Abnormality detection using classifiers is one of the recent research areas where much importance is given. It is one of the critical issues where excessive care needs to be taken for better diagnosis. An input image may contain excessive information either wanted or unwanted which depends upon the problem formulation. The problem in this project is to analyze the performance of the classifier in terms of its efficiency in detecting abnormalities in medical images. Any classifier needs to detect the carcinogenesis with respect to the efficiency in time of detection and performance. Here two classifiers are selected namely Singular Value Decomposition (SVD), and Principle Component Analysis (PCA). Both the SVD and PCA are applied for dual class classification procedure. The performance analysis of all these classifiers are analyzed using the classifier performance measures like, Sensitivity, Selectivity, Average Detection, Perfect Classification, Missed Classification, False Alarm, F-score and Quality Metrics. Here CT images of brain and skull are used for analysis. Two sets of 30 images are taken which contain both normal and abnormal ones.
Inhaltsverzeichnis (Table of Contents)
- INTRODUCTION
- SELECTING THE REGION OF INTEREST
- FEATURE EXTRACTION OF MEDICAL IMAGES
- FEATURE CLASSIFICATION USING SVD
- RESULTS AND DISCUSSION
Zielsetzung und Themenschwerpunkte (Objectives and Key Themes)
This book aims to introduce newcomers to the field of feature extraction concepts for medical images, a rapidly developing area in engineering. It provides a brief overview of different classifiers used for detecting abnormalities in medical images, outlining their role in the design, implementation, research, and invention of new image processing techniques. The book caters to practicing engineers, researchers, and students at both undergraduate and graduate levels.
- Feature extraction techniques for medical images.
- Classifiers used in medical image abnormality detection.
- Preprocessing techniques, including region of interest selection.
- Performance evaluation of classifiers using metrics like sensitivity, selectivity, and F-score.
- Application of feature extraction and classification in medical image analysis, specifically for Computer Tomography (CT) images of the brain and skull.
Zusammenfassung der Kapitel (Chapter Summaries)
- Chapter 1: INTRODUCTION This chapter introduces the fundamental concepts of selecting the region of interest (ROI), feature extraction, and various classifiers applied for detecting abnormalities in Computer Tomography (CT) images. It highlights the importance of selecting the region of interest as a preprocessing step that enhances classifier performance.
- Chapter 2: SELECTING THE REGION OF INTEREST This chapter delves into the importance of selecting the region of interest (ROI) as a crucial preprocessing stage in abnormality detection. It explains how efficient ROI selection directly impacts the effectiveness of the detection process, particularly in cancer detection. This stage can improve the efficiency and performance of both feature extraction and classification by focusing on relevant regions for further processing.
- Chapter 3: FEATURE EXTRACTION OF MEDICAL IMAGES This chapter explores the process of feature extraction in medical images, aiming to represent data in a compact and unique form. It emphasizes the importance of feature selection in reducing redundancy and maximizing the joint dependency with the target variable. The chapter discusses the challenges posed by medical image processing and classification, including the need for extensive storage space and processing time. It highlights the wavelet transform as an efficient technique for data analysis, particularly in image processing applications.
- Chapter 4: FEATURE CLASSIFICATION USING SVD This chapter focuses on the application of Singular Value Decomposition (SVD) for feature classification. It explores the use of SVD for dual class classification procedures and discusses its role in abnormality detection. The chapter also examines the performance analysis of SVD, utilizing measures such as sensitivity, selectivity, and F-score to evaluate its efficiency.
Schlüsselwörter (Keywords)
The main keywords and focus topics include medical image processing, feature extraction, classification, Computer Tomography (CT) images, region of interest (ROI), Singular Value Decomposition (SVD), Principle Component Analysis (PCA), sensitivity, selectivity, and F-score.
- Arbeit zitieren
- Sunil Kumar Prabhakar (Autor:in), Harikumar Rajaguru (Autor:in), Vinoth Kumar Bojan (Autor:in), 2014, Feature Extraction and Different Classifiers Applied for Detection of Abnormalities in Computer Tomography (CT) Images, München, GRIN Verlag, https://www.hausarbeiten.de/document/287937
