Search

This paper attempts to estimate diagnostically relevant measure, i.e., Arteriovenous Ratio with an improved retinal vessel classification using feature ranking strategies and multiple classifiers decision-combination scheme. The features exploited for retinal vessel characterization are based on statistical measures of histogram, different filter responses of images and local gradient information. The feature selection process is based on two feature ranking approaches (Pearson Correlation Coefficient technique and Relief-F method) to rank the features followed by use of maximum classification accuracy of three supervised classifiers (k-Nearest Neighbor, Support Vector Machine and Naïve Bayes) as a threshold for feature subset selection. Retinal vessels are labeled using the selected feature subset and proposed hybrid classification scheme, i.e., decision fusion of multiple classifiers. The comparative analysis shows an increase in vessel classification accuracy as well as Arteriovenous Ratio calculation performance. The system is tested on three databases, a local dataset of 44 images and two publically available databases, INSPIRE-AVR containing 40 images and VICAVR containing 58 images. The local database also contains images with pathologically diseased structures. The performance of the proposed system is assessed by comparing the experimental results with the gold standard estimations as well as with the results of previous methodologies. Overall, an accuracy of 90.45%, 93.90% and 87.82% is achieved in retinal blood vessel separation with 0.0565, 0.0650 and 0.0849 mean error in Arteriovenous Ratio calculation for Local, INSPIRE-AVR and VICAVR dataset, respectively. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) has been a prevalence technique for breast cancer diagnosis. Computer-aided detection and segmentation of lesions from MRIs plays a vital role for the MRI-based disease analysis. There are two main issues of the existing breast lesion segmentation techniques: requiring manual delineation of Regions of Interests (ROIs) as a step of initialization; and requiring a large amount of labeled images for model construction or parameter learning, while in real clinical or experimental settings, it is highly challenging to get sufficient labeled MRIs. To resolve these issues, this work proposes a semi-supervised method for breast tumor segmentation based on super voxel strategies. After image segmentation with advanced cluster techniques, we take a supervised learning step to classify the tumor and nontumor patches in order to automatically locate the tumor regions in an MRI. To obtain the optimal performance of tumor extraction, we take extensive experiments to learn parameters for tumor segmentation and classification, and design 225 classifiers corresponding to different parameter settings. We call the proposed method as Semi-supervised Tumor Segmentation (SSTS), and apply it to both mass and nonmass lesions. Experimental results show better performance of SSTS compared with five state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This paper presents an approach for automatic classification of pulsed Terahertz (THz), or T-ray, signals highlighting their potential in biomedical, pharmaceutical and security applications. T-ray classification systems supply a wealth of information about test samples and make possible the discrimination of heterogeneous layers within an object. In this paper, a novel technique involving the use of Auto Regressive (AR) and Auto Regressive Moving Average (ARMA) models on the wavelet transforms of measured T-ray pulse data is presented. Two example applications are examined — the classification of normal human bone (NHB) osteoblasts against human osteosarcoma (HOS) cells and the identification of six different powder samples. A variety of model types and orders are used to generate descriptive features for subsequent classification. Wavelet-based de-noising with soft threshold shrinkage is applied to the measured T-ray signals prior to modeling. For classification, a simple Mahalanobis distance classifier is used. After feature extraction, classification accuracy for cancerous and normal cell types is 93%, whereas for powders, it is 98%. [ABSTRACT FROM AUTHOR]