Walter Grassi

Background: Deep learning applied to ultrasound (US) can provide a feedback to the sonographer about the correct identification of scanned tissues and allows for faster and standardized measurements. The most frequently adopted parameter for US diagnosis of carpal tunnel syndrome is the increasing of the cross-sectional area (CSA) of the median nerve. Our aim was to develop a deep learning algorithm, relying on convolutional neural networks (CNNs), for the localization and segmentation of the median nerve and the automatic measurement of its CSA on US images acquired at the proximal inlet of the carpal tunnel.Methods: Consecutive patients with rheumatic and musculoskeletal disorders were recruited. Transverse US images were acquired at the carpal tunnel inlet, and the CSA was manually measured. Anatomical variants were registered. The dataset consisted of 246 images (157 for training, 40 for validation, and 49 for testing) from 103 patients each associated with manual annotations of the nerve boundary. A Mask R-CNN, state-of-the-art CNN for image semantic segmentation, was trained on this dataset to accurately localize and segment the median nerve section. To evaluate the performances on the testing set, precision (Prec), recall (Rec), mean average precision (mAP), and Dice similarity coefficient (DSC) were computed. A sub-analysis excluding anatomical variants was performed. The CSA was automatically measured by the algorithm.Results: The algorithm correctly identified the median nerve in 41/49 images (83.7%) and in 41/43 images (95.3%) excluding anatomical variants. The following metrics were obtained (with and without anatomical variants, respectively): Prec 0.86 ± 0.33 and 0.96 ± 0.18, Rec 0.88 ± 0.33 and 0.98 ± 0.15, mAP 0.88 ± 0.33 and 0.98 ± 0.15, and DSC 0.86 ± 0.19 and 0.88 ± 0.19. The agreement between the algorithm and the sonographer CSA measurements was excellent [ICC 0.97 (0.94–0.98)].Conclusions: The developed algorithm has shown excellent performances, especially if excluding anatomical variants. Future research should aim at expanding the US image dataset including a wider spectrum of normal anatomy and pathology. This deep learning approach has shown very high potentiality for a fully automatic support for US assessment of carpal tunnel syndrome.

Purpose of Review: To provide an overview of the ultrasound (US) studies focusing on enthesitis in psoriatic arthritis (PsA).Recent Findings: Last-generation US equipment has demonstrated the ability to detect subtle morphostructural and vascular abnormalities at entheseal level. US is able to identify pathologic changes in both “classical” (i.e., the site of attachment of tendons, ligaments, and joint capsules into the bone) and “functional” entheses (i.e., anatomical regions where tendons or ligaments wrap around bony pulleys).Summary: US has the potential to be the first-line method in the assessment of enthesitis. In the present review we critically discussed the current definitions of US enthesitis, the scoring systems, and the main fields of application (i.e., the detection of enthesitis in PsA and psoriasis, the identification of different disease subsets, and the assessment of response to treatment).

Objective: To investigate whether baseline monosodium urate (MSU) burden estimated by ultrasound (US) predicts the achievement of the 2016 remission criteria for gout after 12 months. Methods: In this 12-month prospective, observational and single-center study, patients with gout fulfilling all the domains of the 2016 preliminary remission criteria for gout at baseline and on urate-lowering therapy (ULT) for at least the preceding 6 months were consecutively enrolled. The US findings indicative of MSU deposits [aggregates, double contour (DC) sign, and/or tophi] were identified according to the Outcome Measure in Rheumatology US Working Group definitions. The US MSU burden was estimated by evaluating elbows, wrists, 2nd metacarpophalangeal joints, knees, ankles, and 1st metatarsophalangeal joints. Results: Remission criteria were fulfilled in 21 (42.0%) out of 50 patients at 12 months. The baseline US MSU burden was significantly lower in patients who achieved remission than in those who did not fulfill the remission criteria at 12 months (1.9±1.8 vs 5.1±3.1, p<0.01). US scores and ongoing flare prophylaxis were the only significant predictors of remission with an odds ratio of 10.83 [(95%CI=1.14–102.59), p=0.04] for the absence of MSU deposits, 5.53 [(95%CI=1.34–22.76), p<0.01] for the absence of aggregates, 7.33 [(95%CI=1.71–31.44), p<0.01] for the absence of DC sign, 3.88 [(95%CI=1.08–13.92), p=0.04] for the absence of tophi, and 0.23 [(95%CI=0.07–0.75), p=0.02] for ongoing flare prophylaxis. Conclusion: In gout, baseline US estimation of MSU burden is an independent predictor of the achievement of the remission criteria at 12 months.

