Brain Tumor Diagnosis Support System: A decision Fusion Framework
| dc.contributor.author | Shantta, Kalifa | |
| dc.date.accessioned | 2022-01-21T13:50:14Z | |
| dc.date.available | 2022-01-21T13:50:14Z | |
| dc.date.issued | 2022-01-21 | |
| dc.date.submitted | 2021-01-13 | |
| dc.description.abstract | An important factor in providing effective and efficient therapy for brain tumors is early and accurate detection, which can increase survival rates. Current image-based tumor detection and diagnosis techniques are heavily dependent on interpretation by neuro-specialists and/or radiologists, making the evaluation process time-consuming and prone to human error and subjectivity. Besides, widespread use of MR spectroscopy requires specialized processing and assessment of the data and obvious and fast show of the results as photos or maps for routine medical interpretative of an exam. Automatic brain tumor detection and classification have the potential to offer greater efficiency and predictions that are more accurate. However, the performance accuracy of automatic detection and classification techniques tends to be dependent on the specific image modality and is well known to vary from technique to technique. For this reason, it would be prudent to examine the variations in the execution of these methods to obtain consistently high levels of achievement accuracy. Designing, implementing, and evaluating categorization software is the goal of the suggested framework for discerning various brain tumor types on magnetic resonance imaging (MRI) using textural features. This thesis introduces a brain tumor detection support system that involves the use of a variety of tumor classifiers. The system is designed as a decision fusion framework that enables these multi-classifier to analyze medical images, such as those obtained from magnetic resonance imaging (MRI). The fusion procedure is ground on the Dempster-Shafer evidence fusion theory. Numerous experimental scenarios have been implemented to validate the efficiency of the proposed framework. Compared with alternative approaches, the outcomes show that the methodology developed in this thesis demonstrates higher accuracy and higher computational efficiency. | en |
| dc.identifier.uri | http://hdl.handle.net/10012/17937 | |
| dc.language.iso | en | en |
| dc.pending | false | |
| dc.publisher | University of Waterloo | en |
| dc.relation.uri | (http://oasis-brains.org | en |
| dc.subject | Brain Tumor Detection | en |
| dc.title | Brain Tumor Diagnosis Support System: A decision Fusion Framework | en |
| dc.type | Doctoral Thesis | en |
| uws-etd.degree | Doctor of Philosophy | en |
| uws-etd.degree.department | Electrical and Computer Engineering | en |
| uws-etd.degree.discipline | Electrical and Computer Engineering | en |
| uws-etd.degree.grantor | University of Waterloo | en |
| uws-etd.embargo.terms | 0 | en |
| uws.contributor.advisor | Basir, Otman | |
| uws.contributor.affiliation1 | Faculty of Engineering | en |
| uws.peerReviewStatus | Unreviewed | en |
| uws.published.city | Waterloo | en |
| uws.published.country | Canada | en |
| uws.published.province | Ontario | en |
| uws.scholarLevel | Graduate | en |
| uws.typeOfResource | Text | en |