Background: Among the paraspinal muscles, the structure and function of the lumbar multifidus (LM) has become of great interest to researchers and clinicians involved in lower back pain and muscle rehabilitation. Ultrasound (US) imaging of the LM muscle is a useful clinical tool which can be used in the assessment of muscle morphology and function. US is widely used due to its portability, cost-effectiveness, and ease-of-use. In order to assess muscle function, quantitative information of the LM must be extracted from the US image by means of manual segmentation. However, manual segmentation requires a higher level of training and experience and is characterized by a level of difficulty and subjectivity associated with image interpretation. Thus, the development of automated segmentation methods is warranted and would strongly benefit clinicians and researchers. The aim of this study is to provide a database which will contribute to the development of automated segmentation algorithms of the LM. Construction and content: This database provides the US ground truth of the left and right LM muscles at the L5 level (in prone and standing positions) of 109 young athletic adults involved in Concordia University’s varsity teams. The LUMINOUS database contains the US images with their corresponding manually segmented binary masks, serving as the ground truth. The purpose of the database is to enable development and validation of deep learning algorithms used for automatic segmentation tasks related to the assessment of the LM cross-sectional area (CSA) and echo intensity (EI). The LUMINOUS database is publicly available at http://data.sonography.ai. Conclusion: The development of automated segmentation algorithms based on this database will promote the standardization of LM measurements and facilitate comparison among studies. Moreover, it can accelerate the clinical implementation of quantitative muscle assessment in clinical and research settings.

Ultrasound imaging is crucial in medical diagnostics, offering real-time visualization of internal anatomical structures. However, accurate automatic segmentation of ultrasound images remains challenging, particularly in scenarios with limited labeled data. In this paper, we propose a semi-supervised learning approach for ultrasound image segmentation, leveraging the statistics of data in unlabeled images to enhance segmentation accuracy. Our method builds upon the encoder-decoder architecture and incorporates innovative semi-supervised learning techniques based on contrastive learning. We have collected ultrasound images from 80 patients and 34 healthy volunteers, focusing on applications in sarcopenia assessment and emergency response scenarios. We demonstrate the effectiveness of our approach through extensive experiments on expert segmentations in this dataset.Our results demonstrate the superior performance of the proposed method across various training data splits (i.e., 1%, 5%, 10%, 20%, 30%, and 100%). While U-NET performed the best with 100% of the training data (i.e., 154 annotated images), the proposed method achieved comparable performance with only 10% of the data (i.e., 16 annotated images). Furthermore, statistical analysis confirmed that our method significantly outperforms existing models, including U-NET, CCT, and UniMatch, in most scenarios (i.e., training set splits). These findings highlight the robustness and efficiency of the proposed method, especially in environments where labeled data is scarce

Sarcopenia, the age-related loss of skeletal muscle mass, is a core component of frailty that is associated with functional decline and adverse health events in older adults. Unfortunately, the available tools to diagnose sarcopenia are often inaccessible or not user-friendly for clinicians. Point-of-care ultrasound (US) is a promising tool that has been used to image the quadriceps muscle and measure its thickness (QMT) as a diagnostic criterion for sarcopenia. This measurement can be challenging for clinicians, especially when performed at the bedside using handheld systems or phased-array probes not designed for this use case. In this paper, we sought to automate this measurement using deep learning methods to improve its accuracy, reliability, and speed in the hands of untrained clinicians. In the proposed framework, which aids in better training, particularly when limited data are available, convolutional and transformer-based deep learning models with generic or data-driven pre-trained weights were compared. We evaluated regression (QMT as a continuous output in cm) and classification (QMT as an ordinal output in 0.5 cm bins) approaches, and in the latter, activation maps were generated to interpret the anatomical landmarks driving the model predictions. Finally, we evaluated a segmentation approach to derive QMT. The results showed that both transformer-based models and convolutional neural networks benefit from the proposed framework in estimating QMT. Additionally, the activation maps highlighted the interface between the femur bone and the quadriceps muscle as a key anatomical landmark for accurate predictions. The proposed framework is a pivotal step to enable the application of US-based measurement of QMT in large-scale clinical studies seeking to validate its diagnostic performance for sarcopenia, alone or with ancillary criteria assessing muscle quality or strength. We believe that implementing the proposed framework will empower clinicians to conveniently diagnose sarcopenia in clinical settings and accordingly personalize the care of older patients, leading to improved patient outcomes and a more efficient allocation of healthcare resources.

Most modern models designed for ultrasound (US) image segmentation are characterized by high computational and memory requirements, limiting their practical utility in point-of-care US settings. Consequently, researchers have devised innovative approaches to compress these large models, enabling the training of smaller networks capable of achieving comparable generalization performance. Among these strategies, knowledge distillation (KD) has emerged as particularly suitable for scenarios involving small datasets or where significant efficiency improvements are desired. While previous KD-based methods have focused on extracting comprehensive information from diverse levels of teacher representation, they often overlook the identification of the most effective representation level. Additionally, many existing techniques propose intricate strategies that present implementation challenges. To address this gap, our study concentrates on selecting optimal teacher representations from various levels. Through an exhaustive analysis of KD pathways, loss functions, and the impact of augmentation, we offer valuable insights into the mechanisms underlying knowledge transfer from the teacher to the student networks. Our proposed methodology significantly enhances student performance, elevating the Dice similarity score from 73% to 80%, while the teacher model achieves 81%. Notably, our student model achieves this improvement with only 0.82 million parameters, compared to the teacher model’s 96 million parameters.