scholarly journals Surface Muscle Segmentation Using 3D U-Net Based on Selective Voxel Patch Generation in Whole-Body CT Images

2020 ◽  
Vol 10 (13) ◽  
pp. 4477
Author(s):  
Naoki Kamiya ◽  
Ami Oshima ◽  
Xiangrong Zhou ◽  
Hiroki Kato ◽  
Takeshi Hara ◽  
...  
Keyword(s):  
Three Dimensional ◽  
Ct Images ◽  
Whole Body ◽  
Test Case ◽  
Whole Body Ct ◽  
Segmentation Accuracy ◽  
Small Muscle ◽  
Using Data ◽  
Muscle Segmentation ◽  
Body Ct

This study aimed to develop and validate an automated segmentation method for surface muscles using a three-dimensional (3D) U-Net based on selective voxel patches from whole-body computed tomography (CT) images. Our method defined a voxel patch (VP) as the input images, which consisted of 56 slices selected at equal intervals from the whole slices. In training, one VP was used for each case. In the test, multiple VPs were created according to the number of slices in the test case. Segmentation was then performed for each VP and the results of each VP merged. The proposed method achieved a segmentation accuracy mean dice coefficient of 0.900 for 8 cases. Although challenges remain in muscles adjacent to visceral organs and in small muscle areas, VP is useful for surface muscle segmentation using whole-body CT images with limited annotation data. The limitation of our study is that it is limited to cases of muscular disease with atrophy. Future studies should address whether the proposed method is effective for other modalities or using data with different imaging ranges.

Saliency-based rotation invariant descriptor for wrist detection in whole body CT images

2014 ◽  
Author(s):  
Mingchen Gao ◽  
Yiqiang Zhan ◽  
Gerardo Hermosillo ◽  
Yoshihisa Shinagawa ◽  
Dimitris Metaxas ◽  
...  
Keyword(s):  
Ct Images ◽  
Whole Body ◽  
Rotation Invariant ◽  
Whole Body Ct ◽  
Body Ct

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

2021 ◽  
Author(s):  
Noémie Moreau ◽  
Caroline Rousseau ◽  
Constance Fourcade ◽  
Gianmarco Santini ◽  
Ludovic Ferrer ◽  
...  
Keyword(s):  
Deep Learning ◽  
Ct Images ◽  
Whole Body ◽  
Bone Segmentation ◽  
Whole Body Ct ◽  
Body Ct

Automatic bone segmentation in whole-body CT images

2018 ◽  
Vol 14 (1) ◽  
pp. 21-29 ◽  
Author(s):  
André Klein ◽  
Jan Warszawski ◽  
Jens Hillengaß ◽  
Klaus H. Maier-Hein
Keyword(s):  
Ct Images ◽  
Whole Body ◽  
Bone Segmentation ◽  
Whole Body Ct ◽  
Body Ct

Segmentation of Skeleton and Organs in Whole-Body CT Images via Iterative Trilateration

2017 ◽  
Vol 36 (11) ◽  
pp. 2276-2286 ◽  
Author(s):  
Marie Bieth ◽  
Loic Peter ◽  
Stephan G. Nekolla ◽  
Matthias Eiber ◽  
Georg Langs ◽  
...  
Keyword(s):  
Ct Images ◽  
Whole Body ◽  
Whole Body Ct ◽  
Body Ct

scholarly journals Semantic Segmentation of Eight Regions of Upper and Lower Limb Bones Using 3D U-Net in Whole-body CT Images

2020 ◽  
Vol 76 (11) ◽  
pp. 1125-1132
Author(s):  
Yuichi Wakamatsu ◽  
Naoki Kamiya ◽  
Xiangrong Zhou ◽  
Takeshi Hara ◽  
Hiroshi Fujita
Keyword(s):  
Lower Limb ◽  
Semantic Segmentation ◽  
Ct Images ◽  
Whole Body ◽  
Limb Bones ◽  
Whole Body Ct ◽  
Body Ct

scholarly journals Deep neural network for automatic volumetric segmentation of whole-body CT images for body composition assessment

2020 ◽  
Author(s):  
Yoon Seong Lee ◽  
Namki Hong ◽  
Joseph Nathanael Witanto ◽  
Ye Ra Choi ◽  
Junghoan Park ◽  
...  
Keyword(s):  
Neural Network ◽  
Body Composition ◽  
Ct Scan ◽  
Deep Neural Network ◽  
Ct Images ◽  
Whole Body ◽  
Whole Body Ct ◽  
Pet Ct ◽  
Pet Ct Scan ◽  
Body Ct

Abstract Body composition analysis on CT images is a valuable tool for sarcopenia assessment. We aimed to develop and validate a deep neural network applicable to whole-body CT images of PET-CT scan for the automatic volumetric segmentation of body composition.Methods For model development, CT images of 100 patients who underwent a whole-body or torso 18F-fluorodeoxyglucose PET–CT scan were retrospectively included. Two radiologists semi-automatically labeled the following seven body components in every CT image slice, providing 39,268 images for training the 3D U-Net: skin, bone, muscle, abdominal visceral fat, subcutaneous fat, internal organs with vessels, and central nervous system. The segmentation accuracy was assessed using reference masks from one internal and three external datasets: two domestic centers (n=20, each) and a French public dataset (n=24). The 3D U-Net-driven values were clinically validated using bioelectrical impedance analysis (BIA) and by assessing the model’s diagnostic performance for sarcopenia in a community-based elderly cohort (n=522).Results The 3D U-Net achieved accurate body composition segmentation with an average dice similarity coefficient of 96.5% to 98.9% for all masks and 92.3% to 99.3% for muscle, abdominal visceral fat, and subcutaneous fat in the validation datasets. The 3D U-Net-derived torso volume of skeletal muscle and fat tissue and the average area of those tissues in the waist were correlated with BIA-derived appendicular lean mass (correlation coefficients: 0.71 and 0.72, each) and fat mass (correlation coefficients: 0.95 and 0.93, each). The 3D U-Net-derived average areas of skeletal muscle and fat tissue in the waist were independently associated with sarcopenia (P<.001, each) with adjustment for age and sex, providing an area under the curve of 0.858 (95% CI, 0.815 to 0.901).Conclusions This deep neural network model enabled the automatic volumetric segmentation of body composition on whole-body CT images, potentially expanding adjunctive sarcopenia assessment on PET-CT scan and volumetric assessment of metabolism in whole-body muscle and fat tissues.

Sign in / Sign up

Export Citation Format

Share Document