The role of imaging in rheumatoid arthritis

A Stepwise Approach to Analyzing Musculoskeletal Imaging Data With Artificial Intelligence

The digitization of medical records and expanding electronic health records has created an era of "Big Data" with an abundance of available information ranging from clinical notes to imaging studies. In the field of rheumatology, medical imaging is used to guide both diagnosis and treatment of a wide variety of rheumatic conditions. Although there is an abundance of data to analyze, traditional methods of image analysis are human resource intensive. Fortunately, the growth of artificial intelligence (AI) may be a solution to handle large datasets. In particular, computer vision is a field within AI that analyzes images and extracts information. Computer vision has impressive capabilities and can be applied to rheumatologic conditions, necessitating a need to understand how computer vision works. In this article, we provide an overview of AI in rheumatology and conclude with a five step process to plan and conduct research in the field of computer vision. The five steps include (1) project definition, (2) data handling, (3) model development, (4) performance evaluation, and (5) deployment into clinical care.

Harmonizing Medicine and Surgery in the Pursuit of Boolean Remission: A Rheumatological Magnum Opus

Rheumatic diseases encompass a diverse group of musculoskeletal conditions that often lead to inflammation, pain, and significant limitations in patients' lives. While traditional treatment approaches have primarily centered on medications to control symptoms, recent developments have introduced the concept of Boolean remission. Boolean remission offers a comprehensive evaluation of disease activity by considering clinical, biochemical, and patient-reported outcomes. This narrative review explores the multifaceted landscape of Boolean remission in the context of rheumatic diseases, with a focus on rheumatoid arthritis (RA), as it remains a substantial clinical challenge. The review outlines the definition, criteria, historical context, and development of Boolean remission, shedding light on its emergence as a more patient-centered and stringent treatment goal. The role of pharmacological interventions, including immunomodulators and biologics, in achieving Boolean remission is discussed, emphasizing the significance of treatment protocols that encompass regular monitoring, medication adjustment, shared decision-making, and patient education. Surgical interventions, such as joint replacements and synovectomies, complement medication-based strategies when joint damage becomes severe, with adherence to surgical protocols ensuring sustained Boolean remission. The integration of medicine and surgery through integrated care models and interdisciplinary teams is examined as a critical aspect of optimizing patient outcomes. Boolean remission's broader impact on healthcare policies and clinical trial endpoints is explored, underscoring its growing significance in rheumatic disease management. The review concludes by looking toward the future, where emerging technologies, biomarkers, and personalized medicine approaches hold promise in refining Boolean remission criteria and making it a more attainable and impactful treatment goal. Policy implications suggest the integration of Boolean remission into healthcare quality metrics, incentivizing healthcare providers to prioritize this rigorous standard of care. Boolean remission represents a pivotal shift in the holistic and patient-centered management of rheumatic diseases, offering hope for improved patient outcomes and enhanced quality of life in this challenging clinical landscape.

