Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/35302
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.date.accessioned | 2018-10-29T10:09:04Z | - |
dc.date.available | 2018-10-29T10:09:04Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | Sant, K. (2018). Classification of brain haemorrhages in head CT scans (Bachelor's dissertation). | en_GB |
dc.identifier.uri | https://www.um.edu.mt/library/oar//handle/123456789/35302 | - |
dc.description | B.SC.(HONS)COMPUTER ENG. | en_GB |
dc.description.abstract | Brain haemorrhage is defined as a bleed in the brain tissue caused by a blood vessel breaking or due to trauma to the head. Brain haemorrhage caused by trauma is the major cause of death in young patients, whereas haemorrhages due to ruptured vessels is the third major cause of death. The quick and correct diagnosis of such pathologies is of utmost importance since a late or incorrect diagnosis can potentially lead to disabilities or even death. A bleed within the brain would result in swelling of the brain due to the blood irritating the brain tissue, increasing pressure within the brain and resulting in brain cell and tissue damage. In such cases, CT scans are mainly used due to the cheap running cost, extensive availability of the service, fast scanning and high contrasts in the image. This study utilises Artificial Intelligence and Computer Vision techniques to develop a CAD system designed to classify brain CT scan images containing haemorrhage into the type of haemorrhage based on intensity, shape and texture features. This system is a continuation of the work carried out by Mr. Napier in his final year project, which was a system that can detect the presence of haemorrhage in brain CT scans. The system accepts as inputs processed images from Mr. Napier’s detection system and outputs an image with the perimeter of the detected bleed highlighted and the classifier result as a percentage confidence in the class selected. For this study, the selected classification algorithm implemented is an Artificial Neural Network. Two different neural network structures were used, each with 220 variants. 30 anonymised CT scan sets were used, divided into a group of 24 cases used for training the neural networks and 6 cases used for testing the neural networks. Out of the 440 total neural network variants trained and tested, three variants that gave an overall percentage correctness of 88.3335%, 88.07692% and 88.10684% respectively were chosen for this system. | en_GB |
dc.language.iso | en | en_GB |
dc.rights | info:eu-repo/semantics/restrictedAccess | en_GB |
dc.subject | Brain -- Hemorrhage | en_GB |
dc.subject | CAD/CAM systems | en_GB |
dc.subject | Brain -- Tomography | en_GB |
dc.subject | Neural networks (Computer science) | en_GB |
dc.title | Classification of brain haemorrhages in head CT scans | en_GB |
dc.type | bachelorThesis | en_GB |
dc.rights.holder | The copyright of this work belongs to the author(s)/publisher. The rights of this work are as defined by the appropriate Copyright Legislation or as modified by any successive legislation. Users may access this work and can make use of the information contained in accordance with the Copyright Legislation provided that the author must be properly acknowledged. Further distribution or reproduction in any format is prohibited without the prior permission of the copyright holder. | en_GB |
dc.publisher.institution | University of Malta | en_GB |
dc.publisher.department | Faculty of Information and Communication Technology. Department of Communications and Computer Engineering | en_GB |
dc.description.reviewed | N/A | en_GB |
dc.contributor.creator | Sant, Kirsty | - |
Appears in Collections: | Dissertations - FacICT - 2018 Dissertations - FacICTCCE - 2018 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
18BSCIT0005.pdf Restricted Access | 2.13 MB | Adobe PDF | View/Open Request a copy |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.