Label efficient segmentation of single slice thigh CT with two-stage pseudo labels
Authors:
- Qi YangQYQi Yang
- Xin YuXYXin Yu
- Ho Hin LeeHLHo Hin Lee
- Yucheng TangYTYucheng Tang
- Shunxing BaoSBShunxing Bao
- Kristofer S. GravensteinKGKristofer S. Gravenstein
- Ann Zenobia MooreAMAnn Zenobia Moore
- Sokratis MakrogiannisSokratis Makrogiannis
- Luigi FerrucciLFLuigi Ferrucci
- Bennett A. LandmanBLBennett A. Landman
Open Access
- 19 May 2022
- journal article
- research article
- Published by SPIE-Intl Soc Optical Eng in Journal of Medical Imaging
- Vol. 9 (05) , 052405-11
Abstract
Estimating volumes and masses of total body components is important for research of cancer, joint replacement, and exercise physiology.1 Full body CT scans can be used to calculate whole body compositions directly. However, it is hard to acquire a typical full body CT in the usual medical context due to the intense radiology dose. Mourtzakis et al.2 proposed that body components measured on abdomen or thigh slices are highly correlated with the mass of whole-body tissues. Thus, accurate segmentation of thigh slices can quantify tissue area properties to estimate body composition without requiring additional irradiation or examinations. Thus, this paper aims to segment muscle, fat, and bones from 2D thigh and lower leg CT slices.Keywords
Funding Information
- National Science Foundation (2040462)
This publication has 10 references indexed in Scilit:
- Deep learning methods for automatic segmentation of lower leg muscles and bones from MRI scans of children with and without cerebral palsyNMR in Biomedicine, 2021
- Text Data Augmentation for Deep LearningJournal of Big Data, 2021
- Self-supervised learning for medical image analysis using image context restorationMedical Image Analysis, 2019
- RIL-Contour: a Medical Imaging Dataset Annotation Tool for and with Deep LearningJournal of Digital Imaging, 2019
- Quantitative analysis of skeletal muscle by computed tomography imaging—State of the artJournal of Orthopaedic Translation, 2018
- UNet++: A Nested U-Net Architecture for Medical Image Segmentation2018
- Body composition estimation from selected slices: equations computed from a new semi-automatic thresholding method developed on whole-body CT scansPeerJ, 2017
- Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?IEEE Transactions on Medical Imaging, 2016
- FSLNeuroImage, 2012
- A practical and precise approach to quantification of body composition in cancer patients using computed tomography images acquired during routine careApplied Physiology, Nutrition, and Metabolism, 2008