Mahdi Mazinani

An Automatic Approach for Learning and Tuning Gaussian Interval Type-2 Fuzzy Membership Functions Applied to Lung CAD Classification System

The potential of type-2 fuzzy sets to manage high levels of uncertainty in the subjective knowledge of experts or of numerical information has focused on control and pattern classification systems in recent years. One of the main challenges in designing a type-2 fuzzy logic system (FLS) is how to estimate the parameters of the type-2 fuzzy membership function (T2MF) and the footprint of uncertainty (FOU) from imperfect and noisy datasets. This paper presents an automatic approach to learn and tune Gaussian interval type-2 membership functions (IT2MFs) with application to multidimensional pattern classification problems. T2MFs and their FOUs are tuned according to the uncertainties in the training dataset by a combination of genetic algorithm (GA) and cross-validation techniques. In our GA-based approach, the structure of the chromosome has fewer genes than other GA methods, and chromosome initialization is more precise. The proposed approach addresses the application of the interval type-2 fuzzy logic system (IT2FLS) for the problem of nodule classification in a lung computer-aided detection system. The designed IT2FLS is compared with its type-1 fuzzy logic system (T1FLS) counterpart. The results demonstrate that the IT2FLS outperforms the T1FLS by more than 30% in terms of classification accuracy.

A Genetic type-2 fuzzy logic system for pattern recognition in computer aided detection systems

A computer aided detection (CAD) system suffers from vagueness and imprecision in both medical science and image processing techniques. These uncertainty issues in the classification components of a CAD system directly influence the accuracy. This paper takes advantage of type-2 fuzzy sets as three-dimensional fuzzy sets with high potential for managing uncertainty issues in vague environments. In this paper, an automatic optimized approach for generating and tuning type-2 Gaussian membership function (MF) parameters and their footprint of uncertainty is proposed. In this approach, two interval type-2 fuzzy logic system (IT2FLS) methods based on the Mamdani rules model are presented for tackling the uncertainty issues in classification problems in pattern recognition. Furthermore, the Genetic algorithm is employed for tuning of the MFs parameters and footprint of uncertainty. In order to assess the performance, the designed IT2FLSs are applied on a lung CAD application for classification of nodules. The ROC accuracy and mean absolute error (MAE) are considered as the performance indicators. The results reveal that the Genetic IT2FLS classifier outperforms the equivalent type-1 FLS and is capable of capturing more uncertainties.

A Fuzzy Logic System for Classification of the Lung Nodule in Digital Images in Computer Aided Detection

Digital image analysis technology suffers from imperfection, imprecision and vagueness of the input data and its propagation in all individual components of the technology including image enhancement, segmentation and pattern recognition. Furthermore, a Medical Digital Image Analysis System (MDIAS) such as computer aided detection (CAD) technology deals with another source of uncertainty that is inherent in an image-based practice of medicine. While there are several technology-oriented studies reported in developing CAD applications, no attempt has been made to address, model and integrate these types of uncertainty in the design of the system components even though uncertainty issues directly affect the performance and its accuracy. In order to tackle the problem of uncertainty in the classification design of the system two fuzzy methods are employed and are evaluated for the lung nodule CAD application. The Mamdani model and the Sugeno model of the fuzzy logic system are implemented and the classification results are compared and evaluated through ROC curve analysis and root mean squared error methods. The novelty of the study is to investigate the effect of training algorithms on the performance of the CAD system. The results reveal that the fuzzy logic system with hybrid-training is superior to the other models in terms of root-mean-squared error and ROC curve sensitivity and specificity rates.

Automatic Segmentation of Soft Plaque by Modeling the Partial Volume Problem in the Coronary Artery

Automatic segmentation and quantification of stenosis is an important task in assessing coronary artery disease, especially when the investigation of the disease progress is considered. The reproducibility and robustness of the segmentation algorithm against partial volume effect and noise is critical for an accurate quantification. A major issue in the quantification of the stenosis is to segment the soft plaque in the blood vessel. While there are several approaches for segmentation of the volume of the blood vessel and soft plaque in the literature, the main drawback of these approaches is making a deterministic decision in terms of assigning a particular voxel to only one type of tissue (such as blood vessel, soft plaque or surrounding area). However in reality, because of the partial volume effect, a voxel may contain more than one tissue type. In particular, using deterministic methods for quantification of the small objects such as thin blood vessels or soft plaque may lead to inaccurate results and higher inter and intra-scan variability. In this paper, an approach is proposed to tackle the partial volume effect problem using an adaptive fuzzy algorithm incorporating a Markov random field model. The presented method segments the blood vessel, soft plaque and surrounding tissue areas more accurately. The algorithm is applied to several datasets and the outcomes have been judged visually by a qualified radiologist. The proposed algorithm has the potential to be applied for the accurate quantification of the degree of stenosis.

Modeling uncertainty in classification design of a computer-aided detection system

A computerized image analysis technology suffers from imperfection, imprecision and vagueness of the input data and its propagation in all individual components of the technology including image enhancement, segmentation and pattern recognition. Furthermore, a Computerized Medical Image Analysis System (CMIAS) such as computer aided detection (CAD) technology deals with another source of uncertainty that is inherent in image-based practice of medicine. While there are several technology-oriented studies reported in developing CAD applications, no attempt has been made to address, model and integrate these types of uncertainty in the design of the system components, even though uncertainty issues directly affect the performance and its accuracy. In this paper, the main uncertainty paradigms associated with CAD technologies are addressed. The influence of the vagueness and imprecision in the classification of the CAD, as a second reader, on the validity of ROC analysis results is defined. In order to tackle the problem of uncertainty in the classification design of the CAD, two fuzzy methods are applied and evaluated for a lung nodule CAD application. Type-1 fuzzy logic system (T1FLS) and an extension of it, interval type-2 fuzzy logic system (IT2FLS) are employed as methods with high potential for managing uncertainty issues. The novelty of the proposed classification methods is to address and handle all sources of uncertainty associated with a CAD system. The results reveal that IT2FLS is superior to T1FLS for tackling all sources of uncertainty and significantly, the problem of inter and intra operator observer variability.

A Practical Approach for Measuring IT Effectiveness in Business Processes

Information technology (IT) is an important component in organizations competitive advantages. IT services directly effect on business processes and organizations success. It is essential to adapt the IT function with business objectives and priorities, and work toward the optimization of IT resources globally for higher performance of the organization. Most companies spend too much time for determining how much money to spend on IT and not enough time determining how to manage and allocate their IT spending in any part of business processes. Seeking high-performance results from the use of IT is very important for business executive managers and information technology managers in every organization. In this paper a practical approach for measuring the amount of IT effectiveness on business processes by using a fuzzy approach that is known as MADM (multiple-attribute decision making) has been proposed. The amount of this metric enables managers to discover exactly where business performance improvement opportunities lie and finally elevates IT function to its rightful place in organizations.