Hand Radiographs Research Articles

A critical comparative study of the performance of three AI-assisted programs for bone age determination.

To date, AI-supported programs for bone age (BA) determination for medical use in Europe have almost only been validated separately, according to Greulich and Pyle (G&P). Therefore, the current study aimed to compare the performance of three programs, namely BoneXpert, PANDA, and BoneView, on a single Central European population. For this retrospective study, hand radiographs of 306 children aged 1-18 years, stratified by gender and age, were included. A subgroup consisting of the age group accounting for 90% of examinations in clinical practice was formed. The G&P BA was estimated by three human experts-as ground truth-and three AI-supported programs. The mean absolute deviation, the root mean squared error (RMSE), and dropouts by the AI were calculated. The correlation between all programs and the ground truth was prominent (R2 ≥ 0.98). In the total group, BoneXpert had a lower RMSE than BoneView and PANDA (0.62 vs. 0.65 and 0.75 years) with a dropout rate of 2.3%, 20.3% and 0%, respectively. In the subgroup, there was less difference in RMSE (0.66 vs. 0.68 and 0.65 years, max. 4% dropouts). The standard deviation between the AI readers was lower than that between the human readers (0.54 vs. 0.62 years, p < 0.01). All three AI programs predict BA after G&P in the main age range with similar high reliability. Differences arise at the boundaries of childhood. Question There is a lack of comparative, independent validation for artificial intelligence-based bone age estimation in children. Findings Three commercially available programs estimate bone age after Greulich and Pyle with similarly high reliability in a central European cohort. Clinical relevance The comparative study will help the reader choose a software for bone age estimation approved for the European market depending on the targeted age group and economic considerations.

Routine radiographs of hands and feet do not have diagnostic or prognostic value in patients with clinically suspect arthralgia: a large longitudinal study

BackgroundConventional radiographs of hands and feet are used to depict structural damage in rheumatoid arthritis (RA). This is also commonly done in clinical practice in symptomatic patients at risk for...

HarDNet-based deep learning model for osteoporosis screening and bone mineral density inference from hand radiographs

PurposeOsteoporosis, affecting over 200 million individuals, often remains unrecognized and untreated, increasing the risk of fractures in older adults. Osteoporosis is typically diagnosed with bone mineral density (BMD) measured by dual-energy X-ray absorptiometry (DXA). This study aims to develop DeepDXA-Hand, a deep learning model using the efficient CNN-based deep learning architecture, for opportunistic osteoporosis screening from hand radiographs. MethodsDeepDXA-Hand utilizes a CNN-based, HarDNet, approach to predict BMD non-invasively. A total of 10,351 hand radiographs and DXA pairs were used for model training and validation. The model's interpretability was enhanced using GradCAM for hotspot analysis to determine the model's attention areas. ResultsThe predicted and ground truth BMD were significantly correlated with a correlation coefficient of 0.745. For binary classification of osteoporosis, DeepDXA-Hand demonstrated a sensitivity of 0.73, specificity of 0.83, and accuracy of 0.80, indicating its clinical potential. The model mainly focused on the carpal bones, such as the capitate, trapezoid, hamate, triquetrum, and the head of the second metacarpal bone, suggesting these areas provide radiological features for inferring BMD. ConclusionDeepDXA-Hand shows potential for the early detection of osteoporosis with high sensitivity and specificity. Further studies should explore its utility in predicting fracture risks. Mini abstractOsteoporosis affects millions and often goes undetected and untreated. DeepDXA-Hand, a HarDNet-based deep learning model, predicted bone mineral density with a correlation of 0.745 and classified osteoporosis with 0.80 accuracy. This model enhances early detection and has significant clinical potential as osteoporosis opportunistic screening tool.

Application of Machine Learning to Osteoporosis and Osteopenia Screening Using Hand Radiographs

Application of Machine Learning to Osteoporosis and Osteopenia Screening Using Hand Radiographs

Tubercular dactylitis/Spina ventosa-A rare skeletal form of extrapulmonary tuberculosis.

