Mehrdad J. Gangeh

A texton-based approach for the classification of lung parenchyma in CT images

In this paper, a texton-based classification system based on raw pixel representation along with a support vector machine with radial basis function kernel is proposed for the classification of emphysema in computed tomography images of the lung. The proposed approach is tested on 168 annotated regions of interest consisting of normal tissue, centrilobular emphysema, and paraseptal emphysema. The results show the superiority of the proposed approach to common techniques in the literature including moments of the histogram of filter responses based on Gaussian derivatives. The performance of the proposed system, with an accuracy of 96.43%, also slightly improves over a recently proposed approach based on local binary patterns.

Kernelized Supervised Dictionary Learning

In this paper, we propose supervised dictionary learning (SDL) by incorporating information on class labels into the learning of the dictionary. To this end, we propose to learn the dictionary in a space where the dependency between the signals and their corresponding labels is maximized. To maximize this dependency, the recently introduced Hilbert Schmidt independence criterion (HSIC) is used. One of the main advantages of this novel approach for SDL is that it can be easily kernelized by incorporating a kernel, particularly a data-dependent kernel such as normalized compression distance, into the formulation. The learned dictionary is compact and the proposed approach is fast. We show that it outperforms other unsupervised and supervised dictionary learning approaches in the literature, using real-world data.

Multiview supervised dictionary learning in speech emotion recognition

Recently, a supervised dictionary learning (SDL) approach based on the Hilbert-Schmidt independence criterion (HSIC) has been proposed that learns the dictionary and the corresponding sparse coefficients in a space where the dependency between the data and the corresponding labels is maximized. In this paper, two multiview dictionary learning techniques are proposed based on this HSIC-based SDL. While one of these two techniques learns one dictionary and the corresponding coefficients in the space of fused features in all views, the other learns one dictionary in each view and subsequently fuses the sparse coefficients in the spaces of learned dictionaries. The effectiveness of the proposed multiview learning techniques in using the complementary information of single views is demonstrated in the application of speech emotion recognition (SER). The fully-continuous sub-challenge (FCSC) of the AVEC 2012 dataset is used in two different views: baseline and spectral energy distribution (SED) feature sets. Four dimensional affects, i.e., arousal, expectation, power, and valence are predicted using the proposed multiview methods as the continuous response variables. The results are compared with the single views, AVEC 2012 baseline system, and also other supervised and unsupervised multiview learning approaches in the literature. Using correlation coefficient as the performance measure in predicting the continuous dimensional affects, it is shown that the proposed approach achieves the highest performance among the rivals. The relative performance of the two proposed multiview techniques and their relationship are also discussed. Particularly, it is shown that by providing an additional constraint on the dictionary of one of these approaches, it becomes the same as the other.

Assessment of cancer therapy effects using texton-based characterization of quantitative ultrasound parametric images

This paper proposes the application of texton-based approach for textural characterization of quantitative ultrasound parametric maps, in order to assess noninvasively the progressive effects of cancer treatment in preclinical animal models. Xenograft tumour-bearing animals were treated with chemotherapy. Ultrasound data were acquired from tumours prior to, and at different times after exposure, and quantitative ultrasound spectral parametric maps were generated. Texton-based features were extracted from 0-MHz Intercept parametric maps and applied to differentiate between preand posttreatment states. The classification error was then translated into a quantitative measure of the treatment effects. Obtained results demonstrated a very good agreement with histological observations, and suggested that the proposed approach can be used noninvasively to evaluate the progressive effects of cancer treatment.

Dictionary learning in texture classification

Texture analysis is used in numerous applications in various fields. There have been many different approaches/techniques in the literature for texture analysis among which the texton-based approach that computes the primitive elements representing textures using k-means algorithm has shown great success. Recently, dictionary learning and sparse coding has provided state-of-the-art results in various applications. With recent advances in computing the dictionary and sparse coefficients using fast algorithms, it is possible to use these techniques to learn the primitive elements and histogram of them to represent textures. In this paper, online learning is used as fast implementation of sparse coding for texture classification. The results show similar to or better performance than texton based approach on CUReT database despite of computation of dictionary without taking into account the class labels.

