Improved distinct bone segmentation from upper-body CT using binary-prediction-enhanced multi-class inference.
Authors:
Open Access
- 20 May 2022
- journal article
- research article
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 17 (11) , 2113-2120
Abstract
Purpose:: Automated distinct bone segmentation has many applications in planning and navigation tasks. 3D U-Nets have previously been used to segment distinct bones in the upper body, but their performance is not yet optimal. Their most substantial source of error lies not in confusing one bone for another, but in confusing background with bone-tissue. Methods:: In this work, we propose binary-prediction-enhanced multi-class (BEM) inference, which takes into account an additional binary background/bone-tissue prediction, to improve the multi-class distinct bone segmentation. We evaluate the method using different ways of obtaining the binary prediction, contrasting a two-stage approach to four networks with two segmentation heads. We perform our experiments on two datasets: An in-house dataset comprising 16 upper-body CT scans with voxelwise labelling into 126 distinct classes, and a public dataset containing 50 synthetic CT scans, with 41 different classes. Results:: The most successful network with two segmentation heads achieves a class-median Dice coefficient of 0.85 on cross-validation with the upper-body CT dataset. These results outperform both our previously published 3D U-Net baseline with standard inference, and previously reported results from other groups. On the synthetic dataset, we also obtain improved results when using BEM-inference. Conclusion:: Using a binary bone-tissue/background prediction as guidance during inference improves distinct bone segmentation from upper-body CT scans and from the synthetic dataset. The results are robust to multiple ways of obtaining the bone-tissue segmentation and hold for the two-stage approach as well as for networks with two segmentation heads.Keywords
Funding Information
- Werner Siemens-Stiftung
This publication has 15 references indexed in Scilit:
- 3D Segmentation Networks for Excessive Numbers of Classes: Distinct Bone Segmentation in Upper Bodies2020
- Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation2020
- Bone segmentation on whole-body CT using convolutional neural network with novel data augmentation techniquesComputers in Biology and Medicine, 2020
- Automatic segmentation of the mandible from computed tomography scans for 3D virtual surgical planning using the convolutional neural networkPhysics in Medicine & Biology, 2019
- Deep learning for segmentation of 49 selected bones in CT scans: First step in automated PET/CT-based 3D quantification of skeletal metastasesEuropean Journal of Radiology, 2019
- Automatic bone segmentation in whole-body CT imagesInternational Journal of Computer Assisted Radiology and Surgery, 2018
- Automatic and hierarchical segmentation of the human skeleton in CT imagesPhysics in Medicine & Biology, 2017
- 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation2016
- V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015