A 9-year-old girl presented with progressive, painful swelling over the left index finger, associated with local signs of inflammation and restriction of finger movements. After the swelling was punctured using a needle, chronic discharging sinus formed. Examination revealed firm swelling over the right parotid area, bilateral cervical and left axillary lymphadenopathy, and firm swelling over the left index finger with a chronic discharging sinus over the lateral aspect of proximal phalanx. Mantoux intradermal injection was reactive (22x24 mm induration). Blood and pus cultures were sterile. Hand radiograph revealed dactylitis (Figure 1A-C). Fine aspiration and cytology of the cervical lymph node showed degenerated inflammatory cells, epithelioid granuloma and acid-fast bacilli. She was initiated on 4-drug antitubercular therapy (ATT). At 2-months follow-up, she was asymptomatic and had the pain and swelling over the left finger have reduced with significant radiological improvement. Tubercular dactylitis or 'spina ventosa' (wind-filled sail) refers to cystic expansion of short, tubular bones. It is commonly seen in younger children (between 1 and 6 years of age) and adults (between 20 and 50 years of age). A common presentation in endemic areas is presence of a painless, fusiform swelling over a single digit, most commonly the proximal phalanx of index or middle finger as in the index case, or over the metacarpals of middle and ring fingers. Earliest radiological clues include periosteitis followed by gradual destruction of bone and cyst formation in the cavity giving a ballooned-out appearance.

Quantitative analysis of effectiveness and associated factors of exercise on symptoms in osteoarthritis: a pharmacodynamic model-based meta-analysis

ObjectiveThis study aims to evaluate the time point and magnitude of peak effectiveness of exercise and the effects of various exercise modalities for osteoarthritis (OA) symptoms and to identify factors...

Can eye-tracking help to create a new method for X-ray analysis of rheumatoid arthritis patients, including joint segmentation and scoring methods?

Reading hand and foot X-rays in rheumatoid arthritis patients is difficult and time-consuming. In research, physicians use the modified Sharp van der Heijde Sharp (mvdH) score by reading of hand and foot radiographs. The aim of this study was to create a new method of determining the mvdH via eye tracking and to study its concordance with the mvdH score. We created a new method of quantifying the mvdH score based on reading time of a reader monitored via eye tracking (Tobii Pro Lab software) after training with the aid of a metronome. Radiographs were read twice by the trained eye-tracking reader and once by an experienced reference radiologist. A total of 440 joints were selected; 416 could be interpreted for erosion, and 396 could be interpreted for joint space narrowing (JSN) when read by eye tracking (eye tracking could not measure the time spent when two pathological joints were too close together). The agreement between eye tracking mvdH Sharp score and classical mvdH Sharp score yes (at least one erosion or JSN) versus no (no erosion or no JSN) was excellent for both erosions (kappa 0.97; 95% CI: 0.96-0.99) and JSN (kappa: 0.95; 95% CI: 0.93-0.097). This agreement by class (0 to 10) remained excellent for both erosions (kappa 0.82; 95% CI: 0.79-0.0.85) and JSN (kappa: 0.68; 95% CI: 0.65-0.0.71). To conclude, eye-tracking reading correlates strongly with classical mvdH-Sharp and is useful for assessing severity, segmenting joints and establishing a rapid score for lesions.

The Validation of the Greulich and Pyle Atlas for Radiological Bone Age Assessments in a Pediatric Population from the Canary Islands.