Ultrasound (US) is a promising tool for assessing sarcopenia. We aimed to test in the rheumatology setting two US scanning protocols to measure muscle thickness (MT) at the anterior thigh level and to assess their feasibility and reliability. In the first phase of the study, three rheumatologists performed a US examination on 19 consecutive patients adopting two scanning protocols, namely the anterior superior iliac spine (ASIS) and the greater trochanter techniques. After consensus was obtained on the easiest scanning protocol to perform, two rheumatologists adopted only the ASIS technique in 40 consecutive patients. MT measurements were recorded as well as the time needed to complete each scanning protocol bilaterally. The median time needed to complete the US examination was under 5 minutes for each of the two techniques, with no significant difference between them (p = 0.64). In the first phase, we found an excellent inter-observer reliability of the proposed scanning protocols, with a higher but nonstatistically significant intraclass correlation coefficient (ICC) for the ASIS technique compared with the greater trochanter technique (ICC 0.97 vs. ICC 0.92, p = 0.05). The ASIS technique had a significantly higher intra-observer reliability (ICC 0.97 vs. ICC 0.92, p < 0.01). In the second phase, the ASIS technique confirmed on a larger sample its excellent inter-observer reliability, with an ICC of 0.96. The present study presents a novel tool for assessing sarcopenia and provides evidence in favor of feasibility and reliability of US measurement of MT at the anterior thigh level in rheumatology setting. Key Points • This study demonstrates that ultrasound (US) measurement of muscle thickness at the anterior thigh level is highly reliable, especially for the “anterior superior iliac spine (ASIS)” technique. • The short time needed to complete the US assessment highlights the feasibility of the proposed scanning protocols. • The simplicity and conciseness of the proposed techniques will allow other researchers and clinicians to use it for a fast assessment of sarcopenia.

Objectives: To comparatively assess the sonographic spectrum of carpal tunnel syndrome (CTS) in patients with rheumatoid arthritis (RA) and in patients with idiopathic CTS. Methods: Fifty-seven RA patients and 25 idiopathic CTS patients were consecutively enrolled. The diagnosis of CTS in RA patients was made according to clinical history and examination. The following sonographic findings were assessed at carpal tunnel level: median nerve cross-sectional area (CSA) at the carpal tunnel proximal inlet, finger flexor tendons tenosynovitis, radio-carpal synovitis and intraneural power Doppler (PD) signal. Results: CTS was diagnosed in 15/57 RA patients (26.3%). Twenty-three RA wrists with CTS, 84 RA wrists without CTS and 34 idiopathic CTS wrists were evaluated. The average CSA of the median nerve was higher in idiopathic CTS than in RA wrists with CTS (17.7 mm² vs 10.6 mm², p < 0.01). A higher rate of inflammation of synovial structures (flexor tendons sheath and/or radio-carpal joint) was found in RA wrists with CTS compared with those without CTS (p = 0.04) and idiopathic CTS (p = 0.02). Intraneural PD signal was more common in CTS (in both RA and idiopathic CTS) wrists compared with wrists without CTS (p < 0.01). Conclusion: The sonographic spectrum of CTS in RA patients is characterized by an inflammatory pattern, defined by the presence of finger flexor tendons tenosynovitis and/or radio-carpal joint synovitis. Conversely, a marked median nerve swelling is the dominant feature in idiopathic CTS. Intraneural PD signal is a frequent finding in both conditions. Key Points• Carpal tunnel syndrome (CTS) associated with rheumatoid arthritis (RA) and idiopathic CTS have distinct ultrasound patterns.• The most characteristic sonographic features of CTS in RA patients are those indicative of synovial tissue inflammation at carpal tunnel level. Conversely, marked median nerve swelling is the dominant finding in idiopathic CTS.• Intraneural power Doppler signal is a frequent finding in both conditions.• In patients with CTS, differently from electrophysiology, US can provide clues prompting a rheumatology referral in case of prominent inflammatory findings at carpal tunnel level.

