Ehab Essa

Combining region-based and imprecise boundary-based cues for interactive medical image segmentation.

In this paper, we present an approach combining both region selection and user point selection for user-assisted segmentation as either an enclosed object or an open curve, investigate the method of image segmentation in specific medical applications (user-assisted segmentation of the media-adventitia border in intravascular ultrasound images, and lumen border in optical coherence tomography images), and then demonstrate the method with generic images to show how it could be utilized in other types of medical image and is not limited to the applications described. The proposed method combines point-based soft constraint on object boundary and stroke-based regional constraint. The user points act as attraction points and are treated as soft constraints rather than hard constraints that the segmented boundary has to pass through. The user can also use strokes to specify region of interest. The probabilities of region of interest for each pixel are then calculated, and their discontinuity is used to indicate object boundary. The combinations of different types of user constraints and image features allow flexible and robust segmentation, which is formulated as an energy minimization problem on a multilayered graph and is solved using a shortest path search algorithm. We show that this combinatorial approach allows efficient and effective interactive segmentation, which can be used with both open and closed curves to segment a variety of images in different ways. The proposed method is demonstrated in the two medical applications, that is, intravascular ultrasound and optical coherence tomography images, where image artefacts such as acoustic shadow and calcification are commonplace and thus user guidance is desirable. We carried out both qualitative and quantitative analysis of the results for the medical data; comparing the proposed method against a number of interactive segmentation techniques.

Shape prior model for media-adventitia border segmentation in IVUS using graph cut

We present a shape prior based graph cut method which does not require user initialisation. The shape prior is generalised from multiple training shapes, rather than using singular templates as priors. Weighted directed graph construction is used to impose geometrical and smooth constraints learned from priors. The proposed cost function is built upon combining selective feature extractors. A SVM classifier is used to determine an optimal combination of features in presence of calcification, fibrotic tissues, soft plaques, and metallic stent, each of which has its own characteristics in ultrasound images. Comparative analysis on manually labelled ground-truth shows superior performance of the proposed method compared to conventional graph cut methods.

A comparison of combined classifier architectures for Arabic Speech Recognition

Combined classifiers offer solution to the pattern classification problems which arise from variation of the data acquisition conditions, the signal representing the pattern to be recognized and classifier architecture itself. This paper studies the effect of classifier architecture on the overall performance of the Arabic Speech Recognition System. Five different proposed combined classifier architectures are studied and a comparison of their performance is conducted. Boosting is another type of combined classifier to improve the performance of almost any learning algorithm. We investigate the effect of combining Neural Networks by AdaBoost.M1 and propose an enhancement for AdaBoost.M1 algorithm. It is found that the proposed enhanced AdaBoost.M1 outperforms either the architectures based on ensemble approaches or the modular approaches.

Automatic IVUS media-adventitia border extraction using double interface graph cut segmentation

We present a fully automatic segmentation method to extract media-adventitia border in IVUS images. Segmentation in IVUS has shown to be an intricate process due to relatively low contrast and various forms of interferences and artifacts caused by, for example, calcification and acoustic shadow. Graph cut based methods often require careful manual initialization and produces in consistent tracing of the border. We use a double interface automatic graph cut technique to prevent the extraction of media-adventitia border from being distracted by those image features. Novel cost functions are derived from using a combination of complementary texture features. Comparative studies on manual labeled data show promising performance of the proposed method.

Cascade Multimodal Biometric System Using Fingerprint and Iris Patterns.

Unimodal biometric systems based on single biometric trait do not often afford performance requirements for the security applications. Multimodal biometric system uses two or more biometric traits consolidated in one single system to identify users of the system. Among many biometrics traits, fingerprint and iris can accurately identify system’s users due to their unique textures which extracted during the recognition process. In this paper we proposed a multimodal biometric identification system that sequentially combines fingerprint and iris traits in the identification process. The proposed system design improves the user convenience by reducing the identification time and maintaining very high accuracy. The proposed system tested on CASIA-Iris V1 database and FVC 2000 and 2002 fingerprint database. The experimental results show that proposed multimodal system is better than unimodal system using fingerprint or iris.

