Sameem Abdul Kareem

Automated breast profile segmentation for ROI detection using digital mammograms

Mammography is currently the most effective imaging modality used by radiologists for the screening of breast cancer. Finding an accurate, robust and efficient breast profile segmentation technique still remains a challenging problem in digital mammography. Extraction of the breast profile region and the pectoral muscle is an essential pre-processing step in the process of computer-aided detection. Primarily it allows the search for abnormalities to be limited to the region of the breast tissue without undue influence from the background of the mammogram. The presence of pectoral muscle in mammograms biases detection procedures, which recommends removing the pectoral muscle during mammogram pre-processing. In this paper we explore an automated technique for mammogram segmentation. The proposed algorithm uses morphological preprocessing and seeded region growing (SRG) algorithm in order to: (1) remove digitization noises, (2) suppress radiopaque artifacts, (3) separate background region from the breast profile region, and (4) remove the pectoral muscle, for accentuating the breast profile region. To demonstrate the capability of our proposed approach, digital mammograms from two separate sources are tested using Ground Truth (GT) images for evaluation of performance characteristics. Experimental results obtained indicate that the breast regions extracted accurately correspond to the respective GT images.

An Image Processing Application for the Localization and Segmentation of Lymphoblast Cell Using Peripheral Blood Images

An important preliminary step in the diagnosis of leukemia is the visual examination of the patient’s peripheral blood smear under the microscope. Morphological changes in the white blood cells can be an indicator of the nature and severity of the disease. Manual techniques are labor intensive, slow, error prone and costly. A computerized system can be used as a supportive tool for the specialist in order to enhance and accelerate the morphological analysis process. This research present a new method that integrates color features with the morphological reconstruction to localize and isolate lymphoblast cells from a microscope image that contains many cells. The localization and segmentation are conducted using a proposed method that consists of an integration of several digital image processing techniques. 180 microscopic blood images were tested, and the proposed framework managed to obtain 100% accuracy for the localization of the lymphoblast cells and separate it from the image scene. The results obtained indicate that the proposed method can be safely used for the purpose of lymphoblast cells localization and segmentation and subsequently, aiding the diagnosis of leukemia.

A Robust Feature Extraction and Selection Method for the Recognition of Lymphocytes versus Acute Lymphoblastic Leukemia

An essential part of the diagnosis and treatment of leukemia is the visual examination of the patients peripheral blood smear under the microscope. Morphological changes in the white blood cells are commonly used to determine the nature of the malignant cells, namely blasts. Manual techniques are labor intensive slow, subjected to error and costly. A computerized system can be used as an aiding tool for the specialist in order to improve and accelerate the morphological analysis process. This paper presents and application of feature extraction, selection and cell classification to the recognition and differentiation of normal lymphocytes versus abnormal lymphoblast cells on the image of peripheral blood smears. This is considered as a very useful procedure in the initial treatment process of leukemia patients. A computerized recognition system has been developed, and the results of its numerical verification are presented and discussed. The methodology demonstrates that the application of pattern recognition is a powerful tool for the differentiation of normal lymphocytes and acute lymphoblastic leukemia, leading to the improvement in the early effective treatment for leukemia.

Automated Bone Age Assessment: Motivation, Taxonomies, and Challenges

Bone age assessment (BAA) of unknown people is one of the most important topics in clinical procedure for evaluation of biological maturity of children. BAA is performed usually by comparing an X-ray of left hand wrist with an atlas of known sample bones. Recently, BAA has gained remarkable ground from academia and medicine. Manual methods of BAA are time-consuming and prone to observer variability. This is a motivation for developing automated methods of BAA. However, there is considerable research on the automated assessment, much of which are still in the experimental stage. This survey provides taxonomy of automated BAA approaches and discusses the challenges. Finally, we present suggestions for future research.

