Automatic Tracking of Muscle Cross-Sectional Area Using Convolutional Neural Networks with Ultrasound

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.

Ultrasound Imaging in Knee Osteoarthritis: Current Role, Recent Advancements, and Future Perspectives

While conventional radiography and MRI have a well-established role in the assessment of patients with knee osteoarthritis, ultrasound is considered a complementary and additional tool. Moreover, the actual usefulness of ultrasound is still a matter of debate in knee osteoarthritis assessment. Despite that, ultrasound offers several advantages and interesting aspects for both current clinical practice and future perspectives. Ultrasound is potentially a helpful tool in the detection of anomalies such as cartilage degradation, osteophytes, and synovitis in cases of knee osteoarthritis. Furthermore, local diagnostic and minimally invasive therapeutic operations pertaining to knee osteoarthritis can be safely guided by real-time ultrasound imaging. We are constantly observing a growing knowledge and awareness among radiologists and other physicians, concerning ultrasound imaging. Ultrasound studies can be extremely useful to track the response to various therapies. For this specific aim, tele-ultrasonography may constitute an easy tool aiding precise and repeated follow-up controls. Moreover, raw radio-frequency data from US backscattering signals contain more information than B-mode imaging. This paves the way for quantitative in-depth analyses of cartilage, bone, and other articular structures. Overall, ultrasound technologies and their rapid evolution have the potential to make a difference at both the research and clinical levels. This narrative review article describes the potential of such technologies and their possible future implications.

Reliability and Validity of Muscle Size and Quality Analysis Techniques

OBJECTIVE

This study investigated reliability and validity of muscle cross-sectional area and echo intensity using an automatic image analysis program.

METHODS

Twenty-two participants completed two data collection trials consisting of ultrasound imaging of the vastus lateralis (VL) at 10 and 12 MHz. Images were analyzed manually and with Deep Anatomical Cross-Sectional Area (DeepACSA). Reliability statistics (i.e., intraclass correlation coefficient [ICC] model 2,1, standard error of measure expressed as a percentage of the mean [SEM%], minimal differences [MD] values needed to be considered real) and validity statistics (i.e., constant error [CE], total error [TE], standard error of the estimate [SEE]) were calculated.

RESULTS

Automatic analyses of ACSA and EI demonstrated good reliability (10 MHz: ICC2,1 = 0.83 - 0.90; 12 MHz: ICC2,1 = 0.87-0.88), while manual analyses demonstrated moderate to excellent reliability (10 MHz: ICC2,1 = 0.82-0.99; 12 MHz: ICC2,1 = 0.73-0.99). Automatic analyses of ACSA presented greater error at 10 (CE = -0.76 cm2, TE = 4.94 cm2, SEE = 3.65 cm2) than 12 MHz (CE = 0.17 cm2, TE = 3.44 cm2, SEE = 3.11 cm2). Analyses of EI presented greater error at 10 (CE = 3.35 a.u., TE = 2.70 a.u., SEE = 2.58 a.u.) than at 12 MHz (CE = 3.21 a.u., TE = 2.61 a.u., SEE = 2.34 a.u.).

CONCLUSION

The results suggest the DeepACSA program may be less reliable compared to manual analysis for VL ACSA but displayed similar reliability for EI. In addition, the results demonstrated the automatic program had low error for 10 and 12 MHz.

Clinical evaluation of AI-assisted muscle ultrasound for monitoring muscle wasting in ICU patients

Muscle ultrasound has been shown to be a valid and safe imaging modality to assess muscle wasting in critically ill patients in the intensive care unit (ICU). This typically involves manual delineation to measure the rectus femoris cross-sectional area (RFCSA), which is a subjective, time-consuming, and laborious task that requires significant expertise. We aimed to develop and evaluate an AI tool that performs automated recognition and measurement of RFCSA to support non-expert operators in measurement of the RFCSA using muscle ultrasound. Twenty patients were recruited between Feb 2023 and July 2023 and were randomized sequentially to operators using AI (n = 10) or non-AI (n = 10). Muscle loss during ICU stay was similar for both methods: 26 ± 15% for AI and 23 ± 11% for the non-AI, respectively (p = 0.13). In total 59 ultrasound examinations were carried out (30 without AI and 29 with AI). When assisted by our AI tool, the operators showed less variability between measurements with higher intraclass correlation coefficients (ICCs 0.999 95% CI 0.998-0.999 vs. 0.982 95% CI 0.962-0.993) and lower Bland Altman limits of agreement (± 1.9% vs. ± 6.6%) compared to not using the AI tool. The time spent on scans reduced significantly from a median of 19.6 min (IQR 16.9-21.7) to 9.4 min (IQR 7.2-11.7) compared to when using the AI tool (p < 0.001). AI-assisted muscle ultrasound removes the need for manual tracing, increases reproducibility and saves time. This system may aid monitoring muscle size in ICU patients assisting rehabilitation programmes.

