Machine learning and deep learning techniques have been used in many fields, especially automatic image processing techniques, in recent years. In light of these developments, it has become inevitable to develop applications in the medical field. This study focuses on the past few years of research using machine learning and deep learning methods in the context of image processing in the field of rheumatology. This review provides researchers with the latest information on the use of deep learning and machine learning and inspires them to generate new ideas in their research by analyzing image processing systems performed by these artificial intelligence methods. In the proposed systematic review, 28 articles covering the application of deep learning and machine learning methods in the domain of rheumatology with the aim of digital image processing in the last 18 years were evaluated. Experiments emphasize that machine learning and deep learning methods provide significant segmentation accuracy and better case classification accuracy for various rheumatologic diseases like rheumatoid arthritis, osteoarthritis, and ankylosing spondylitis. Lastly submitted review presents possible different research ideas for related researchers to concentrate on for their future studies.
1 April 2021 in Meandros Medical and Dental Journal
Background: Rheumatoid arthritis (RA) is a chronic, systemic autoimmune disease characterized by progressive joint deformity and increased mortality. RA patients typically exhibit elevated plasma levels of inflammatory markers, contributing to endothelial dysfunction and increased arterial wall stiffness—a recognized marker of subclinical atherosclerosis and heightened cardiovascular risk. This study aimed to evaluate carotid arterial wall stiffness in RA patients using ultrasound (US) imaging modality with speckle tracking carotid strain (STCS) software, a non-invasive method for assessing subclinical cardiovascular disease indicators. Methods: This analytical case–control study was conducted at Aydin Adnan Menderes University Hospital Department of Radiology and Department of Rheumatology. Patients who met the inclusion criteria were enrolled in the study. Data collection tools included an 11-item case report form developed by the researcher based on relevant literature and carotid US examinations performed. Results: The study included 143 participants: 75 RA patients (60 female and 15 male) and 68 control subjects (54 female and 14 male). The mean age was 50.9 ± 11.4 years (range: 25.0–74.0) for the RA group and 53.1 ± 12.6 years (range: 20.0–77.0) for the control group. Systolic blood pressure (SBP) and C-reactive protein (CRP) levels (mean ± SD) were 7.4 ± 11.5 in the RA group and 8.6 ± 22.2 in the control group. However, due to a few outliers in the control group, the median CRP was 3.3 mg/L (range: 2.0–71.9) in the RA group versus 2.0 mg/L (range: 0.8–145.0) in the controls. This nonparametric comparison showed significantly higher typical CRP levels in the RA group (p < 0.05). All stiffness and strain parameters in axial and longitudinal planes showed statistically significant differences between the two groups (p < 0.05), except the circumferential strain parameter “displacement (DP)” (p = 0.074). Although no significant correlation was found between the disease activity score (DAS) and any strain or stiffness parameter, the carotid intima-media thickness (CIMT) exhibited a significant positive correlation with disease duration (p = 0.001). After adjusting for confounding factors (age, gender, body mass index (BMI), and smoking status) using multivariate linear regression analysis, RA remained a significant predictor for all stiffness and strain parameters, except for the circumferential strain parameter DP. Conclusion: Applying functional parameters to assess arterial wall stiffness and tension levels provides valuable insights for early detection of cardiovascular disease risk, preceding classical US findings such as increased intima-media thickness (IMT) and plaque formation. While preliminary, our findings from STCS measurements in RA patients show promise in evaluating cardiovascular disease risk in this population and potentially improving long-term outcomes through timely interventions.
Objective: A marked relationship is known between low birth weight and reduced nephron number. In this study, it was aimed to investigate the effects of low birth weight on renal function and blood pressure in healthy children and adolescents. Methods: This study was carried out on 33 children (7 to 18 years) who were born with a birth weight under 2500 g. The control group was composed of 30 children born at term with a birth weight appropriate for gestational age. Urine microalbumin, N-Acetyl-β-D Glucosaminidase, sodium levels and blood urea nitrogen, creatinine, and cystatin-C levels were investigated in patients and the control group. The sizes of kidneys in both groups were examined by ultrasonography. Blood pressure was monitored for 24 hours as ambulatory blood pressure. Results: The study group had higher levels of blood cystatin-C, urinary sodium, and N-Acetyl-βD-Glucosaminidase than the control group. Kidney volumes were smaller in the study group than in the controls. Conclusion: In our study, we observed that some glomerular and tubular functions were affected in children with low birth weight and in children born preterm. These effects were not observed in children with mature small for gestational age. Considering that nephron formation is completed at the 37th week, gestational age (prematurity) was thought to affect glomerular maturation more than intrauterine growth retardation. Our findings did not demonstrate hypertension in children born with low birth weight in childhood. We suggest that low birth weight children should be followed carefully for renal functions and blood pressure.