Naoki Kamiya1, Jing Li2, Masanori Kume3, Hiroshi Fujita3, Dinggang Shen4, Guoyan Zheng5. 1. School of Information Science and Technology, Aichi Prefectural University, Nagakute, Japan. 2. Institute for Surgical Technology and Biomechanics, University of Bern, Bern, Switzerland. 3. Department of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu University, Gifu, Japan. 4. Department of Brain and Cognitive Engineering, Korea University, Seoul, 02841, Republic of Korea. dgshen@med.unc.edu. 5. Institute for Surgical Technology and Biomechanics, University of Bern, Bern, Switzerland. guoyan.zheng@istb.unibe.ch.
Abstract
PURPOSE: To develop and validate a fully automatic method for segmentation of paraspinal muscles from 3D torso CT images. METHODS: We propose a novel learning-based method to address this challenging problem. Multi-scale iterative random forest classifications with multi-source information are employed in this study to speed up the segmentation and to improve the accuracy. Here, multi-source images include the original torso CT images and later also the iteratively estimated and refined probability maps of the paraspinal muscles. We validated our method on 20 torso CT data with associated manual segmentation. We randomly partitioned the 20 CT data into two evenly distributed groups and took one group as the training data and the other group as the test data. RESULTS: The proposed method achieved a mean Dice coefficient of 93.0%. It took on average 46.5 s to segment a 3D torso CT image with the size ranging from [Formula: see text] voxels to [Formula: see text] voxels. CONCLUSIONS: Our fully automatic, learning-based method can accurately segment paraspinal muscles from 3D torso CT images. It generates segmentation results that are better than those achieved by the state-of-the-art methods.
PURPOSE: To develop and validate a fully automatic method for segmentation of paraspinal muscles from 3D torso CT images. METHODS: We propose a novel learning-based method to address this challenging problem. Multi-scale iterative random forest classifications with multi-source information are employed in this study to speed up the segmentation and to improve the accuracy. Here, multi-source images include the original torso CT images and later also the iteratively estimated and refined probability maps of the paraspinal muscles. We validated our method on 20 torso CT data with associated manual segmentation. We randomly partitioned the 20 CT data into two evenly distributed groups and took one group as the training data and the other group as the test data. RESULTS: The proposed method achieved a mean Dice coefficient of 93.0%. It took on average 46.5 s to segment a 3D torso CT image with the size ranging from [Formula: see text] voxels to [Formula: see text] voxels. CONCLUSIONS: Our fully automatic, learning-based method can accurately segment paraspinal muscles from 3D torso CT images. It generates segmentation results that are better than those achieved by the state-of-the-art methods.
Entities:
Keywords:
CT; Paraspinal muscles; Random forest; Segmentation
Authors: Lacey E Bresnahan; Justin S Smith; Alfred T Ogden; Steven Quinn; George R Cybulski; Narina Simonian; Raghu N Natarajan; Richard D Fessler; Richard G Fessler Journal: Clin Spine Surg Date: 2017-04 Impact factor: 1.876