Bone age assessments measure the growth and development of children and adolescents by evaluating their skeletal maturity, which is influenced by various factors like heredity, ethnicity, culture, and nutrition. The clinical standards for this assessment should be up to date and appropriate for the specific population being studied. This study validates the GP-Canary Atlas for accurately predicting bone age by analyzing posteroanterior left hand and wrist radiographs of healthy children (80 females and 134 males) from the Canary Islands across various developmental stages and genders. We found strong intra-rater reliability among all three raters, with Raters 1 and 2 indicating very high consistency (intra-class coefficients = 0.990 to 0.996) and Rater 3 displaying slightly lower but still strong reliability (intra-class coefficients = 0.921 to 0.976). The inter-rater agreement was excellent between Raters 1 and 2 but significantly lower between Rater 3 and the other two raters, with intra-class coefficients of 0.408 and 0.463 for Rater 1 and 0.327 and 0.509 for Rater 2. The accuracy analysis revealed a substantial underestimation of bone age compared to chronological age for preschool- (mean difference = 17.036 months; p < 0.001) and school-age males (mean difference = 13.298 months; p < 0.001). However, this was not observed in females, where the mean difference was minimal (3.949 months; p < 0.239). In contrast, the Atlas showed greater accuracy for teenagers, showing only a slight overestimation (mean difference = 3.159 months; p = 0.823). In conclusion, the GP-Canary Atlas demonstrates overall precision but requires caution as it underestimates the BA in preschool children and overestimates it in school-age girls and adolescents.

Doctor simulator: Delta-Age-Sex-AdaIn enhancing bone age assessment through AdaIn style transfer.

Bone age assessment assists physicians in evaluating the growth and development of children. However, deep learning methods for bone age estimation do not currently incorporate differential features obtained through comparisons with other bone atlases. To propose a more accurate method, Delta-Age-Sex-AdaIn (DASA-net), for bone age assessment, this paper combines age and sex distribution through adaptive instance normalization (AdaIN) and style transfer, simulating the process of visually comparing hand images with a standard bone atlas to determine bone age. The proposed Delta-Age-Sex-AdaIn (DASA-net) consists of four modules: BoneEncoder, Binary code distribution, Delta-Age-Sex-AdaIn, and AgeDecoder. It is compared with state-of-the-art methods on both a public Radiological Society of North America (RSNA) pediatric bone age prediction dataset (14,236 hand radiographs, ranging from 1 to 228 months) and a private bone age prediction dataset from Zigong Fourth People's Hospital (474 hand radiographs, ranging from 12 to 218 months, 268 male). Ablation experiments were designed to demonstrate the necessity of incorporating age distribution and sex distribution. The DASA-net model achieved a lower mean absolute deviation (MAD) of 3.52 months on the RSNA dataset, outperforming other methods such as BoneXpert, Deeplasia, BoNet, and other deep learning based methods. On the private dataset, the DASA-net model obtained a MAD of 3.82 months, which is also superior to other methods. The proposed DASA-net model aided the model's learning of the distinctive characteristics of hand bones of various ages and bothsexes by integrating age and sex distribution into style transfer.

RA-XTNet: A Novel CNN Model to Predict Rheumatoid Arthritis from Hand Radiographs and Thermal Images: A Comparison with CNN Transformer and Quantum Computing.

The aim and objective of the research are to develop an automated diagnosis system for the prediction of rheumatoid arthritis (RA) based on artificial intelligence (AI) and quantum computing for hand radiographs and thermal images. The hand radiographs and thermal images were segmented using a UNet++ model and color-based k-means clustering technique, respectively. The attributes from the segmented regions were generated using the Speeded-Up Robust Features (SURF) feature extractor and classification was performed using k-star and Hoeffding classifiers. For the ground truth and the predicted test image, the study utilizing UNet++ segmentation achieved a pixel-wise accuracy of 98.75%, an intersection over union (IoU) of 0.87, and a dice coefficient of 0.86, indicating a high level of similarity. The custom RA-X-ray thermal imaging (XTNet) surpassed all the models for the detection of RA with a classification accuracy of 90% and 93% for X-ray and thermal imaging modalities, respectively. Furthermore, the study employed quantum support vector machine (QSVM) as a quantum computing approach which yielded an accuracy of 93.75% and 87.5% for the detection of RA from hand X-ray and thermal images. In addition, vision transformer (ViT) was employed to classify RA which obtained an accuracy of 80% for hand X-rays and 90% for thermal images. Thus, depending on the performance measures, the RA-XTNet model can be used as an effective automated diagnostic method to diagnose RA accurately and rapidly in hand radiographs and thermal images.

