Openly accessible

A deep learning model to automate skeletal muscle area measurement on computed tomography images

Amarasinghe, Kaushalya C., Lopes, Jamie, Beraldo, Julian, Kiss, Nicole, Bucknell, Nicholas, Everitt, Sarah, Jackson, Price, Litchfield, Cassandra, Denehy, Linda, Blyth, Benjamin J., Siva, Shankar, MacManus, Michael, Ball, David, Li, Jason and Hardcastle, Nicholas 2021, A deep learning model to automate skeletal muscle area measurement on computed tomography images, Frontiers in oncology, vol. 11, pp. 1-10, doi: 10.3389/fonc.2021.580806.

Attached Files
Name Description MIMEType Size Downloads

Title A deep learning model to automate skeletal muscle area measurement on computed tomography images
Author(s) Amarasinghe, Kaushalya C.
Lopes, Jamie
Beraldo, Julian
Kiss, NicoleORCID iD for Kiss, Nicole orcid.org/0000-0002-6476-9834
Bucknell, Nicholas
Everitt, Sarah
Jackson, Price
Litchfield, Cassandra
Denehy, Linda
Blyth, Benjamin J.
Siva, Shankar
MacManus, Michael
Ball, David
Li, Jason
Hardcastle, Nicholas
Journal name Frontiers in oncology
Volume number 11
Article ID 580806
Start page 1
End page 10
Total pages 10
Publisher Frontiers
Place of publication Lausanne, Switzerland
Publication date 2021-05
ISSN 2234-943X
2234-943X
Keyword(s) CANCER
convolutional neural networks
deep learning
image segmentation
Life Sciences & Biomedicine
lung cancer
Oncology
sarcopenia
Science & Technology
skeletal muscle
Summary Background:
Muscle wasting (Sarcopenia) is associated with poor outcomes in cancer patients. Early identification of sarcopenia can facilitate nutritional and exercise intervention. Cross-sectional skeletal muscle (SM) area at the third lumbar vertebra (L3) slice of a computed tomography (CT) image is increasingly used to assess body composition and calculate SM index (SMI), a validated surrogate marker for sarcopenia in cancer. Manual segmentation of SM requires multiple steps, which limits use in routine clinical practice. This project aims to develop an automatic method to segment L3 muscle in CT scans.
Methods:
Attenuation correction CTs from full body PET-CT scans from patients enrolled in two prospective trials were used. The training set consisted of 66 non-small cell lung cancer (NSCLC) patients who underwent curative intent radiotherapy. An additional 42 NSCLC patients prescribed curative intent chemo-radiotherapy from a second trial were used for testing. Each patient had multiple CT scans taken at different time points prior to and post- treatment (147 CTs in the training and validation set and 116 CTs in the independent testing set). Skeletal muscle at L3 vertebra was manually segmented by two observers, according to the Alberta protocol to serve as ground truth labels. This included 40 images segmented by both observers to measure inter-observer variation. An ensemble of 2.5D fully convolutional neural networks (U-Nets) was used to perform the segmentation. The final layer of U-Net produced the binary classification of the pixels into muscle and non-muscle area. The model performance was calculated using Dice score and absolute percentage error (APE) in skeletal muscle area between manual and automated contours.
Results:
We trained five 2.5D U-Nets using 5-fold cross validation and used them to predict the contours in the testing set. The model achieved a mean Dice score of 0.92 and an APE of 3.1% on the independent testing set. This was similar to inter-observer variation of 0.96 and 2.9% for mean Dice and APE respectively. We further quantified the performance of sarcopenia classification using computer generated skeletal muscle area. To meet a clinical diagnosis of sarcopenia based on Alberta protocol the model achieved a sensitivity of 84% and a specificity of 95%.
Conclusions:
This work demonstrates an automated method for accurate and reproducible segmentation of skeletal muscle area at L3. This is an efficient tool for large scale or routine computation of skeletal muscle area in cancer patients which may have applications on low quality CTs acquired as part of PET/CT studies for staging and surveillance of patients with cancer.
Language eng
DOI 10.3389/fonc.2021.580806
Indigenous content off
Field of Research 1112 Oncology and Carcinogenesis
HERDC Research category C1 Refereed article in a scholarly journal
Free to Read? Yes
Persistent URL http://hdl.handle.net/10536/DRO/DU:30151644

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 9 Abstract Views, 0 File Downloads  -  Detailed Statistics
Created: Wed, 26 May 2021, 09:00:37 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.