Automated Method for Tracking Human Muscle Architecture on Ultrasound Scans during Dynamic Tasks

MyoVision-US: an Artificial Intelligence-Powered Software for Automated Analysis of Skeletal Muscle Ultrasonography

Introduction/Aims

Muscle ultrasound has high utility in clinical practice and research; however, the main challenges are the training and time required for manual analysis to achieve objective quantification of morphometry. This study aimed to develop and validate a software tool powered by artificial intelligence (AI) by measuring its consistency and predictability of expert manual analysis quantifying lower limb muscle ultrasound images across healthy, acute, and chronic illness subjects.

Methods

Quadriceps complex (QC [rectus femoris and vastus intermedius]) and tibialis anterior (TA) muscle ultrasound images of healthy, intensive care unit, and/or lung cancer subjects were captured with portable devices. Automated analyses of muscle morphometry were performed using a custom-built deep-learning model (MyoVision-US), while manual analyses were performed by experts. Consistency between manual and automated analyses was determined using intraclass correlation coefficients (ICC), while predictability of MyoVision -US was calculated using adjusted linear regression (adj.R 2 ).

Results

Manual analysis took approximately 24 hours to analyze all 180 images, while MyoVision - US took 247 seconds, saving roughly 99.8%. Consistency between the manual and automated analyses by ICC was good to excellent for all QC (ICC:0.85-0.99) and TA (ICC:0.93-0.99) measurements, even for critically ill (ICC:0.91-0.98) and lung cancer (ICC:0.85-0.99) images. The predictability of MyoVision-US was moderate to strong for QC (adj.R 2 :0.56-0.94) and TA parameters (adj.R 2 :0.81-0.97).

Discussion

The application of AI automating lower limb muscle ultrasound analyses showed excellent consistency and strong predictability compared with human analysis. Future work needs to explore AI-powered models for the evaluation of other skeletal muscle groups.

Muscle mass loss measured with portable ultrasound in hospitalized older adults: The ECOSARC study

OBJECTIVES

The main objective was to analyze the evolution of muscle of the Quadriceps Rectus Femoris (QRF) between admission and discharge, in older adults hospitalized with an acute medical disease in Acute Geriatric Units (AGUs).

DESIGN

Prospective multicentric observational cohort study.

SETTING

Seven AGUs from University Hospitals in Spain.

PARTICIPANTS

Hospitalized adults ≥ 70 years old, able to ambulate and without severe dementia.

MEASUREMENTS

Ultrasound measurements of QRF were acquired at 2/3 distal between anterior-superior iliac spine and patella in both legs by trained Geriatricians. Ultrasound Chison model ECO2 was used. QRF area, thickness, edema, echogenicity, and fasciculations were measured.

RESULTS

From the complete sample (n = 143), in 45 (31.5%) participants, ultrasound images were classified as non-valid by an expert radiologist. Mean age was 87.8 (SD 5.4). Mean hospital stay 7.6 days (SD 4.3). From those with valid images, 36 (49.3%), 2 (2.7%), and 35 (47.9%) presented a decrease, equal values, or an increase in QRF area from baseline to discharge, respectively, and 37 (50.0%), 2 (2.7%), and 35 (47.3%) presented a decrease, equal values, or an increase in QRF thickness, respectively. 26 (35.6%) presented a decrease in more than 0.2 cm2 of QRF area, and 23 (31.1%) a decrease in more than 0.1 cm of QRF thickness. Only 4 (5.4%) patients presented new edema, while 13 (17.6%) worsened echogenicity.

CONCLUSION

One third of older adults develop significant muscle loss during a hospitalization for acute medical diseases.

TRIAL REGISTRATION NUMBER

NCT05113758.