SonoMyoNet: A Convolutional Neural Network for Predicting Isometric Force from Highly Sparse Ultrasound Images

Ultrasound imaging or sonomyography has been found to be a robust modality for measuring muscle activity due to its ability to image deep-seated muscles directly while providing superior spatiotemporal specificity compared to surface electromyography-based techniques. Quantifying the morphological changes during muscle activity involves computationally expensive approaches for tracking muscle anatomical structures or extracting features from brightness-mode (B-mode) images and amplitude-mode (A-mode) signals. This paper uses an offline regression convolutional neural network (CNN) called SonoMyoNet to estimate continuous isometric force from sparse ultrasound scanlines. SonoMyoNet learns features from a few equispaced scanlines selected from B-mode images and utilizes the learned features to estimate continuous isometric force accurately. The performance of SonoMyoNet was evaluated by varying the number of scanlines to simulate the placement of multiple single-element ultrasound transducers in a wearable system. Results showed that SonoMyoNet could accurately predict isometric force with just four scanlines and is immune to speckle noise and shifts in the scanline location. Thus, the proposed network reduces the computational load involved in feature tracking algorithms and estimates muscle force from the global features of sparse ultrasound images.

One-Stop Automated Diagnostic System for Carpal Tunnel Syndrome in Ultrasound Images Using Deep Learning

OBJECTIVE

Ultrasound (US) examination has unique advantages in diagnosing carpal tunnel syndrome (CTS), although identification of the median nerve (MN) and diagnosis of CTS depend heavily on the expertise of examiners. In the aim of alleviating this problem, we developed a one-stop automated CTS diagnosis system (OSA-CTSD) and evaluated its effectiveness as a computer-aided diagnostic tool.

METHODS

We combined real-time MN delineation, accurate biometric measurements and explainable CTS diagnosis into a unified framework, called OSA-CTSD. We then collected a total of 32,301 static images from US videos of 90 normal wrists and 40 CTS wrists for evaluation using a simplified scanning protocol.

RESULTS

The proposed model exhibited better segmentation and measurement performance than competing methods, with a Hausdorff distance (95th percentile) score of 7.21 px, average symmetric surface distance score of 2.64 px, Dice score of 85.78% and intersection over union score of 76.00%. In the reader study, it exhibited performance comparable to the average performance of experienced radiologists in classifying CTS and outperformed inexperienced radiologists in terms of classification metrics (e.g., accuracy score 3.59% higher and F1 score 5.85% higher).

CONCLUSION

Diagnostic performance of the OSA-CTSD was promising, with the advantages of real-time delineation, automation and clinical interpretability. The application of such a tool not only reduces reliance on the expertise of examiners but also can help to promote future standardization of the CTS diagnostic process, benefiting both patients and radiologists.

The Cross-Sectional Area Assessment of Pelvic Muscles Using the MRI Manual Segmentation among Patients with Low Back Pain and Healthy Subjects

The pain pathomechanism of chronic low back pain (LBP) is complex and the available diagnostic methods are insufficient. Patients present morphological changes in volume and cross-sectional area (CSA) of lumbosacral region. The main objective of this study was to assess if CSA measurements of pelvic muscle will indicate muscle atrophy between asymptomatic and symptomatic sides in chronic LBP patients, as well as between right and left sides in healthy volunteers. In addition, inter-rater reliability for CSA measurements was examined. The study involved 71 chronic LBP patients and 29 healthy volunteers. The CSA of gluteus maximus, medius, minimus and piriformis were measured using the MRI manual segmentation method. Muscle atrophy was confirmed in gluteus maximus, gluteus minimus and piriformis muscle for over 50% of chronic LBP patients (p < 0.05). Gluteus medius showed atrophy in patients with left side pain occurrence (p < 0.001). Muscle atrophy occurred on the symptomatic side for all inspected muscles, except gluteus maximus in rater one assessment. The reliability of CSA measurements between raters calculated using CCC and ICC presented great inter-rater reproducibility for each muscle both in patients and healthy volunteers (p < 0.95). Therefore, there is the possibility of using CSA assessment in the diagnosis of patients with symptoms of chronic LBP.

