Application of Artificial Intelligence to Automate the Reconstruction of Muscle Cross-Sectional Area Obtained by Ultrasound.

PURPOSE: Manual reconstruction (MR) of the vastus lateralis (VL) muscle cross-sectional area (CSA) from sequential ultrasound (US) images is accessible, is reproducible, and has concurrent validity with magnetic resonance imaging. However, this technique requires numerous controls and procedures during image acquisition and reconstruction, making it laborious and time-consuming. The aim of this study was to determine the concurrent validity of VL CSA assessments between MR and computer vision-based automated reconstruction (AR) of CSA from sequential images of the VL obtained by US. METHODS: The images from each sequence were manually rotated to align the fascia between images and thus visualize the VL CSA. For the AR, an artificial neural network model was utilized to segment areas of interest in the image, such as skin, fascia, deep aponeurosis, and femur. This segmentation was crucial to impose necessary constraints for the main assembly phase. At this stage, an image registration application, combined with differential evolution, was employed to achieve appropriate adjustments between the images. Next, the VL CSA obtained from the MR ( n = 488) and AR ( n = 488) techniques was used to determine their concurrent validity. RESULTS: Our findings demonstrated a low coefficient of variation (CV) (1.51%) for AR compared with MR. The Bland-Altman plot showed low bias and close limits of agreement (+1.18 cm 2 , -1.19 cm 2 ), containing more than 95% of the data points. CONCLUSIONS: The AR technique is valid compared with MR when measuring VL CSA in a heterogeneous sample.

Low-Load Resistance Training Performed to Muscle Failure or Near Muscle Failure Does Not Promote Additional Gains on Muscle Strength, Hypertrophy, and Functional Performance of Older Adults.

ABSTRACT: Bergamasco, JGA, Gomes da Silva, D, Bittencourt, DF, Martins de Oliveira, R, Júnior, JCB, Caruso, FC, Godoi, D, Borghi-Silva, A, and Libardi, CA. Low-load resistance training performed to muscle failure or near muscle failure does not promote additional gains on muscle strength, hypertrophy, and functional performance of older adults. J Strength Cond Res 36(5): 1209-1215, 2022-The aim of the present study was to compare the effects of low-load resistance training (RT) protocols performed to failure (FAI), to voluntary interruption (VOL), and with a fixed low repetitions (FIX) on muscle strength, hypertrophy, and functional performance in older adults. Forty-one subjects (60-77 years) were randomized into one of the RT protocols (FAI, VOL, or FIX) and completed 12 weeks of RT at 40% of 1 repetition maximum (1RM), twice a week. The assessments included 1RM test, muscle cross-sectional area (CSA), rate of torque development (RTD), and functional performance (chair stand [CS], habitual gait speed [HGS], maximal gait speed [MGS], and timed up-and-go [TUG]). All protocols significantly increased 1RM values from Pre (FAI: 318.3 ± 116.3 kg; VOL: 342.9 ± 93.7 kg; FIX: 328.0 ± 107.2 kg) to Post (FAI: 393.0 ± 143.1 kg, 23.5%; VOL: 423.0 ± 114.5 kg, 23.3%; FIX: 397.8 ± 94.6 kg, 21.3%; p < 0.0001 for all groups). Regarding CS, all protocols showed significant improvements from Pre (FAI: 11.5 ± 2.4 seconds; VOL: 12.1 ± 2.5 seconds; FIX: 11.3 ± 1.1 seconds) to Post (FAI: 10.5 ± 1.1 seconds, -8.5%, p = 0.001; VOL: 10.3 ± 1.5 seconds, -15.1%, p = 0.001; FIX: 11.0 ± 1.1, -3.2%, p = 0.001). Habitual gait speed values increased significantly from Pre (FAI: 1.3 ± 0.2 m·s-1; VOL: 1.3 ± 0.1 m·s-1; FIX: 1.3 ± 0.1 m·s-1) to Post (FAI: 1.4 ± 0.2 m·s-1, 2.5%, p = 0.03; VOL: 1.4 ± 0.2 m·s-1, 5.2%, p = 0.036; FIX: 1.4 ± 0.1 m·s-1, 5.7%, p = 0.03). No significant differences between protocols were found (p > 0.05). In addition, there were no significant changes in CSA, RTD, MGS, and TUG for any protocols (p > 0.05). In conclusion, low-load RT performed without muscle failure promotes significant improvements in muscle strength and some parameters of functional performance in older adults.

Suspension training vs. traditional resistance training: effects on muscle mass, strength and functional performance in older adults.

PURPOSE: We compared the effects of suspension training (ST) with traditional resistance training (TRT) on muscle mass, strength and functional performance in older adults. METHODS: Forty-two untrained older adults were randomized in TRT, ST (both performed 3 sets of whole body exercises to muscle failure) or control group (CON). Muscle thickness (MT) of biceps brachii (MTBB) and vastus lateralis (MTVL), maximal dynamic strength test (1RM) for biceps curl (1RMBC) and leg extension exercises (1RMLE), and functional performance tests (chair stand [CS], timed up and go [TUG] and maximal gait speed [MGS]) were performed before and after 12 weeks of training. RESULTS: MTBB increased significantly and similarly for all training groups (TRT 23.35%; ST 21.56%). MTVL increased significantly and similarly for all training groups (TRT 13.03%; ST 14.07%). 1RMBC increased significantly and similarly for all training groups (TRT 16.06%; ST 14.33%). 1RMLE increased significantly and similarly for all training groups (TRT 14.89%; ST 18.06%). MGS increased significantly and similarly for all groups (TRT 6.26%; ST 5.99%; CON 2.87%). CS decreased significantly and similarly for all training groups (TRT - 20.80%; ST - 15.73%). TUG decreased significantly and similarly for all training groups (TRT - 8.66%; ST - 9.16%). CONCLUSION: Suspension training (ST) promotes similar muscle mass, strength and functional performance improvements compared to TRT in older adults.

Effect of individualized resistance training prescription with heart rate variability on individual muscle hypertrophy and strength responses.

The aim of the present study was to investigate if resistance training (RT), performed with individualized recovery between sessions (RT-IND), promotes greater gains in strength and muscle mass and reduces the variability on adaptations compared to RT with fixed recovery intervals (RT-FIX). Twenty young men (age 21.9 ± 3.3 years) were randomized in the RT-IND and RT-FIX groups. Five days before the beginning of the training, measurements of the root mean square of successive R-R intervals differences (RMSSD) values of each individual were performed to establish the baseline values. Before each RT session, the RMSSD values determined whether the participants from RT-IND protocol were recovered from the previous session. Participants performed the RT session only if RMSSD values had returned to the baseline, otherwise they had to wait for an additional 24 h. RT-FIX performed an RT session every 48 h. Muscle strength was measured by one-maximal repetition (1-RM) test and muscle cross-section area (CSA) of the vastus laterals by ultrasonography were assessed pre- and post-training. 1-RM values increased significantly from pre to post-training for both groups (RT-IND: 30% and RT-FIX: 42%, main time effect, P < 0001), with no significant difference between groups. Muscle CSA increased significantly from pre to post-training (RT-IND: 15.7% and RT-FIX: 15.8%, main time effect, P < 0001), with no significant difference between groups. In conclusion, RT-IND did not increase the gains in muscle strength and mass neither reduce the variability in muscle adaptations when compared to the RT-FIX.