Automated Liver Tumor Detection Using Markov Random Field Segmentation. (2016)

• Record Type: Journal Article
• Authors: Raj, Amitha; Jayasree, M.
• Is Part Of: Procedia technology. Volume 24(2016)
• Page Start: 1305
• Page End: 1310
• Publication Date: 2016
• Subjects: Liver tumor -- MRF segmentation -- Shape ambiguities correction -- Tumor detection; Technology -- Congresses; Technology -- Periodicals; Engineering -- Congresses; Engineering -- Periodicals; Engineering; Technology; Conference proceedings; Periodicals; 605
• DOI: 10.1016/j.protcy.2016.05.126
• Languages: English
• ISSNs: 2212-0173

Abstract

Abstract: Liver cancers are one of the most popular cancers occurring now a days. The majority of liver carcinomas are dueto alcohol related cirrhosis and hepatitis. Also there are metastatic liver cancer, in which cancer originated from other organs extends to liver. Early detection of liver cancer helps to improve life expectancy. We also need to know the tumor status during treatment stages. Manual segmentation and detection is time consuming. Here we propose an automated computer aided diagnosis of liver tumors from CT images. Initially liver is segmented using MRF embedded level set method. It provides robustness to noise and fast segmentation. The shape ambiguities of the segmented liver is found out by shape analysis methods which uses training set for correction. From the corrected liver segmentation, hepatic tumors are detected by graph cut method and feature extraction is done to classify them using SVM classifier.