The assessment of bone health in children with juvenile idiopathic arthritis; comparison of different imaging-based methods

BackgroundOsteoporosis is increasingly being recognized in children, mostly secondary to systemic underlying conditions or medication. However, no imaging modality currently provides a full evaluation of bone health in children. We compared DXA, a radiographic bone health index (BHI (BoneXpert) and cone-beam CT for the assessment of low bone mass in children with juvenile idiopathic arthritis (JIA).MethodsData used in the present study was drawn from a large multicentre study including 228 children aged 4–16 years, examined between 2015 and 2020. All had a radiograph of the left hand, a DXA scan and a cone-beam CT of the temporomandibular joints within four weeks of each other. For the present study, we included 120 subjects, selected based on DXA BMD and BoneXpert BHI to secure values across the whole range to be tested.ResultsOne hundred and twenty children (60.0% females) were included, mean age 11.6 years (SD 3.1 years). There was a strong correlation between the absolute values of BHI and BMD for both total body less head (TBLH) (r = 0.75, p < 0.001) and lumbar spine (L1-L4) (r = 0.77, p < 0.001). The correlation between BHI standard deviation score (SDS) and BMD TBLH Z-scores was weak (r = 0.34) but significant (0 = 0.001), varying from weak (r = 0.31) to moderate (r = 0.42) between the three study sites.Categorizing BHI SDS and DXA BMD Z-scores on a 0–5 scale yielded a weak agreement between the two for both TBLH and LS, with w-kappa of 0.2, increasing to 0.3 when using quadratic weights. The agreement was notably higher for one of the three study sites as compared to the two others, particularly for spine assessment, yielding a moderate kappa value of 0.4 – 0.5.For cone-beam CT, based on a 1–3 scale, 59 out of 94 left TMJ’s were scored as 1 and 31 as score 2 by the first observer vs. 87 and 7 by the second observer yielding a poor agreement (kappa 0.1).ConclusionsCategorizing DXA LS and automated radiographic Z-scores on a 0–5 scale gave a weak to moderate agreement between the two methods, indicating that a hand radiograph might provide an adjuvant tool to DXA when assessing bone health children with JIA, given thorough calibration is performed.

Opportunistic Screening for Osteoporosis Using Hand Radiographs - A Feature Augmentation Study Technique (FAST).

Patients with low bone mineral density (BMD) face an increased risk of fractures, yet are frequently undiagnosed. Consequently, it is imperative to have opportunistically screen for low BMD in patients undergoing other medical evaluations. This retrospective study encompassed 422 patients aged ≥ 50 who underwent both dual-energy X-ray absorptiometry (DXA) and hand radiographs (modality of digital X-ray) from three different vendors within a 12-month period. The dataset was randomly divided into training/validation (n=338) and test (n=84) datasets. we sought to predict osteoporosis/osteopenia and establish correlations between bone textural analysis and DXA measurements. Our results demonstrate that the deep learning model achieved an accuracy of 77.38%, sensitivity of 77.38%, specificity of 73.63%, and an area under the curve (AUC) of 83% in detecting osteoporosis/osteopenia. These findings suggest that hand radiographs can serve as a viable screening tool for identifying individuals warranting formal DXA assessment for osteoporosis/osteopenia.

The natural history of marginal erosions in hands with and without osteoarthritis.

