Automated Muscle Segmentation from Clinical CT Using Bayesian U-Net for Personalized Musculoskeletal Modeling
Top Cited Papers
- 10 September 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 39 (4) , 1030-1040
Abstract
We propose a method for automatic segmentation of individual muscles from a clinical CT. The method uses Bayesian convolutional neural networks with the U-Net architecture, using Monte Carlo dropout that infers an uncertainty metric in addition to the segmentation label. We evaluated the performance of the proposed method using two data sets: 20 fully annotated CTs of the hip and thigh regions and 18 partially annotated CTs that are publicly available from The Cancer Imaging Archive (TCIA) database. The experiments showed a Dice coefficient (DC) of 0.891±0.016 (mean±std) and an average symmetric surface distance (ASD) of 0.994±0.230 mm over 19 muscles in the set of 20 CTs. These results were statistically significant improvements compared to the state-of-the-art hierarchical multi-atlas method which resulted in 0.845±0.031 DC and 1.556±0.444 mm ASD. We evaluated validity of the uncertainty metric in the multi-class organ segmentation problem and demonstrated a correlation between the pixels with high uncertainty and the segmentation failure. One application of the uncertainty metric in activelearning is demonstrated, and the proposed query pixel selection method considerably reduced the manual annotation cost for expanding the training data set. The proposed method allows an accurate patient-specific analysis of individual muscle shapes in a clinical routine. This would open up various applications including personalization of biomechanical simulation and quantitative evaluation of muscle atrophy.Keywords
All Related Versions
Funding Information
- Ministry of Education, Culture, Sports, Science and Technology (19H01176, 26108004)
- Japan Society for the Promotion of Science (20407)
- AMED/ETH Strategic Japanese-Swiss Cooperative Program
This publication has 25 references indexed in Scilit:
- Multi-atlas segmentation of biomedical images: A surveyMedical Image Analysis, 2015
- The Generalized Log-Ratio Transformation: Learning Shape and Adjacency Priors for Simultaneous Thigh Muscle SegmentationIEEE Transactions on Medical Imaging, 2015
- Automatic and quantitative assessment of regional muscle volume by multi‐atlas segmentation using whole‐body water–fat MRIJournal of Magnetic Resonance Imaging, 2014
- Relationships of 35 lower limb muscles to height and body mass quantified using MRIJournal of Biomechanics, 2014
- Effect of tendon stiffness on the generated force at the Achilles tendon - 3D finite element simulation of a human triceps surae muscle during isometric contractionJournal of Biomechanical Science and Engineering, 2014
- 3D finite element models of shoulder muscles for computing lines of actions and moment armsComputer Methods in Biomechanics and Biomedical Engineering, 2012
- Femoral loads during gait in a patient with massive skeletal reconstructionClinical Biomechanics, 2012
- Quantitative computed tomographyEuropean Journal of Radiology, 2009
- Persisting muscle atrophy two years after replacement of the hipThe Journal of Bone and Joint Surgery. British volume, 2009
- Measures of the Amount of Ecologic Association Between SpeciesEcology, 1945