A computer-aided diagnostic system to characterize CT focal liver lesions: design and optimization of a neural network classifier

• Published in: IEEE transactions on information technology in biomedicine Vol. 7; no. 3; pp. 153 - 162
• Main Authors: Gletsos, M., Mougiakakou, S.G., Matsopoulos, G.K., Nikita, K.S., Nikita, A.S., Kelekis, D.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2003
• Subjects: Algorithms; Carcinoma, Hepatocellular - diagnostic imaging; Carcinoma, Hepatocellular - pathology; Classification; Computed tomography; Computer networks; Cysts; Cysts - diagnostic imaging; Cysts - pathology; Design automation; Design optimization; Feature extraction; Genetic algorithms; Hemangioma - diagnostic imaging; Hemangioma - pathology; Humans; Lesions; Liver; Liver - diagnostic imaging; Liver diseases; Liver Neoplasms - diagnostic imaging; Liver Neoplasms - pathology; Mathematical analysis; Modules; Neural networks; Neural Networks (Computer); Pathology; Pattern Recognition, Automated; Radiographic Image Enhancement - methods; Radiographic Image Interpretation, Computer-Assisted - methods; Reproducibility of Results; Sensitivity and Specificity; Texture; Tomography, X-Ray Computed - methods
• ISSN: 1089-7771; 1558-0032
• DOI: 10.1109/TITB.2003.813793

In this paper, a computer-aided diagnostic (CAD) system for the classification of hepatic lesions from computed tomography (CT) images is presented. Regions of interest (ROIs) taken from nonenhanced CT images of normal liver, hepatic cysts, hemangiomas, and hepatocellular carcinomas have been used as input to the system. The proposed system consists of two modules: the feature extraction and the classification modules. The feature extraction module calculates the average gray level and 48 texture characteristics, which are derived from the spatial gray-level co-occurrence matrices, obtained from the ROIs. The classifier module consists of three sequentially placed feed-forward neural networks (NNs). The first NN classifies into normal or pathological liver regions. The pathological liver regions are characterized by the second NN as cyst or "other disease". The third NN classifies "other disease" into hemangioma or hepatocellular carcinoma. Three feature selection techniques have been applied to each individual NN: the sequential forward selection, the sequential floating forward selection, and a genetic algorithm for feature selection. The comparative study of the above dimensionality reduction methods shows that genetic algorithms result in lower dimension feature vectors and improved classification performance.