Neuromuscular Ultrasound in Intensive Care Unit-Acquired Weakness: Current State and Future Directions

Intensive care unit-acquired weakness (ICUAW) is one of the most common causes of muscle atrophy and functional disability in critically ill intensive care patients. Clinical examination, manual muscle strength testing and monitoring are frequently hampered by sedation, delirium and cognitive impairment. Many different attempts have been made to evaluate alternative compliance-independent methods, such as muscle biopsies, nerve conduction studies, electromyography and serum biomarkers. However, they are invasive, time-consuming and often require special expertise to perform, making them vastly impractical for daily intensive care medicine. Ultrasound is a broadly accepted, non-invasive, bedside-accessible diagnostic tool and well established in various clinical applications. Hereby, neuromuscular ultrasound (NMUS), in particular, has been proven to be of significant diagnostic value in many different neuromuscular diseases. In ICUAW, NMUS has been shown to detect and monitor alterations of muscles and nerves, and might help to predict patient outcome. This narrative review is focused on the recent scientific literature investigating NMUS in ICUAW and highlights the current state and future opportunities of this promising diagnostic tool.

DeepACSA: Automatic Segmentation of Cross-Sectional Area in Ultrasound Images of Lower Limb Muscles Using Deep Learning

PURPOSE

Muscle anatomical cross-sectional area (ACSA) can be assessed using ultrasound and images are usually evaluated manually. Here, we present DeepACSA, a deep learning approach to automatically segment ACSA in panoramic ultrasound images of the human rectus femoris (RF), vastus lateralis (VL), gastrocnemius medialis (GM) and lateralis (GL) muscles.

METHODS

We trained three muscle-specific convolutional neural networks (CNN) using 1772 ultrasound images from 153 participants (age = 38.2 yr, range = 13-78). Images were acquired in 10% increments from 30% to 70% of femur length for RF and VL and at 30% and 50% of muscle length for GM and GL. During training, CNN performance was evaluated using intersection-over-union scores. We compared the performance of DeepACSA to manual analysis and a semiautomated algorithm using an unseen test set.

RESULTS

Comparing DeepACSA analysis of the RF to manual analysis with erroneous predictions removed (3.3%) resulted in intraclass correlation (ICC) of 0.989 (95% confidence interval = 0.983-0.992), mean difference of 0.20 cm 2 (0.10-0.30), and SEM of 0.33 cm 2 (0.26-0.41). For the VL, ICC was 0.97 (0.96-0.968), mean difference was 0.85 cm 2 (-0.4 to 1.31), and SEM was 0.92 cm 2 (0.73-1.09) after removal of erroneous predictions (7.7%). After removal of erroneous predictions (12.3%), GM/GL muscles demonstrated an ICC of 0.98 (0.96-0.99), a mean difference of 0.43 cm 2 (0.21-0.65), and an SEM of 0.41 cm 2 (0.29-0.51). Analysis duration was 4.0 ± 0.43 s (mean ± SD) for analysis of one image in our test set using DeepACSA.

CONCLUSIONS

DeepACSA provides fast and objective segmentation of lower limb panoramic ultrasound images comparable with manual segmentation. Inaccurate model predictions occurred predominantly on low-quality images, highlighting the importance of high-quality image for accurate prediction.

Human skeletal muscle size with ultrasound imaging: a comprehensive review

Skeletal muscle size is an important factor in assessing adaptation to exercise training and detraining, athletic performance, age-associated atrophy and mobility decline, clinical conditions associated with cachexia, and overall skeletal muscle health. Magnetic resonance (MR) imaging and computed tomography (CT) are widely accepted as the gold standard methods for skeletal muscle size quantification. However, it is not always feasible to use these methods (e.g., field studies, bedside studies, large cohort studies). Ultrasound has been available for skeletal muscle examination for more than 50 years and the development, utility, and validity of ultrasound imaging are underappreciated. It is now possible to use ultrasound in situations where MR and CT imaging are not suitable. This review provides a comprehensive summary of ultrasound imaging and human skeletal muscle size assessment. Since the first study in 1968, more than 600 articles have used ultrasound to examine the cross-sectional area and/or volume of 107 different skeletal muscles in more than 27,500 subjects of various ages, health status, and fitness conditions. Data from these studies, supported by decades of technological developments, collectively show that ultrasonography is a valid tool for skeletal muscle size quantification. Considering the wide-ranging connections between human health and function and skeletal muscle mass, the utility of ultrasound imaging will allow it to be employed in research investigations and clinical practice in ways not previously appreciated or considered.

