Original InvestigationA Machine Learning Algorithm to Estimate Sarcopenia on Abdominal CT
Introduction
Sarcopenia, initially defined as the loss of muscle mass by Rosenberg, has evolved as a syndrome to include other muscle function measurements such as strength and performance (1, 2). In 2016, the CDC established an ICD-10 code for sarcopenia, making it a recognized medical condition (3). This crucial step is allowing clinicians to code for sarcopenia, a risk factor associated with physical decline, decreased quality of life, and increased mortality (4). Computed tomography (CT), the gold standard for muscle mass and body composition measurement, is the imaging tool of choice for opportunistic sarcopenia diagnosis. With over 70 million CT scans conducted every year in the US alone (5), scans are readily available for sarcopenia screening justifying the need for a fully automated deep learning system.
Central sarcopenia is a risk factor for mortality in multiple disease processes, including cancer (6, 7). Varying criteria for determination of central sarcopenia on CT have been developed and linked to patient outcomes in clinical series. These criteria have in common that they attempt to gauge the mass of truncal muscle groups as a presumed measure of patient physiologic reserve (8). The common metric association of these series is that worsening patient outcomes are correlated with decreased cross-sectional area of tested truncal muscle groups.
The most common muscle groups tested in these series include the total axial cross section of truncal abdominal musculature also known as skeletal muscle area (SMA) normalized for patient height (skeletal muscle index – SMI or MI), the total psoas muscle cross-section (total psoas area – TPA) normalized for patient height (total psoas index – TPI), and the paraspinous muscle group, as measured on axial CT images. The SMI has been used as an imaging biomarker for mortality in lung cancer (L1 and L3), cirrhosis (L3), and trauma patients (L3); blood transfusion and hospitalization in proximal femoral fracture patients (L4); and therapy monitoring in pancreatic cancer patients (L3) (9, 10, 11, 12, 13, 14, 15). The TPA muscle group has been previously proposed for risk assessment in elderly trauma (L3 level), liver transplant (L4), and in pancreatic (L3), esophageal (L3), and endometrial cancer (L3) groups (16, 17, 18, 19, 20). The paraspinous muscle group has been discussed as a central sarcopenia determinant metric for survival and surgical outcomes in patients with colorectal cancer (L4), liver transplant (T12), and general and vascular surgery patients (T12) (15,21,22).
The standard for segmentation used in the determination of sarcopenia on CT is manual tracing of muscle group margins on axial sections, replicated over many patients. Preliminary work has been performed for automated segmentation of the total abdominal muscle cross section on a manually extracted CT image at the L3 level (23). The previously discussed studies conducted on patients with varying medical conditions, showed that different muscle groups assessed at distinct lumbar spine levels are linked to different outcomes. As such, a system which would automatically detect vertebral levels and segment multiple combinations of muscle groups at those levels would allow the radiologist to provide directed information to multiple specialties according to their own metric standards, for use in surgical planning and pretreatment risk assessment.
The purpose of this paper is to assess whether a fully-automated deep learning system can be created to opportunistically detect and analyze truncal musculature at set vertebral levels and for varied muscle groupings, for potential use in the detection of central sarcopenia using Computed Tomography (CT) scans.
Section snippets
Study Subjects
Approval of our Institutional Review Board was obtained, and our study was Health Insurance Portability and Accountability Act compliant. This retrospective study utilized previously performed imaging studies for system testing and analysis, and informed consent was waived.
Searches of the National Institutes of Health Clinical Center picture and archiving systems (PACS) database for CT examinations of the chest, abdomen, and pelvis, and abdomen and pelvis, with intravenous contrast
Patient Cohort
The mean patient age was 66.7 ± 5.8 years, with an age range of 59–81 years. There were 53 females and 49 males in the set. The mean age of the female patient cohort was 66.7 ± 5.9 years, with an age range of 59–78 years. The mean age of the male patient cohort was 66.8 ± 5.7 years, with an age range of 59–81 years. The patients were partitioned into subsets as 51 training and 51 testing cases.
Muscle Segmentation Precision
For the posterior paraspinous muscles, mean DSCs were consistently high across all lumbar spine levels
Discussion
This system autonomously determines the axial cross-sectional area of multiple truncal muscle groups on CT studies at standardized craniocaudal levels using lumbar vertebrae as measurement landmarks. The current build of this system is for use in fully-automated opportunistic detection and monitoring of sarcopenia.
Quantitative data generated by our system has potential to decrease interobserver variability in sarcopenia detection. Detailed information regarding overall severity of sarcopenia in
Conclusion
We have created and validated an automated computer system to detect and quantify the truncal musculature on CT studies, and detect central sarcopenia. This system is presented as a proof of concept assembly for surgical planning and pretreatment risk assessment.
Funding
This research was supported in part by the Intramural Research Programs of the National Institutes of Health Clinical Center (grant 1Z01 CL040004) (RMS, JY, DC).
References (31)
Summary comments: epidemiological and methodological problems in determining nutritional status of older persons
Am J Clin Nutr
(1989)Sarcopenia: origins and clinical relevance
J Nutr
(1997)- et al.
Prognostic value of sarcopenia in adults with solid tumours: a meta-analysis and systematic review
Eur J Cancer
(2016) - et al.
Prognostic significance of CT-determined sarcopenia in patients with small-cell lung cancer
J Thoracic Oncol
(2015) - et al.
Sarcopenia and mortality after liver transplantation
J Am Coll Surg
(2010) - et al.
Impact of sarcopenia on outcomes following resection of pancreatic adenocarcinoma
J Gastrointest Surg
(2012) - et al.
Paraspinous muscle as a predictor of surgical outcome
J Surg Res
(2014) - et al.
Statistical validation of image segmentation quality based on a spatial overlap index
Acad Radiol
(2004) - et al.
Definition and classification of cancer cachexia: an international consensus
Lancet Oncol
(2011) - et al.
Prevalence and clinical implications of sarcopenic obesity in patients with solid tumours of the respiratory and gastrointestinal tracts: a population-based study
Lancet Oncol
(2008)
Welcome to the ICD-10 code for sarcopenia
J Cachexia Sarcopenia Muscle
Clinical definition of sarcopenia
Clin Cases Miner Bone Metab
Slowing the increase in the population dose resulting from CT scans
Radiat Res
The prevalence and prognostic value of low muscle mass in cancer patients: a review of the literature
The Oncologist
Role of frailty and sarcopenia in predicting outcomes among patients undergoing gastrointestinal surgery
World J Gastrointest Surg
Cited by (0)
Disclosures: Author Summers receives patent royalties from iCAD, Philips, ScanMed, PingAn and research support from PingAn and NVIDIA. Author Yao receives patent royalties from iCAD, PingAn, Imbio, Zebra Medical, and is currently employed in private industry, but the work described in the manuscript was all performed as part of his employment with the NIH, and is unrelated to his subsequent private employment.