RETRACTED ARTICLE: Automatic segmentation and classification of liver tumor from CT image using feature difference and SVM based classifier-soft computing technique

• Published in: Soft computing (Berlin, Germany) Vol. 24; no. 24; pp. 18591 - 18598
• Main Authors: Devi, R. Manjula, Seenivasagam, V.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01-12-2020; Springer Nature B.V
• Subjects: Abdomen; Accuracy; Algorithms; Artificial Intelligence; Back propagation; Carbohydrates; Classification; Classifiers; Computational Intelligence; Computed tomography; Control; Datasets; Engineering; Image classification; Image segmentation; Lesions; Liver diseases; Machine learning; Magnetic resonance imaging; Mathematical Logic and Foundations; Mechatronics; Medical imaging; Methodologies and Application; Neural networks; Robotics; Soft computing; Support vector machines; Tumors; Tumor; Difference feature; Region growing; SVM classifier; Liver
• ISSN: 1432-7643; 1433-7479
• DOI: 10.1007/s00500-020-05094-1

The liver is essential for endurance and to carry out a large number of significant functions, including manufacture of indispensable proteins, and metabolism of fats and carbohydrates. The examination of CT might be employed for planning and managing the treatments for tumor in a proper way and for directing biopsies as well as other simply determined process. The Manual segmentation and Computed Axial Tomography (CT) image classification is a tedious task and time consuming process for large amount of data. Computer-Aided Diagnosis (CAD) systems take part in a fundamental role in the detection of liver disease in an early stage and therefore decrease death rate of liver cancer. In this paper an automatic CAD system is presented in three stage. In the first step, automatic liver segmentation and lesion’s detection is carried out. Then, the next step is to extract features. At last, liver lesions classification into malignant and benign is done by using the novel contrast based feature-difference method. The extracted features from the lesion area with its surrounding normal liver tissue are based on intensity and texture. The lesion descriptor is obtained by considering the difference between the features of both lesion area and normal tissue of liver. Finally to categorize the liver lesions into malignant or benign a new SVM based machine learning classifier is trained on the new descriptors. The investigational outcome show hopeful improvement. Besides, the projected approach is insensitive to ranges of textures and intensity between demographics, imaging devices, and patients and settings. The classifier discriminates the tumor by comparatively high precision and offers a subsequent view to the radiologist.