Among people with or without hand osteoarthritis, we aimed to identify characteristics of people (e.g., age and gender) with marginal erosions (MEs). We also examined changes in MEs during 48months. We described radiographic severity and progression among joints with MEs, changes in MEs, or central erosions (CEs). We studied participants from the Osteoarthritis Initiative with baseline and 48-month hand radiographs. A radiologist and rheumatologist evaluated the radiographs for disease severity (Kellgren-Lawrence grades) and erosions (central or marginal), respectively. We used descriptive statistics to characterize participants and calculated frequencies at the joint level. Of the 3558 participants, 89 had a ME at baseline. People with MEs were more often male, older, and ever (former and current) smokers than those without a ME. There was no difference in inflammatory biomarkers or the presence of hand pain between individuals with and without a baseline ME. Almost all hands had only one ME (80%), whereas only 50% of individuals with CEs had only one CE at baseline. Compared to CEs, MEs appeared more frequently in joints without osteoarthritis (54% vs. < 1%). Approximately 18% of joints with an ME progressed in Kellgren-Lawrence grade versus 4% without ME. Among the joints with an ME at baseline, 10% resolved by 48months. Less than 0.1% of joints developed a new ME. MEs appear to be distinct from CEs. MEs are predominantly present in males, isolated to one specific joint without osteoarthritis within a hand, and possibly predictive of radiographic progression. Key Points • Marginal erosions appear to be distinct from central erosions. • Most marginal erosions occur in joints without radiographic osteoarthritis. • Radiographic progression but not hand pain is more common in joints with a marginal erosion than without one.

Multimodal Imaging of Structural Damage and Inflammation in Psoriatic Arthritis: A comparison of DMARD-Naive and DMARD-Failure Patients.

To compare inflammatory and structural differences in active Psoriatic Arthritis (PsA) between disease-modifying antirheumatic drug (DMARD)-naive and DMARD-failure patients using diverse imaging approaches for future analyses. Additionally, to explore the influence of patient characteristics (clinical and demographic variables) on imaging findings. Of the 80 patients included from the first cohort of the ongoing multicentre TOFA-PREDICT trial, 40 were DMARD-naive and 40 were DMARD-failure (csDMARD failure; 1 prior bDMARD excluding etanercept was allowed), all meeting classification criteria for PsA with a minimum disease duration of eight weeks. Baseline conventional radiographs of hands and feet, MRIs of both ankles, and whole-body 18F-FDG PET/CT were evaluated for inflammatory and structural imaging parameters, including Sharp-van der Heijde (SHS), Heel Enthesitis Magnetic Resonance Imaging Scoring System (HEMRIS) and Deauville synovitis scoring. Differences between groups and the influence of patient characteristics were examined with multiple linear regression. At baseline, patient characteristics were similar between groups. Imaging parameters showed limited inflammation and structural damage. Inflammatory imaging parameters were not significantly different (p> 0.200). Among structural parameters, only HEMRIS Achilles tendon structural damage was significantly different (p= 0.024, R2=0.071) and, SHS Joint Space Narrowing was not statistically significant (p= 0.050, R2=0.048) with higher values for both in DMARD-failures. After correction of patient characteristics, these differences in imaging disappeared (both p> 0.600). At baseline, PsA patient groups were comparable concerning structural and inflammatory imaging parameters, especially after correcting for patient characteristics. Thus, DMARD-naive and DMARD-failure patient groups may be combined in future PsA progression and treatment decision studies. EudraCT: 2017-003900-28.

Decoding Radiology Reports: Artificial Intelligence-Large Language Models Can Improve the Readability of Hand and Wrist Orthopedic Radiology Reports.

