Original title: The Process Of Ct Image Classifier Optimization For Pedatric Spine Segmentation
Authors: Kohúteková, Táňa
Document type: Papers
Language: cze
Publisher: Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií
Abstract: Computed tomography (CT) is a method commonly used when generating images ofa spine diagnosed with scoliosis. The main reason for this common employment is found in itspracticality: the spine in the image is clearly visible. However, while portraying, a child is exposedto a dose of radiation. To eliminate a risk of children being negatively affected, this article is tryingto find the best technique of segmentation, that could be applied also while using magneticresonance imaging (MRI). It implements a 3D Slicer equipped with Support Vector Machines(SVM) Classifier plug-in to search for the best feature combination. Afterwards, segmentationresults are compared to ground truth image, where the area of hard tissue is determined. The aim isto get Dice coefficients as close as possible to 1.
Keywords: image processing; scoliosis; segmentation; spine
Host item entry: Proceedings I of the 27st Conference STUDENT EEICT 2021: General papers, ISBN 978-80-214-5942-7

Institution: Brno University of Technology (web)
Document availability information: Fulltext is available in the Brno University of Technology Digital Library.
Original record: http://hdl.handle.net/11012/200713

Permalink: http://www.nusl.cz/ntk/nusl-447758


The record appears in these collections:
Universities and colleges > Public universities > Brno University of Technology
Conference materials > Papers