Categorizing Extent of Tumor Cell Death Response to Cancer Therapy Using Quantitative Ultrasound Spectroscopy and Maximum Mean Discrepancy

Quantitative ultrasound (QUS) spectroscopic techniques in conjunction with maximum mean discrepancy (MMD) have been proposed to detect, and to classify noninvasively the levels of cell death in response to cancer therapy administration in tumor models. Evaluation of xenograft tumor responses to cancer treatments were carried out using conventional-frequency ultrasound at different times after chemotherapy exposure. Ultrasound data were analyzed using spectroscopic techniques and multi-parametric QUS spectral maps were generated. MMD was applied as a distance criterion, measuring alterations in each tumor in response to chemotherapy, and the extent of cell death was classified into less/more than 20% and 40% categories. Statistically significant differences were observed between “pre-” and “post-treatment” groups at different times after chemotherapy exposure, suggesting a high capability of proposed framework for detecting tumor response noninvasively. Promising results were also obtained for categorizing the extent of cell death response in each tumor using the proposed framework, with gold standard histological quantification of cell death as ground truth. The best classification results were obtained using MMD when applied on histograms of QUS parametric maps. In this case, classification accuracies of 84.7% and 88.2% were achieved for categorizing extent of tumor cell death into less/more than 20% and 40%, respectively.

Random Subspace Method in Text Categorization

In text categorization (TC), which is a supervised technique, a feature vector of terms or phrases is usually used to represent the documents. Due to the huge number of terms in even a moderate-size text corpus, high dimensional feature space is an intrinsic problem in TC. Random subspace method (RSM), a technique that divides the feature space to smaller ones each submitted to a (base) classifier (BC) in an ensemble, can be an effective approach to reduce the dimensionality of the feature space. Inspired by a similar research on functional magnetic resonance imaging (fMRI) of brain, here we address the estimation of ensemble parameters, i.e., the ensemble size (L) and the dimensionality of feature subsets (M) by defining three criteria: usability, coverage, and diversity of the ensemble. We will show that relatively medium M and small L yield an ensemble that improves the performance of a single support vector machine, which is considered as the state-of-the-art in TC.

Multiple classifier systems in texton-based approach for the classification of CT images of lung

In this paper, we propose using texton signatures based on raw pixel representation along with a parallel multiple classifier system for the classification of emphysema in computed tomography images of the lung. The multiple classifier system is composed of support vector machines on the texton signatures as base classifiers and combines their decisions using product rule. The proposed approach is tested on 168 annotated regions of interest consisting of normal tissue, centrilobular emphysema, and paraseptal emphysema. Textonbased approach in texture classification mainly has two parameters, i.e., texton size and k value in k-means. Our results show that while aggregation of single decisions by SVMs over various k values using multiple classifier systems helps to improve the results compared to single SVMs, combining over different texton sizes is not beneficial. The performance of the proposed system, with an accuracy of 95%, is similar to a recently proposed approach based on local binary patterns, which performs almost the best among other approaches in the literature.

Design of a Web-based wireless mobile teleconsultation system with a remote control camera

In this paper, the design of a mobile teleconsultation system is presented. A wireless frequency hopping spread spectrum link is used to provide mobility of the system in a hospital. The user-interface has been greatly simplified by accessing the video data and controlling the camera via any common Web-browser. Special emphasis has been put on using off-the-shelf available software/hardware components and open systems. This approach has enabled the system to have the most upto date features while being cost effective and upgradable at any time.

Tumour ROI estimation in ultrasound images via radon barcodes in patients with locally advanced breast cancer

Quantitative ultrasound (QUS) methods provide a promising framework that can non-invasively and inexpensively be used to predict or assess the tumour response to cancer treatment. The first step in using the QUS methods is to select a region of interest (ROI) inside the tumour in ultrasound images. Manual segmentation, however, is very time consuming and tedious. In this paper, a semi-automated approach will be proposed to roughly localize an ROI for a tumour in ultrasound images of patients with locally advanced breast cancer (LABC). Content-based barcodes, a recently introduced binary descriptor based on Radon transform, were used in order to find similar cases and estimate a bounding box surrounding the tumour. Experiments with 33 B-scan images resulted in promising results with an accuracy of 81%.