Application of Artificial Intelligence Algorithm Based on CT Imaging for Muscle Parameter Measurement

Application of Artificial Intelligence Algorithm Based on CT Imaging for Muscle Parameter Measurement in the Diagnosis of Sarcopenia

To establish an artificial intelligence model for automated diagnosis of sarcopenia based on CT imaging

Study Overview

• Status: Completed
• Conditions: Body Composition; Sarcopenia; Computed Tomography; Deep Learning

Detailed Description

With the accelerating aging process, the early identification and diagnosis of sarcopenia, along with the effective prevention of its adverse outcomes, have become a focal point in medical research. However, current methods for assessing and diagnosing sarcopenia still face significant limitations, making the development of more efficient and accurate techniques for muscle mass evaluation an urgent clinical need. Although CT is considered as the most promising method for assessing muscle mass, its practical application is hindered by factors such as reliance on physician expertise and time-consuming procedures, limiting its widespread clinical adoption. In light of these challenges, this study aims to develop an artificial intelligence model for fully automated muscle mass measurement based on abdominal CT imaging and to validate its application value in assisting the diagnosis of sarcopenia.

• Study Type: Observational
• Enrollment (Actual): 1080

Contacts and Locations

Study Locations

• China
  • Shanghai
    • Shanghai, Shanghai, China, 2000127
      • Shanghai Jiaotong University School of Medicine, Renji Hospital Ethics Committee

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

960 inpatients in the geriatric department of Renji Hospital, 20 patients from Ruijin Hospital affiliated to Shanghai Jiaotong University School of Medicine, 20 patients from The First Affiliated Hospital of Zhejiang Medical University, 50 patients from The First Affiliated Hospital of Wenzhou Medical University, and 30 patients from Huangshan People's Hospital.

Description

Inclusion criteria：

1. The population undergoing BIA and abdominal CT examinations;
2. Can cooperate to complete human body composition analysis, grip strength measurement, 6m walking time measurement, and questionnaire survey.

Exclusion criteria：

1. Age<18 years old;
2. Existence of abdominal wall edema;
3. History of spinal surgery or vertebral fractures, or vertebral tumor lesions;
4. History of neuromuscular disorders.

Study Plan

How is the study designed?

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
To automatedly and precisely quantify three-dimensional muscle volume and fat volume.	To achieve an automated and precise quantification of three-dimensional muscle volume and fat volume at the L3 vertebral region by deep learning.	2020-2023
To establish an artificial intelligence model for diagnosis of sarcopenia.	The validation of artificial intelligence models can assist in the diagnosis of sarcopenia.	2020-2023

Collaborators and Investigators

• Sponsor: RenJi Hospital

Study record dates

Study Major Dates

• Study Start (Actual): September 5, 2023
• Primary Completion (Actual): December 31, 2024
• Study Completion (Actual): December 31, 2024

Study Registration Dates

• First Submitted: February 20, 2025
• First Submitted That Met QC Criteria: February 20, 2025
• First Posted (Actual): March 25, 2025

Study Record Updates

• Last Update Posted (Actual): March 25, 2025
• Last Update Submitted That Met QC Criteria: February 20, 2025
• Last Verified: February 1, 2025

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Neurologic Manifestations; Nervous System Diseases; Neuromuscular Manifestations; Pathological Conditions, Anatomical; Muscular Atrophy; Atrophy; Sarcopenia
• Other Study ID Numbers: LY2023-150-A

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No