Interactive Segmentation of Media-Adventitia Border in IVUS

In this paper, we present an approach for user assisted seg- mentation of media-adventitia border in IVUS images. This interactive segmentation is performed by a combination of point based soft con- straint on object boundary and stroke based regional constraint. The edge based boundary constraint is imposed through searching the short- est path in a three-dimensional graph, derived from a multi-layer image representation. The user points act as attraction points and are treated as soft constraints, rather than hard constraints that the segmented bound- ary has to pass through the user specified points. User can also use strokes to specify foreground (region of interest). The probabilities of region of interest for each pixel are then calculated and their discontinuity is used to indicate object boundary. This combined approach is formulated as an energy minimization problem that is solved using a shortest path search algorithm. We show that this combined approach allows efficient and effective interactive segmentation, which is demonstrated through iden- tifying media-adventitia border in IVUS images where image artifact, such as acoustic shadow and calcification, are common place. Both qual- itative and quantitative analysis are provided based on manual labeled datasets.

Minimum S-Excess Graph for Segmenting and Tracking Multiple Borders with HMM

We present a novel HMM based approach to simultaneous segmentation of vessel walls in Lymphatic confocal images. The vessel borders are parameterized using RBFs to minimize the number of tracking points. The proposed method tracks the hidden states that indicate border locations for both the inner and outer walls. The observation for both borders is obtained using edge-based features from steerable filters. Two separate Gaussian probability distributions for the vessel borders and background are used to infer the emission probability, and the transmission probability is learned using a Baum-Welch algorithm. We transform the segmentation problem into a minimization of an s-excess graph cost, with each node in the graph corresponding to a hidden state and the weight for each node being defined by its emission probability. We define the inter-relations between neighboring nodes based on the transmission probability. We present both qualitative and quantitative analysis in comparison to the popular Viterbi algorithm.

Fog Intelligence for Real-Time IoT Sensor Data Analytics

The evolution of the Internet of things and the continuing increase in the number of sensors connected to the Internet impose big challenges regarding the management of the resulting deluge of data and network latency. Uploading sensor data over the web does not add value. Therefore, an efficient knowledge extraction technique is badly needed to reduce the amount of data transfer and to help simplify the process of knowledge management. Homoscedasticity and statistical features extraction are introduced in this paper as novelty detection enabling techniques, which help extract the important events in sensor data in real time when used with neural classifiers. Experiments have been conducted on a fog computing platform. System performance has been also evaluated on an occupancy data set and showed promising results.

Phase Contrast Cell Detection Using Multi-level Classification

In this paper, we propose a fully automated learning-based approach for detecting cells in time-lapse phase contrast images. The proposed system combines 2 machine learning approaches to achieve bottom-up image segmentation. We apply pixel-wise classification using random forests (RF) classifiers to determine the potential location of the cells. Each pixel is classified into 4 categories (cell, mitotic cell, halo effect, and background noise). Various image features are extracted at different scales to train the RF classifier. The resulting probability map is partitioned using the k-means algorithm to form potential cell regions. These regions are expanded into the neighboring areas to recover some missing or broken cell regions. To validate the cell regions, another machine learning method based on the bag-of-features and spatial pyramid encoding is proposed. The result of the second classifier can be a validated cell, a merged cell, or a noncell. In the case that the cell region is classified as a merged cell, it is split by using the seeded watershed method. The proposed method is demonstrated on several phase contrast image datasets, ie, U2OS, HeLa, and NIH 3T3. In comparison to state-of-the-art cell detection techniques, the proposed method shows improved performance, particularly in dealing with noise interference and drastic shape variations.

Automatic segmentation of lymph vessel wall using optimal surface graph cut and hidden Markov Models

We present a novel method to segment the lymph vessel wall in confocal microscopy images using Optimal Surface Segmentation (OSS) and hidden Markov Models (HMM). OSS is used to preform a pre-segmentation on the images, to act as the initial state for the HMM. We utilize a steerable filter to determine edge based filters for both of these segmentations, and use these features to build Gaussian probability distributions for both the vessel walls and the background. From this we infer the emission probability for the HMM, and the transmission probability is learned using a Baum-Welch algorithm. We transform the segmentation problem into one of cost minimization, with each node in the graph corresponding to one state, and the weight for each node being defined using its emission probability. We define the inter-relations between neighboring nodes using the transmission probability. Having constructed the problem, it is solved using the Viterbi algorithm, allowing the vessel to be reconstructed. The optimal solution can be found in polynomial time. We present qualitative and quantitative analysis to show the performance of the proposed method.