In this paper, a novel feature extraction scheme is proposed, based on multiresolution fast discrete curvelet transform for computer-aided diagnosis of liver diseases. The liver is segmented from CT images using adaptive threshold detection and morphological processing. The suspected tumour region is extracted from the segmented liver using FCM clustering. The textural information obtained from the extracted tumour using Fast Discrete Curvelet Transform (FDCT) is used to train and classify the liver tumour into hemangioma and hepatoma employing artificial neural network classifier. A comparison with a similar algorithm based on Wavelet texture descriptors shows that using FDCT based texture features significantly improves the classification rate of liver tumours from CT scans.
Computed tomography image based ComputerAided Diagnosis (CAD) could be crucially important in supporting liver cancer diagnosis. An effective approach to realize a CAD system for this purpose is described in this work. The CAD system employs automatic tumor segmentation, texture feature extraction and characterization into malignant and benign tumors. A Region of Interest (ROI) cropped from the automatically segmented tumor by confidence connected region growing and alternative fuzzy c means clustering is decomposed using multiresolution and multidirectional contourlet transform to obtain contourlet coefficients. Both first order statistic and second order statistic features are extracted from the gray level and contourlet detail coefficients. The extracted feature sets are classified by a Probabilistic Neural Network (PNN) classifier into benign and malignant. The system is evaluated by using different performance measures and the results indicate that the contourlet coefficient texture is effective for classifying malignant and benign liver tumors from abdominal CT imaging.