The purpose of this study was to assess the effectiveness of an Artificial Intelligence-Large Language Model (AI-LLM) at improving the readability of hand and wrist radiology reports. The radiology reports of 100 hand and/or wrist radiographs, 100 hand and/or wrist computed tomography (CT) scans, and 100 hand and/or wrist magnetic resonance imaging (MRI) scans were extracted. The following prompt command was inserted into the AI-LLM: "Explain this radiology report to a patient in layman's terms in the second person: [Report Text]." The report length, Flesch reading ease score (FRES), and Flesch-Kincaid reading level (FKRL) were calculated for the original radiology report and the AI-LLM-generated report. The accuracy of the AI-LLM report was assessed via a 5-point Likert scale. Any "hallucination" produced by the AI-LLM-generated report was recorded. There was a statistically significant improvement in mean FRES scores and FKRL scores in the AI-LLM-generated radiograph report, CT report, and MRI report. For all AI-LLM-generated reports, the mean reading level improved to below an eighth-grade reading level. The mean Likert score for the AI-LLM-generated radiograph report, CT report, and MRI report was 4.1 ± 0.6, 3.9 ± 0.6, and 3.9 ± 0.7, respectively. The hallucination rate in the AI-LLM-generated radiograph report, CT report, and MRI report was 3%, 6%, and 6%, respectively. This study demonstrates that AI-LLM effectively improves the readability of hand and wrist radiology reports, underscoring the potential application of AI-LLM as a promising and innovative patient-centric strategy to improve patient comprehension of their imaging reports.Level of Evidence: IV.

Deep learning-based automated bone age estimation for Saudi patients on hand radiograph images: a retrospective study

PurposeIn pediatric medicine, precise estimation of bone age is essential for skeletal maturity evaluation, growth disorder diagnosis, and therapeutic intervention planning. Conventional techniques for determining bone age depend on radiologists’ subjective judgments, which may lead to non-negligible differences in the estimated bone age. This study proposes a deep learning-based model utilizing a fully connected convolutional neural network(CNN) to predict bone age from left-hand radiographs.MethodsThe data set used in this study, consisting of 473 patients, was retrospectively retrieved from the PACS (Picture Achieving and Communication System) of a single institution. We developed a fully connected CNN consisting of four convolutional blocks, three fully connected layers, and a single neuron as output. The model was trained and validated on 80% of the data using the mean-squared error as a cost function to minimize the difference between the predicted and reference bone age values through the Adam optimization algorithm. Data augmentation was applied to the training and validation sets yielded in doubling the data samples. The performance of the trained model was evaluated on a test data set (20%) using various metrics including, the mean absolute error (MAE), median absolute error (MedAE), root-mean-squared error (RMSE), and mean absolute percentage error (MAPE). The code of the developed model for predicting the bone age in this study is available publicly on GitHub at https://github.com/afiosman/deep-learning-based-bone-age-estimation.ResultsExperimental results demonstrate the sound capabilities of our model in predicting the bone age on the left-hand radiographs as in the majority of the cases, the predicted bone ages and reference bone ages are nearly close to each other with a calculated MAE of 2.3 [1.9, 2.7; 0.95 confidence level] years, MedAE of 2.1 years, RMAE of 3.0 [1.5, 4.5; 0.95 confidence level] years, and MAPE of 0.29 (29%) on the test data set.ConclusionThese findings highlight the usability of estimating the bone age from left-hand radiographs, helping radiologists to verify their own results considering the margin of error on the model. The performance of our proposed model could be improved with additional refining and validation.

The impact of HIV infection on skeletal maturity in peripubertal children in Zimbabwe: a cross-sectional study

