Calulo Rivera Zoe, González-Seguel Felipe, Horikawa-Strakovsky Arimitsu, Granger Catherine, Sarwal Aarti, Dhar Sanjay, Ntoumenopoulos George, Chen Jin, Bumgardner V K Cody, Parry Selina M, Mayer Kirby P, Wen Yuan
medRxiv. 2024 Apr 30:2024.04.26.24306153. doi: 10.1101/2024.04.26.24306153.
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.
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 ).
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 :0.56-0.94) and TA parameters (adj.R :0.81-0.97).
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.
引言/目的：肌肉超声在临床实践和研究中具有很高的实用性；然而，主要挑战在于手动分析需要培训且耗时，才能实现形态学的客观量化。本研究旨在通过测量其在健康、急性和慢性病受试者中对下肢肌肉超声图像进行专家手动分析的一致性和可预测性，来开发和验证一种由人工智能（AI）驱动的软件工具。
使用便携式设备采集健康、重症监护病房和/或肺癌受试者的股四头肌复合体（QC[股直肌和股中间肌]）和胫前肌（TA）的肌肉超声图像。使用定制的深度学习模型（MyoVision-US）进行肌肉形态学的自动分析，同时由专家进行手动分析。使用组内相关系数（ICC）确定手动和自动分析之间的一致性，而使用调整线性回归（adj.R²）计算MyoVision-US的可预测性。
手动分析分析所有180张图像大约需要24小时，而MyoVision-US只需247秒，节省了约99.8%的时间。对于所有QC（ICC：0.85 - 0.99）和TA（ICC：0.93 - 0.