Synthetic Inflammation Imaging with PatchGAN Deep Learning Networks

Background: Gadolinium (Gd)-enhanced Magnetic Resonance Imaging (MRI) is crucial in several applications, including oncology, cardiac imaging, and musculoskeletal inflammatory imaging. One use case is rheumatoid arthritis (RA), a widespread autoimmune condition for which Gd MRI is crucial in imaging synovial joint inflammation, but Gd administration has well-documented safety concerns. As such, algorithms that could synthetically generate post-contrast peripheral joint MR images from non-contrast MR sequences would have immense clinical utility. Moreover, while such algorithms have been investigated for other anatomies, they are largely unexplored for musculoskeletal applications such as RA, and efforts to understand trained models and improve trust in their predictions have been limited in medical imaging. Methods: A dataset of 27 RA patients was used to train algorithms that synthetically generated post-Gd IDEAL wrist coronal T₁-weighted scans from pre-contrast scans. UNets and PatchGANs were trained, leveraging an anomaly-weighted L₁ loss and global generative adversarial network (GAN) loss for the PatchGAN. Occlusion and uncertainty maps were also generated to understand model performance. Results: UNet synthetic post-contrast images exhibited stronger normalized root mean square error (nRMSE) than PatchGAN in full volumes and the wrist, but PatchGAN outperformed UNet in synovial joints (UNet nRMSEs: volume = 6.29 ± 0.88, wrist = 4.36 ± 0.60, synovial = 26.18 ± 7.45; PatchGAN nRMSEs: volume = 6.72 ± 0.81, wrist = 6.07 ± 1.22, synovial = 23.14 ± 7.37; n = 7). Occlusion maps showed that synovial joints made substantial contributions to PatchGAN and UNet predictions, while uncertainty maps showed that PatchGAN predictions were more confident within those joints. Conclusions: Both pipelines showed promising performance in synthesizing post-contrast images, but PatchGAN performance was stronger and more confident within synovial joints, where an algorithm like this would have maximal clinical utility. Image synthesis approaches are therefore promising for RA and synthetic inflammatory imaging.

[Rheumatological side effects of checkpoint inhibitors and their treatment]

The spectrum of tumors for which checkpoint inhibitor (CI) treatment is used is constantly expanding. The European Medicines Agency has currently approved nine CIs: one anti-cytotoxic T lymphocyte-associated antigen 4 (CTLA-4) CI, one anti-lymphocyte activation gene 3 (LAG-3) CI, four anti-programmed cell death protein 1 (PD-1) CIs and three anti-programmed death ligand 1 (PD-L1) CIs. By blocking immune checkpoints the physiological downregulation of T cell activity against autologous tissue is prevented. This results in an immunologically unregulated activation of T cells directed against malignant cells. Healthy tissue also expresses antigens and thereby continuously activates autologous T cells. Thus, the blockade of immune checkpoints can lead to T cell activity against healthy tissue (immune-related adverse events, irAE). The irAEs can occur in any organ system and approximately 10% of all patients under CI treatment develop rheumatological irAEs, mostly arthralgia and myalgia. The classification criteria of rheumatological diseases do not need to be met to initiate treatment and the primary goal of treatment of irAEs is to enable continuation of CI treatment. Rheumatological irAEs should be recognized and treated quickly. In the treatment of musculoskeletal irAEs, three stages can be defined. In the first stage, nonsteroidal anti-inflammatory drugs or intra-articular as well as systemic glucocorticoids are used. In the second stage, conventional synthetic and in the third stage, biologic disease-modifying antirheumatic drugs are used. The most severe musculoskeletal irAE is myositis with cardiac and/or respiratory involvement and/or myasthenia gravis. In addition to high-dose glucocorticoids, intravenous immunoglobulins or plasma exchange are used in treatment.

Systematic Review: Targeted Molecular Imaging of Angiogenesis and Its Mediators in Rheumatoid Arthritis

Extensive angiogenesis is a characteristic feature in the synovial tissue of rheumatoid arthritis (RA) from a very early stage of the disease onward and constitutes a crucial event for the development of the proliferative synovium. This process is markedly intensified in patients with prolonged disease duration, high disease activity, disease severity, and significant inflammatory cell infiltration. Angiogenesis is therefore an interesting target for the development of new therapeutic approaches as well as disease monitoring strategies in RA. To this end, nuclear imaging modalities represent valuable non-invasive tools that can selectively target molecular markers of angiogenesis and accurately and quantitatively track molecular changes in multiple joints simultaneously. This systematic review summarizes the imaging markers used for single photon emission computed tomography (SPECT) and/or positron emission tomography (PET) approaches, targeting pathways and mediators involved in synovial neo-angiogenesis in RA.

