A Deep Learning Model to Automate Skeletal Muscle Area Measurement on Computed Tomography Images

Frontiers in Oncology

Nicholas Hardcastle¹  Nicole Kiss²  Cassandra Litchfield³  Jamie Lopes⁴  Benjamin J. Blyth⁴  Linda Denehy⁶  Price Jackson⁷  Michael MacManus⁸  Nicholas Bucknell⁸  Shankar Siva⁸  David Ball⁸  Sarah Everitt⁹  Julian Beraldo⁹  Kaushalya C. Amarasinghe^1,10  Jason Li^1,10 

[1] 0Centre for Medical Radiation Physics, University of Wollongong, Wollongong, NSW, Australia;Allied Health Department, Peter MacCallum Cancer Centre, Melbourne, VIC, Australia;Bioinformatics Core Facility, Cancer Research Division, Peter MacCallum Cancer Centre, Melbourne, VIC, Australia;Cancer Research Division, Peter MacCallum Cancer Centre, Melbourne, VIC, Australia;Institute for Physical Activity and Nutrition (IPAN), Deakin University, Geelong, VIC, Australia;Melbourne School of Health Sciences, The University of Melbourne, Melbourne, VIC, Australia;Physical Sciences, Peter MacCallum Cancer Centre, Melbourne, VIC, Australia;Radiation Oncology, Peter MacCallum Cancer Centre, Melbourne, VIC, Australia;Radiation Therapy, Peter MacCallum Cancer Centre, Melbourne, VIC, Australia;Sir Peter MacCallum Department of Oncology, The University of Melbourne, Parkville, VIC, Australia;

关键词: deep learning;    convolutional neural networks;    skeletal muscle;    image segmentation;    sarcopenia;    lung cancer;   

DOI  :  10.3389/fonc.2021.580806

来源: DOAJ

【 摘 要 】

BackgroundMuscle 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.MethodsAttenuation 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.ResultsWe 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%.ConclusionsThis 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.

【 授权许可】

Unknown