation and Classification of Liver Tumor using Hybrid Neural Network
A Cibi1, Ramya D2, Ramya V3
1Ms. A. Cibi, Assistant Professor, Department of Computer Science and Engineering, Rajalakshmi Engineering College, Chennai, India.
2Ramya D, Student, Department of Computer Science and Engineering, Rajalakshmi Engineering College, Chennai, India.
3Ramya V, Student, Department of Computer Science and Engineering, Rajalakshmi Engineering College, Chennai, India.
Manuscript received on April 30, 2020. | Revised Manuscript received on May 06, 2020. | Manuscript published on May 30, 2020. | PP: 1807-1811 | Volume-9 Issue-1, May 2020. | Retrieval Number: A2279059120/2020©BEIESP | DOI: 10.35940/ijrte.A2279.059120
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Liver tumor is most common nowadays. Liver tumor segmentation is one of the most essential steps in treating it. We have chosen CT scan image for liver tumor diagnosis. Accurate tumor segmentation is done using computed tomography (CT) images. Since the manual identification is not that much accurate and time consuming, we go for active contour method. This automatic segmentation method is highly accurate and provides very less time for computation. The back propagation classifier method has a very good accuracy rate and a very less error rate and hence achieved the best result. The proposed method we used in this paper is back propagation classification algorithm for the detection of early and final stages of liver tumor. For the automatic segmentation, we use an active contour method to segment the liver and liver tumor to overcome the manual segmentation problem. This is an automatic method will help us to know whether the tumor is in benign or malignant stage.
Keywords: Liver tumor, Active Contour, Back propagation, Automatic segmentation, Computer tomography.
Scope of the Article: Classification