Imaging Immune Cells Using Fc Domain Probes in Mouse Cancer Xenograft Models

Simple Summary

The immune system responds to abnormal cell growth by sending immune cells to kill them. The immune cell response is very important since it can usually stop abnormal cells from growing and spreading. Immuno-therapeutics used to treat cancer require help from the immune system to be effective. A biopsy is typically performed to determine the therapeutic efficacy of cancer treatment which is invasive and difficult. A simpler and less invasive way to monitor therapeutic efficacy is needed. Here, we show a molecule that can be used as an imaging agent to determine immune cell recruitment to tumors.

Abstract

Tracking immune responses is complex due to the mixture of cell types, variability in cell populations, and the dynamic environment. Tissue biopsies and blood analysis can identify infiltrating and circulating immune cells; however, due to the dynamic nature of the immune response, these are prone to sampling errors. Non-invasive targeted molecular imaging provides a method to monitor immune response, which has advantages of providing whole-body images, being non-invasive, and allowing longitudinal monitoring. Three non-specific Fc-containing proteins were labeled with near-infrared dye IRDye800CW and used as imaging probes to assess tumor-infiltrating immune cells in FaDu and A-431 xenograft models. We showed that Fc domains localize to tumors and are visible by fluorescent imaging. This tumor localization appears to be based on binding tumor-associated immune cells and some xenografts showed higher fluorescent signals than others. The Fc domain alone bound to different human immune cell types. The Fc domain can be a valuable research tool to study innate immune response.

Management of Rheumatoid Arthritis: An Overview

Rheumatoid arthritis (RA) is a multifactorial autoimmune disease of unknown etiology, primarily affecting the joints, then extra-articular manifestations can occur. Due to its complexity, which is based on an incompletely elucidated pathophysiological mechanism, good RA management requires a multidisciplinary approach. The clinical status of RA patients has improved in recent years due to medical advances in diagnosis and treatment, that have made it possible to reduce disease activity and prevent systemic complications. The most promising results were obtained by developing disease-modifying anti-rheumatic drugs (DMARDs), the class to which conventional synthetic, biologic, and targeted synthetic drugs belong. Furthermore, ongoing drug development has led to obtaining molecules with improved efficacy and safety profiles, but further research is needed until RA turns into a curable pathology. In the present work, we offer a comprehensive perspective on the management of RA, by centralizing the existing data provided by significant literature, emphasizing the importance of an early and accurate diagnosis associated with optimal personalized treatment in order to achieve better outcomes for RA patients. In addition, this study suggests future research perspectives in the treatment of RA that could lead to higher efficacy and safety profiles and lower financial costs.

Monitoring of rheumatoid arthritis: a patient survey on disease insight and possible added value of an innovative inflammation monitoring device

To enable patients with rheumatoid arthritis (RA) and their healthcare professionals to choose the optimal treatment, it is crucial to accurately assess the current state of inflammatory activity. The objectives of this study were to (1) investigate the perspective of RA patients on their insight into the current status of their disease, and to (2) investigate the patients’ perspective on the possible added value of a monitoring device based on optical spectral transmission—called the HandScan—that measures the location and severity of joint inflammation. A survey was distributed online among patients with RA in the Netherlands. Four-hundred and eight patients with RA completed the survey. Of these, 298 (73%) felt they have sufficient insight into their current disease status. Most respondents perceived either a large (n = 242; 59%) or small (n = 148; 36%) added value of the HandScan in their monitoring process, mostly because the device provides additional knowledge on the presence of inflammation. This perceived added value was higher for respondents experienced with the device (n = 46; p = .04). Respondents preferred monitoring with the device on every (n = 192; 47%) or most (n = 171; 42%) visits to the outpatient clinic, or even more often than on every visit (n = 17; 4%). Monitoring RA using an optical spectral transmission device is seen by patients as a possibly valuable addition to the monitoring process of inflammatory activity during visits to an outpatient clinic. Their main reason was that the device can increase insight into their current disease status. More insight may support patients in discussing treatment options with their rheumatologist.