Showing papers by "Mohamed Abdel-Nasser published in 2016"

Towards cost reduction of breast cancer diagnosis using mammography texture analysis

Abstract: In this paper we analyse the performance of various texture analysis methods for the purpose of reducing the number of false positives in breast cancer detection; as a result, the cost of breast cancer diagnosis would be reduced. We consider well-known methods such as local binary patterns, histogram of oriented gradients, co-occurrence matrix features and Gabor filters. Moreover, we propose the use of local directional number patterns as a new feature extraction method for breast mass detection. For each method, different classifiers are trained on the extracted features to predict the class of unknown instances. In order to improve the mass detection capability of each individual method, we use feature combination techniques and classifier majority voting. Some experiments were performed on the images obtained from a public breast cancer database, achieving promising levels of sensitivity and specificity.

Automatic nipple detection in breast thermograms

Abstract: We propose an automatic and accurate method to detect nipples in thermograms.The proposed method determines the nipples using a novel selection algorithm.We achieve accurate nipple detection results in real-time. Breast cancer is one of the most dangerous diseases for women. Detecting breast cancer in its early stage may lead to a reduction in mortality. Although the study of mammographies is the most common method to detect breast cancer, it is outperformed by the analysis of thermographies in dense tissue (breasts of young women). In the last two decades, several computer-aided diagnosis (CAD) systems for the early detection of breast cancer have been proposed. Breast cancer CAD systems consist of many steps, such as segmentation of the region of interest, feature extraction, classification and nipple detection. Indeed, the nipple is an important anatomical landmark in thermograms. The location of the nipple is invaluable in the analysis of medical images because it can be used in several applications, such as image registration and modality fusion. This paper proposes an unsupervised, automatic, accurate, simple and fast method to detect nipples in thermograms. The main stages of the proposed method are: human body segmentation, determination of nipple candidates using adaptive thresholding and detection of the nipples using a novel selection algorithm. Experiments have been carried out on a thermograms dataset to validate the proposed method, achieving accurate nipple detection results in real-time. We also show an application of the proposed method, breast cancer classification in dynamic images, where the new nipple detection technique is used to segment the region of the two breasts from the infrared image. A dataset of dynamic thermograms has been used to validate this application, achieving good results.

The Impact of Pixel Resolution, Integration Scale, Preprocessing, and Feature Normalization on Texture Analysis for Mass Classification in Mammograms

Abstract: Texture analysis methods are widely used to characterize breast masses in mammograms. Texture gives information about the spatial arrangement of the intensities in the region of interest. This information has been used in mammogram analysis applications such as mass detection, mass classification, and breast density estimation. In this paper, we study the effect of factors such as pixel resolution, integration scale, preprocessing, and feature normalization on the performance of those texture methods for mass classification. The classification performance was assessed considering linear and nonlinear support vector machine classifiers. To find the best combination among the studied factors, we used three approaches: greedy, sequential forward selection (SFS), and exhaustive search. On the basis of our study, we conclude that the factors studied affect the performance of texture methods, so the best combination of these factors should be determined to achieve the best performance with each texture method. SFS can be an appropriate way to approach the factor combination problem because it is less computationally intensive than the other methods.

Ultrasound Image Enhancement Using a Deep Learning Architecture

Abstract: Ultrasound images have been used for detecting several diseases such as kidney stones and breast tumors. However, ultrasound images suffer from speckle noise and several artifacts, thus degrading the quality of the images. In this paper, we propose a new method for enhancing the quality of ultrasound images. This method is a multi-frame super resolution approach, where it extracts a high resolution image from a set of low resolution images (down-sampled, blurred, and shifted versions of a high resolution source image). The critical step in multi-frame super resolution approaches is motion estimation, especially when there is noise in the images. To cope with this issue, we propose the use of a deep learning based method for motion estimation. Experimental results using synthetic and realistic sequences demonstrate that our proposed approach is feasible and effective for enhancing the quality of ultrasound images.

Exploiting the Kinematic of the Trajectories of the Local Descriptors to Improve Human Action Recognition

Abstract: This paper presents a video representation that exploits the properties of the trajectories of local descriptors in human action videos. We use spatial-temporal information, which is led by trajectories to extract kinematic properties: tangent vector, normal vector, bi-normal vector and curvature. The results show that the proposed method provides comparable results compared to the state-of-the-art methods. In turn, it outperforms compared methods in terms of time complexity.

Analysis of Temporal Coherence in Videos for Action Recognition

Abstract: This paper proposes an approach to improve the performance of activity recognition methods by analyzing the coherence of the frames in the input videos and then modeling the evolution of the coherent frames, which constitute a sub-sequence, to learn a representation for the videos. The proposed method consist of three steps: coherence analysis, representation leaning and classification. Using two state-of-the-art datasets (Hollywood2 and HMDB51), we demonstrate that learning the evolution of subsequences in lieu of frames, improves the recognition results and makes actions classification faster.