Skip to Main content Skip to Navigation
Conference papers

Comparison between threshold-based and deep learning-based bone segmentation on whole-body CT images

Abstract : Objectives: Bone segmentation can help bone disease diagnosis or post treatment assessment but manual segmentation is a time consuming and tedious task in clinical practice. In this work, three automatic methods to segment bone structures on whole body CT images were compared. Methods: A threshold-based approach with morphological operations and two deep learning methods using a 3D U-Net with different losses, one with a cross entropy/Dice loss and the second with a Hausdorff Distance/Dice loss, were developed. Ground truth bone segmentations were generated by manually correcting the results obtained with the threshold based method. The automatic bone segmentations were evaluated using a Dice score and Hausdorff distance. Visual evaluation was also performed by a medical expert. Results: Dice scores of 0.953, 0.986 and 0.978 were achieved for the Threshold-based method and the two deep learning methods, respectively. Visual evaluation showed that the deep learning method with a Hausdorff Distance/Dice loss performed the best.
Document type :
Conference papers
Complete list of metadata

https://www.hal.inserm.fr/inserm-03540472
Contributor : Elizabeth Bernardo Connect in order to contact the contributor
Submitted on : Monday, January 24, 2022 - 9:18:51 AM
Last modification on : Friday, August 5, 2022 - 2:54:52 PM

Identifiers

Citation

Noémie Moreau, Caroline Rousseau, Constance Fourcade, Gianmarco Santini, Ludovic Ferrer, et al.. Comparison between threshold-based and deep learning-based bone segmentation on whole-body CT images. Computer-Aided Diagnosis, Feb 2021, Online Only, United States. pp.100, ⟨10.1117/12.2580892⟩. ⟨inserm-03540472⟩

Share

Metrics

Record views

28