Local MRI-based measures of thigh adipose tissue derived from fully automated deep convolutional neural network-based segmentation show a comparable responsiveness to bidirectional change in body weight as from quality controlled manual segmentation

•Clinical study can be reproduced by fully automated deep learning segmentation.•Segmentation time is 10% weight loss, and 51 with> 10% weight gain over 2-years. Longitudinal change in IMF and SCF were determined from baseline and year-2 axial thigh MRIs using U-Net segmentation. The standardised...

Full description

Saved in:
Bibliographic Details
Published in:Annals of anatomy 2022-02, Vol.240, p.151866-151866, Article 151866
Main Authors: Kemnitz, Jana, Steidle-Kloc, Eva, Wirth, Wolfgang, Fuerst, David, Wisser, Anna, Eder, Sebastian K., Eckstein, Felix
Format: Article
Language:English
Subjects:
Adipose tissue
Adipose Tissue - diagnostic imaging
Artificial intelligence
Automated segmentation
Clinical study
Humans
Image Processing, Computer-Assisted
Knee osteoarthritis
Magnetic Resonance Imaging
Neural Networks, Computer
Osteoarthritis, Knee - diagnostic imaging
Thigh - diagnostic imaging
Weight Gain
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Clinical study can be reproduced by fully automated deep learning segmentation.•Segmentation time is 10% weight loss, and 51 with> 10% weight gain over 2-years. Longitudinal change in IMF and SCF were determined from baseline and year-2 axial thigh MRIs using U-Net segmentation. The standardised response mean (SRM) was used as measure of sensitivity to change. The U-Net took substantially less time (single-slice MRI:
ISSN:0940-9602
1618-0402
DOI:10.1016/j.aanat.2021.151866