Using Genetic Algorithm to Select Materialized Views Subject to Dual Constraints

Data Warehouse is an approach in which data from multiple heterogeneous and distributed operational systems(OLTP) are extracted, transformed and loaded into a central repository for the purpose of decision making. Since such databases stores huge amounts of historical data, it is necessary to devise methods by which complex OLAP queries can be answered as fast as possible. OLAP is an approach which facilitates analytical queries accessing multidimensional databases. Using materialized views as pre-computed results for time-consuming queries is a common method for speeding up analytical queries. However, some constraints do not allow the systems to create all possible views. Therefore, one of the crucial decisions that data warehouse designers need to make is in the selection of the right set of views to be materialized.This paper focuses on solving the view materialization and selection problem using a genetic algorithm approach subject to both of disk space and maintenance considerations.

Ontology-Based Multimedia Presentation Generation

Multimedia data are illusory entities for the machines. Their contents include interpretable data as well as binary representations. Understanding and accessing the content-driven information for multimedia objects allow us to design an efficient multimedia querying and retrieval system. In this paper, we propose a framework to represent the multimedia information and object roles in order to generate automatic multimedia presentations. The proposed architecture attempts to represent the semantic information and the relations amongst the multimedia objects in a disclosure domain. Thus, the system is domain dependent. The represented data associates with the presentation mechanisms to create an integrated presentation generation system. A multi-layer design defines the various levels of abstraction for the proposed framework.

Identifying ISI-Indexed Articles by Their Lexical Usage: A Text Analysis Approach

This research creates an architecture for investigating the existence of probable lexical divergences between articles, categorized as Institute for Scientific Information (ISI) and non‐ISI, and consequently, if such a difference is discovered, to propose the best available classification method. Based on a collection of ISI‐ and non‐ISI‐indexed articles in the areas of business and computer science, three classification models are trained. A sensitivity analysis is applied to demonstrate the impact of words in different syntactical forms on the classification decision. The results demonstrate that the lexical domains of ISI and non‐ISI articles are distinguishable by machine learning techniques. Our findings indicate that the support vector machine identifies ISI‐indexed articles in both disciplines with higher precision than do the Naïve Bayesian and K‐Nearest Neighbors techniques.

An Adaptive Fuzzy Regression Model for the Prediction of Dichotomous Response Variables

This paper proposes an adaptive technique in the prediction of dichotomous response variable by combining fuzzy concept with statistical logistic regression. The model was tested on an oral cancer dataset in predicting oral cancer susceptibility. In this paper we will present the development, evaluation and validation of the proposed model based on the experiment carried out. Explanatory power of the adaptive model was calculated and compared with fuzzy neural network and statistical logistic regression models using calibration and discrimination techniques. Area under ROC values calculated indicates that the proposed model has compatible predictive ability to both fuzzy neural network and statistical logistic regression models.

RETRACTED ARTICLE: Feature extraction and ML techniques for static gesture recognition

AbstractThe main objective of this study is to explore the utility of a neural network-based approach in hand gesture recognition. The proposed system presents two recognition algorithms to recognize a set of six specific static hand gestures, namely open, close, cut, paste, maximize, and minimize. The hand gesture image is passed through three stages: preprocessing, feature extraction, and classification. In the first method, the hand contour is used as a feature that treats scaling and translation of problems (in some cases). However, the complex moment algorithm is used to describe the hand gesture and to treat the rotation problem in addition to scaling and translation. The back-propagation learning algorithm is employed in the multilayer neural network classifier. The second method proposed in this article achieves better recognition rate than the first method.

Failure recovery of world-altering composite semantic services - a two phase approach

Composite Web services are self-evidently failure-prone. A recovery process is required to survive the execution flow. We propose a method to recover a composite service from a failure. The method replaces a subdigraph of a composite service with its semantically similar one. Our work is motivated by a marked trade-off of multiple needs, i.e. to increase the replacement probability in a minimum delay, a high accuracy and yet no compromise in quality of service. To address the issues, we 1) broaden the subdigraph elimination starting point to even well-executed world-altering services, 2) calculate the prerequisites in an offline phase, and 3) rank the candidate replacements. Our preliminary result shows the efficiency of our method.