Conference paper

KODYM Oldřich and ŠPANĚL Michal. 3D Image Segmentation using Graph-Cut and Random Forests Learned from Partial Annotations. In: Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: BIOIMAGING. Funchal: Institute for Systems and Technologies of Information, Control and Communication, 2018, pp. 124-131. ISBN 978-989-758-278-3. Available from: http://www.scitepress.org/DigitalLibrary/PublicationsDetail.aspx?ID=3oP1dAKzK9U=&t=1
Publication language:english
Original title:3D Image Segmentation using Graph-Cut and Random Forests Learned from Partial Annotations
Title (cs):Segmentace 3D obrazu s využítím metod Graph-Cut a Random Forests
Pages:124-131
Proceedings:Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: BIOIMAGING
Conference:5th Iternational Conference on Bioimaging
Place:Funchal, PT
Year:2018
URL:http://www.scitepress.org/DigitalLibrary/PublicationsDetail.aspx?ID=3oP1dAKzK9U=&t=1
ISBN:978-989-758-278-3
DOI:10.5220/0006588801240131
Publisher:Institute for Systems and Technologies of Information, Control and Communication
Keywords
Computed Tomography, Semi-automatic Segmentation, Random Forests, Graph-Cut
Annotation
Human tissue segmentation is a critical step not only in the process of their visualization and diagnostics but also for pre-operative planning and custom implants engineering. Manual segmentation of three-dimensional data obtained through CT scanning is very time demanding task for clinical experts and therefore the automation of this process is required. Results of fully automatic approaches often lack the required precision in cases of non-standard treatment, which is often the case when computer planning is important, and thus semi-automatic approaches demanding a certain level of expert interaction are being designed. This work presents a semi-automatic method of 3D segmentation applicable to arbitrary tissue that takes several manually annotated slices as an input. These slices are used for training a random forest classifiers to predict the annotation for the remaining part of the CT scan and final segmentation is obtained using the graph-cut method. Precision of the proposed method is evaluated  on CT datasets of hard tissue including tibia, humerus and radius bones, mandible and single teeth using the Dice coefficient of overlap compared to  fully expert-annotated segmentations of these tissues.
BibTeX:
@INPROCEEDINGS{
   author = {Old{\v{r}}ich Kodym and Michal {\v{S}}pan{\v{e}}l},
   title = {3D Image Segmentation using Graph-Cut and Random
	Forests Learned from Partial Annotations},
   pages = {124--131},
   booktitle = {Proceedings of the 11th International Joint Conference on
	Biomedical Engineering Systems and Technologies - Volume 2:
	BIOIMAGING},
   year = 2018,
   location = {Funchal, PT},
   publisher = {Institute for Systems and Technologies of Information,
	Control and Communication},
   ISBN = {978-989-758-278-3},
   doi = {10.5220/0006588801240131},
   language = {english},
   url = {http://www.fit.vutbr.cz/research/view_pub.php?id=11508}
}

Your IPv4 address: 34.204.179.0