To assess the impact of certolizumab pegol (CZP) treatment on clinical, patient-reported, and musculoskeletal ultrasound outcomes and to determine the treatment response time point most predictive of long-term outcomes in Italian patients with rheumatoid arthritis (RA).

Ultrasonography (US) is a safe and cheap imaging technique which in experienced hands allows for a multiplanar and multisite high-resolution assessment of both morphological and structural features of bone, cartilage, and intra- or periarticular soft tissues. This chapter describes the main applications of US in patients with osteoarthritis (OA) and crystal-related arthropathies. Imaging plays a key role for diagnosis, prognosis, and follow-up in patients with OA. Although conventional radiography is still the gold standard imaging technique in daily clinical practice, US has been revealed to be capable of detecting a wide spectrum of otherwise undetectable details, including cartilage damage, joint effusion, synovial hypertrophy, osteophyte formation, and meniscal protrusion. Crystal visualization by US has the potential to change the diagnostic approach in patients with suspicion of crystal-related arthropathies. The double-contour sign, due to urate crystal deposits on the chondrosynovial interface of the hyaline cartilage, is a highly specific finding for gout as well as the hyperechoic spots within the hyaline cartilage for calcium pyrophosphate dihydrate crystal deposition disease. The potential applications of US in the management of patients with OA and crystal-related arthropathies are not only limited to diagnosis and monitoring. Finally, US guidance allows the real-time visualization of the needle moving through different tissues and reaching the target to aspirate and/or inject. The correct placement of the tip of the needle plays a key role in improving efficacy and reducing side effects of the injection.

In the latest recommendations for the diagnosis and management of gout and calcium pyrophosphate dihydrate (CPPD) crystal deposition disease, the diagnostic potential of ultrasound has been recognized. This review highlights the recent advances of research on ultrasound in gout and CPPD crystal deposition disease.Ultrasound allows highly sensitive, noninvasive and quick detection of microcrystal aggregates in multiple anatomic areas. Ultrasound can be used as a safe and reliable guide to aspirate even minimal fluid collections suitable for microscopic analysis, and as a tool for monitoring monosodium urate crystal dissolution induced by urate-lowering therapy. The first metatarsophalangeal joint and the knee should be regarded as the anatomic regions with the highest probability of being respectively positive for monosodium urate and CPPD crystal aggregates.The detection of highly evocative signs in patients with equivocal clinical findings may have a deep impact on the clinical decision-making process, narrowing the differential diagnostic spectrum and avoiding time-consuming and expensive diagnostic procedures. Ultrasound differential diagnosis between gout and CPPD crystal deposition disease is based on the characteristics of crystal aggregates and their preferential localization in different anatomical areas.

To determine the adherence of practicing rheumatologists, before and after an educational project, to Assessment of SpondyloArthritis international Society (ASAS) classification criteria and to ASAS recommendations for the use of anti-tumor necrosis factor (TNF)-alpha agents in patients with axial spondyloarthritis (SpA). The project involved 53 rheumatologists attending 2 educational meetings on an update of SpA. Each meeting included interactive sessions on 1) clinical cases, 2) clinimetric evaluation, including ASAS core set for daily practice and 3) imaging. Diagnostic and therapeutic approach of each participant was tested using short clinical cases, obtained from real-life rheumatology settings, at the beginning and at the end of this educational project. Each case for diagnostic (n=10) or therapeutic purpose (n=10) had 10 possible choices. Each participant gave a score from 0 (total disagreement) to 10 (total agreement) for each choice. At baseline, the rheumatologists had an excellent agreement with ASAS classification criteria for axial SpA and anti-TNF-alpha treatment according to ASAS recommendations with a further significant improvement after the educational programme. In axial SpA cases with acute anterior uveitis (AU) or Crohn's disease, anti-TNF-alpha treatment was indicated mainly as monoclonal anti-TNF antibody. In presence of elevated levels of CRP, anti-TNF option has been considered useful. Practicing rheumatologists had a satisfying adherence to ASAS classification criteria and to ASAS recommendations for the use of anti-TNF-alpha agents for patients with axial SpA. Extra-articular manifestations and other variables might play a role in the decision-process of the management of axial SpA.