Validating a Semi-Automated Technique for Segmenting Femoral Articular Cartilage on Ultrasound Images

The Influence of Knee Position on Ultrasound Imaging of Femoral Cartilage in Individuals with Anterior Cruciate Ligament Reconstruction

BACKGROUND

Articular cartilage is important for knee function and can be imaged using ultrasound. The purpose was to compare femoral cartilage thickness and echo intensity (EI) measured at 90° and 140° of knee flexion and between limbs in a cohort with unilateral anterior cruciate ligament reconstruction (ACLR). We also examined associations between gait biomechanics and cartilage outcomes.

METHODS

Twenty-seven individuals with primary unilateral ACLR participated (12 men, 15 women; age = 22.3 ± 3.8 years; time since ACLR = 71.2 ± 47.2 months). Ultrasound was used to obtain femoral cartilage measurements. Gait outcomes included peak KFA (knee flexion angle) and peak external knee flexion moment (KFM). Cartilage outcomes were compared using a 2 (position) × 2 (limb) repeated measures ANOVA (analysis of variance). Gait and cartilage associations were assessed using linear regression.

FINDINGS

There were no position × limb interactions for any cartilage outcome (all P > 0.05). Medial (P = 0.038) and central cartilage (P < 0.001) were thicker, whereas central (P = 0.029) and lateral cartilage EI (P = 0.003) were lower when measured at 90° than those at 140° of knee flexion. Medial cartilage was thicker in the ACLR than that in the contralateral limb (P = 0.016). A larger KFM was associated with thicker medial cartilage (ΔR2 = 0.146, P = 0.021) and central cartilage (ΔR2 = 0.159, P = 0.039) measured at 140° of knee flexion in the ACLR limb but not at 90°.

INTERPRETATION

Findings suggest that imaging position influences cartilage thickness and EI measurements in individuals with ACLR and should be considered in study designs and clinical evaluation. A greater KFM was associated with thicker cartilage within specific portions of the distal femur.

Femoral cartilage ultrasound echo-intensity is a valid measure of cartilage composition

This study aimed to create a conversion equation that accurately predicts cartilage magnetic resonance imaging (MRI) T2 relaxation times using ultrasound echo-intensity and common participant demographics. We recruited 15 participants with a primary anterior cruciate ligament reconstruction between the ages of 18 and 35 years at 1-5 years after surgery. A single investigator completed a transverse suprapatellar scan with the ACLR limb in max knee flexion to image the femoral trochlea cartilage. A single reader manually segmented the femoral cartilage cross-sectional area to assess the echo-intensity (i.e., mean gray-scale pixel value). At a separate visit, a T2 mapping sequence with the MRI beam set to an oblique angle was used to image the femoral trochlea cartilage. A single reader manually segmented the cartilage cross-sectional area on a single MRI slice to assess the T2 relaxation time. A stepwise, multiple linear regression was used to predict T2 relaxation time from cartilage echo-intensity and common demographic variables. We created a conversion equation using the regression betas and then used an ICC and Bland-Altman plot to assess agreement between the estimated and true T2 relaxation time. Cartilage ultrasound echo-intensity and age significantly predicted T2 relaxation time (F = 7.33, p = 0.008, R2 = 0.55). When using the new conversion equation to estimate T2 relaxation time from cartilage echo-intensity and age, there was strong agreement between the estimated and true T2 relaxation time (ICC2,k = 0.84). This study provides promising preliminary data that cartilage echo-intensity combined with age can be used as a clinically accessible tool for evaluating cartilage composition.

Open-sourced semi-automatic program for ultrasound assessments of femoral trochlea cartilage health

We developed an open-sourced program that accounts for the current limitations of B-mode ultrasound and extends the clinical utility of ultrasound for assessing femoral trochlear cartilage thickness. Images were collected on 18 patients with a history of knee surgery. By failing to account for ultrasound acoustics and beam refraction, cartilage thickness was underestimated by 26% and overestimated by 0-4%, respectively (p < 0.001). Comprehensive thickness measurements achieved by measuring the Euclidean distance between every point were significantly different than traditional single-location measurements or by using the area/length (p = 0.004-0.006). Sub-regions were significantly different than all whole regions of interest (p = 0.001-0.012).