Automated Segmentation of Median Nerve in Dynamic Sonography Using Deep Learning: Evaluation of Model Performance

There is an emerging trend to employ dynamic sonography in the diagnosis of entrapment neuropathy, which exhibits aberrant spatiotemporal characteristics of the entrapped nerve when adjacent tissues move. However, the manual tracking of the entrapped nerve in consecutive images demands tons of human labors and impedes its popularity clinically. Here we evaluated the performance of automated median nerve segmentation in dynamic sonography using a variety of deep learning models pretrained with ImageNet, including DeepLabV3+, U-Net, FPN, and Mask-R-CNN. Dynamic ultrasound images of the median nerve at across wrist level were acquired from 52 subjects diagnosed as carpal tunnel syndrome when they moved their fingers. The videos of 16 subjects exhibiting diverse appearance and that of the remaining 36 subjects were used for model test and training, respectively. The centroid, circularity, perimeter, and cross section area of the median nerve in individual frame were automatically determined from the inferred nerve. The model performance was evaluated by the score of intersection over union (IoU) between the annotated and model-predicted data. We found that both DeepLabV3+ and Mask R-CNN predicted median nerve the best with averaged IOU scores close to 0.83, which indicates the feasibility of automated median nerve segmentation in dynamic sonography using deep learning.

ACSAuto-semi-automatic assessment of human vastus lateralis and rectus femoris cross-sectional area in ultrasound images

Open-access scripts to perform muscle anatomical cross-sectional area (ACSA) evaluation in ultrasound images are currently unavailable. This study presents a novel semi-automatic ImageJ script (named "ACSAuto") for quantifying the ACSA of lower limb muscles. We compared manual ACSA measurements from 180 ultrasound scans of vastus lateralis (VL) and rectus femoris (RF) muscles to measurements assessed by the ACSAuto script. We investigated inter- and intra-investigator reliability of the script. Consecutive-pairwise intra-class correlations (ICC) and standard error of measurement (SEM) with 95% compatibility interval were calculated. Bland-Altman analyses were employed to test the agreement between measurements. Comparing manual and ACSAuto measurements, ICCs and SEMs ranged from 0.96 to 0.999 and 0.12 to 0.96 cm2 (1.2-5.9%) and mean bias was smaller than 0.5 cm2 (4.3%). Inter-investigator comparison revealed ICCs, SEMs and mean bias ranging from 0.85 to 0.999, 0.07 to 1.16 cm2 (0.9-7.6%) and - 0.16 to 0.66 cm2 (- 0.6 to 3.2%). Intra-investigator comparison revealed ICCs, SEMs and mean bias between 0.883-0.998, 0.07-0.93 cm2 (1.1-7.6%) and - 0.80 to 0.15 cm2 (- 3.4 to 1.8%). Image quality needs to be high for efficient and accurate ACSAuto analyses. Taken together, the ACSAuto script represents a reliable tool to measure RF and VL ACSA, is comparable to manual analysis and can reduce time needed to evaluate ultrasound images.

Artificial intelligence in ultrasound

Ultrasound (US), a flexible green imaging modality, is expanding globally as a first-line imaging technique in various clinical fields following with the continual emergence of advanced ultrasonic technologies and the well-established US-based digital health system. Actually, in US practice, qualified physicians should manually collect and visually evaluate images for the detection, identification and monitoring of diseases. The diagnostic performance is inevitably reduced due to the intrinsic property of high operator-dependence from US. In contrast, artificial intelligence (AI) excels at automatically recognizing complex patterns and providing quantitative assessment for imaging data, showing high potential to assist physicians in acquiring more accurate and reproducible results. In this article, we will provide a general understanding of AI, machine learning (ML) and deep learning (DL) technologies; We then review the rapidly growing applications of AI-especially DL technology in the field of US-based on the following anatomical regions: thyroid, breast, abdomen and pelvis, obstetrics heart and blood vessels, musculoskeletal system and other organs by covering image quality control, anatomy localization, object detection, lesion segmentation, and computer-aided diagnosis and prognosis evaluation; Finally, we offer our perspective on the challenges and opportunities for the clinical practice of biomedical AI systems in US.

Automatic segmentation of ultrasound images of gastrocnemius medialis with different echogenicity levels using convolutional neural networks

The purpose of this study was to develop an automatic method for the segmentation of muscle cross-sectional area on transverse B-mode ultrasound images of gastrocnemius medialis using a convolutional neural network(CNN). In the provided dataset images with both normal and increased echogenicity are present. The manually annotated dataset consisted of 591 images, from 200 subjects, 400 relative to subjects with normal echogenicity and 191 to subjects with augmented echogenicity. From the DICOM files, the image has been extracted and processed using the CNN, then the output has been post-processed to obtain a finer segmentation. Final results have been compared to the manual segmentations. Precision and Recall scores as mean ± standard deviation for training, validation, and test sets are 0.96 ± 0.05, 0.90 ± 0.18, 0.89 ± 0.15 and 0.97 ±0.03, 0.89± 0.17, 0.90 ± 0.14 respectively. The CNN approach has also been compared to another automatic algorithm, showing better performances. The proposed automatic method provides an accurate estimation of muscle cross-sectional area in muscles with different echogenicity levels.