Semi-automatic CT Image Segmentation using Random Forests Learned from Partial Annotations

Oldřich Kodym, Michal Španěl

Abstract

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 various CT datasets using fully expert-annotated segmentations of these tissues. Dice coefficient of overlap is 0.976 ± 0.014 for hard tissue segmentation and 0.978 ± 0.008 for kidney segmentation, achieving competitive results with other task-specific methods.

Download


Paper Citation


in Harvard Style

Kodym O. and Španěl M. (2018). Semi-automatic CT Image Segmentation using Random Forests Learned from Partial Annotations.In Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: BIOIMAGING, ISBN 978-989-758-278-3, pages 124-131. DOI: 10.5220/0006588801240131


in Bibtex Style

@conference{bioimaging18,
author={Oldřich Kodym and Michal Španěl},
title={Semi-automatic CT Image Segmentation using Random Forests Learned from Partial Annotations},
booktitle={Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: BIOIMAGING,},
year={2018},
pages={124-131},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006588801240131},
isbn={978-989-758-278-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: BIOIMAGING,
TI - Semi-automatic CT Image Segmentation using Random Forests Learned from Partial Annotations
SN - 978-989-758-278-3
AU - Kodym O.
AU - Španěl M.
PY - 2018
SP - 124
EP - 131
DO - 10.5220/0006588801240131