The short-term effect of glucosamine-sulfate, nonanimal chondroitin-sulfate, and S-adenosylmethionine combination on ultrasonography findings, inflammation, pain, and functionality in patients with knee osteoarthritis: A pilot, double-blind, randomized, placebo-controlled clinical trial

Objectives

This study aimed to investigate the efficacy of glucosamine-sulfate (GS), nonanimal chondroitin-sulfate (naCS), and S-adenosylmethionine (SAMe) combination on ultrasound findings, inflammation, pain, and functionality in knee osteoarthritis.

Patients and methods

In the prospective, randomized, double-blind, placebo-controlled pilot study conducted between August 2019 and November 2019, 120 participants (28 males, 92 females; mean age: 66.4±7.9 years; range, 42.4 to 74.5 years) were randomized at a 1:1:1 ratio to the placebo group, the first experimental group (a combination of GS, naCS, and SAMe was administered to the experimental groups. The first experimental group received 375 mg of GS, 300 mg of naCS, and 100 mg of SAMe, whereas the second experimental group received 750 mg of GS, 600 mg of naCS, and 200 mg of SAMe). Laboratory (erythrocyte sedimentation rate, C-reactive protein, tumor necrosis factor alpha, interleukin [IL]-1β, IL-6, IL-17), clinical (Visual Analog Scale [VAS], short form health survey [SF-36], the Western Ontario and McMaster Universities Arthritis Index [WOMAC], and the Tegner Lysholm Knee Scoring Scale [TLKS]), and musculoskeletal ultrasound (MSUS) assessments were performed at baseline and after three and six months.

Results

A minor increase was observed in the second experimental group after six months using ultrasonography to evaluate articular cartilage thickness (p<0.05). The investigational product's superiority in reducing osteoarthritis ultrasonographic findings was not proven. A moderately negative association was found between cartilage thickness and VAS scores at baseline (ρ=-0.36, p<0.01), while the presence of massive osteophytes on MSUS showed a low to moderate association with all clinical outcomes. There was no difference in the delta changes between groups for the VAS, TLKS, WOMAC, and SF-36. The only serum inflammatory marker outside the reference range was IL-1β, but no significant changes were observed after six months.

Conclusion

According to the results of our investigation, treatment for knee osteoarthritis should be evaluated using more objective outcomes. The most important conclusion of our study is that IP may result in a slight increase in articular cartilage thickness, which was associated with a decrease in pain intensity at baseline. Clarification of the potential influence of this combination on radiographic progression and laboratory markers of inflammation requires further exploration.

Applications of artificial intelligence in musculoskeletal ultrasound: narrative review

Ultrasonography (US) has become a valuable imaging tool for the examination of the musculoskeletal system. It provides important diagnostic information and it can also be very useful in the assessment of disease activity and treatment response. US has gained widespread use in rheumatology practice because it provides real time and dynamic assessment, although it is dependent on the examiner's experience. The implementation of artificial intelligence (AI) techniques in the process of image recognition and interpretation has the potential to overcome certain limitations related to physician-dependent assessment, such as the variability in image acquisition. Multiple studies in the field of AI have explored how integrated machine learning algorithms could automate specific tissue recognition, diagnosis of joint and muscle pathology, and even grading of synovitis which is essential for monitoring disease activity. AI-based techniques applied in musculoskeletal US imaging focus on automated segmentation, image enhancement, detection and classification. AI-based US imaging can thus improve accuracy, time efficiency and offer a framework for standardization between different examinations. This paper will offer an overview of current research in the field of AI-based ultrasonography of the musculoskeletal system with focus on the applications of machine learning techniques in the examination of joints, muscles and peripheral nerves, which could potentially improve the performance of everyday clinical practice.