Abstract
In this paper, an optimized bilevel brain tumor diagnostic system for identifying the tumor type at the first level and grade of the identified tumor at the second level is proposed using genetic algorithm, decision tree, and fuzzy rule-based approach. The dataset is composed of axial MRI of brain tumor types and grades. From the images, various features such as first and second order statistical and textural features are extracted (26 features). In the first level, tumor type classification was done using decision tree constructed with all features. Further evolutionary computing using genetic algorithms (GA) was applied to select the optimal discriminating feature set (5 features) and classification using the decision tree constructed with the reduced feature set resulted in better performance. In the second level, grade classification, a fuzzy rule-based approach was used to resolve the uncertainty in discriminating the tumor grades II and III. Membership functions of all grades were defined for all features extracted from brain tumor grade images, to derive the fuzzy inference rules for grade discrimination. Similar to type classification with GA, better grade discrimination performance was exhibited with fuzzy inference rules derived using optimal feature set (13 features) using GA. Overall performance comparison of the proposed bilevel classifier with all features vs GA-based feature selection, shows that evolutionary computing combined with fuzzy rule-based approach is successful in reducing false positives, thereby enhancing classifier performance.
Highlights
Medical imaging technology has revolutionized health care over the decades, enabling physicians to diagnose disease earlier and improve patient health
In the present research study, an optimized bilevel classification system is proposed with the following objectives: reducing the false positive rate during tumor type and grade classification, identification of optimal feature set for attaining maximum classification accuracy using decision tree and fuzzy rule-based approach with Genetic algorithm (GA) and reducing the uncertainty between the grades II and III of astrocytoma brain tumor
The classifiers built using decision tree algorithm and fuzzy rule-based approach gave decent accuracies for type and grade classification respectively, but when combined with genetic algorithm for selection of optimal feature set, showed significant improvement in the performance measures which is very much necessary for an automation system developed for medical diagnosis
Summary
Medical imaging technology has revolutionized health care over the decades, enabling physicians to diagnose disease earlier and improve patient health. Medical images can be acquired through various modalities such as magnetic resonance imaging (MRI), computed tomography (CT), single photon emission computed tomography, ultrasonography, and positron emission tomography. MRI-based medical image analysis is popularly used in brain image analysis in recent days as it is more suitable for efficient and objective evaluation of large data. Brain tumors are abnormal and uncontrolled proliferations of cells and it is believed to be the most lethal disease [1]. Timely diagnosis of this disease is important for proper treatment for the patients; it crucially determines their lifetime.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