IntroductionHIV infection and its treatment compromises skeletal development (growth and maturation). Skeletal maturity is assessed as bone age (BA) on hand and wrist radiographs. BA younger than chronological age (CA) indicates delayed development. We conducted a cross-sectional study to determine differences between BA and CA (i.e., skeletal maturity deviation [SMD]), and risk factors associated with SMD in peripubertal children with and without HIV established on antiretroviral therapy (ART) including use of tenofovir disoproxil fumarate (TDF).MethodsChildren with HIV taking ART for at least two years and a comparison group of HIV-negative children, aged 8–16 years and frequency-matched by age and sex, were recruited from HIV clinics and local schools in the same catchment area, in Harare, Zimbabwe. BA was assessed from non-dominant hand-wrist radiographs using the Tanner Whitehouse 3 method. Negative SMD values correspond to delayed development, i.e., BA younger than CA. Multivariable linear regression models determined factors associated with SMD overall, and in children with HIV.ResultsIn total, 534 participants (54% males) were included; by design CA was similar in males and females, whether living with or without HIV. Mean (SD) SMD was more negative in CWH than in HIV-negative children in both males [-1.4(1.4) vs. -0.4(1.1) years] and females [-1.1(1.3) vs. -0.0(1.2) years]. HIV infection and weight-for-age Z-score<-2 were associated with more negative SMD in both males and females after adjusting for socio-economic status, orphanhood, pubertal stage, and calcium intake. Age at ART initiation was associated with SMD in both males and females with those starting ART later more delayed: starting ART aged 4–8 years 1.14 (-1.84, -0.43), or over 8 years 1.47 (-2.30, -0.65) (p-value for trend < 0.001). Similar non-significant trends were seen in males. TDF exposure TDF exposure whether < 4years or ≥ 4 years was not associated with delayed development.ConclusionPerinatally-acquired HIV infection and being underweight were independently associated with delayed skeletal maturation in both males and females. Starting ART later was independently associated with skeletal maturation delay in CWH. Given the known effects of delayed development on later health, it is important to find interventions to ensure healthy weight gain through early years and in CWH to initiate ART as early as possible.

Radiograph-based rheumatoid arthritis diagnosis via convolutional neural network

ObjectivesRheumatoid arthritis (RA) is a severe and common autoimmune disease. Conventional diagnostic methods are often subjective, error-prone, and repetitive works. There is an urgent need for a method to detect RA accurately. Therefore, this study aims to develop an automatic diagnostic system based on deep learning for recognizing and staging RA from radiographs to assist physicians in diagnosing RA quickly and accurately.MethodsWe develop a CNN-based fully automated RA diagnostic model, exploring five popular CNN architectures on two clinical applications. The model is trained on a radiograph dataset containing 240 hand radiographs, of which 39 are normal and 201 are RA with five stages. For evaluation, we use 104 hand radiographs, of which 13 are normal and 91 RA with five stages.ResultsThe CNN model achieves good performance in RA diagnosis based on hand radiographs. For the RA recognition, all models achieve an AUC above 90% with a sensitivity over 98%. In particular, the AUC of the GoogLeNet-based model is 97.80%, and the sensitivity is 100.0%. For the RA staging, all models achieve over 77% AUC with a sensitivity over 80%. Specifically, the VGG16-based model achieves 83.36% AUC with 92.67% sensitivity.ConclusionThe presented GoogLeNet-based model and VGG16-based model have the best AUC and sensitivity for RA recognition and staging, respectively. The experimental results demonstrate the feasibility and applicability of CNN in radiograph-based RA diagnosis. Therefore, this model has important clinical significance, especially for resource-limited areas and inexperienced physicians.

Multimodal nature of pain syndrome in patients with rheumatoid arthritis in relation to the course of the disease and clinical characteristics

Purpose of the study. To evaluate the character of pain syndrome in patients with rheumatoid arthritis in correlation with the course of the disease and comorbid pathology.Material and methods. Sixty-six patients with a verified diagnosis of RA were examined. Of them 84.9% were women (n=56) and 15.1% men (n=10). The median age was 59 [52; 63] years. Disease activity was assessed by DAS28-CRP, with a median of 5.2 [4.54; 6.0]. Patients with moderate (31.8%) and high activity (57.5%) predominated. Disease duration averaged Me 156 [93; 246] months. Seropositive RA was suffered by 89.3% of patients. The distribution by radiological stage was as follows: 2 radiological stage – 36.3% (n=24), 3 radiological stage – 30.3% (n=20), 4 radiological stage – 33.4% (n=22). Baseline anti-inflammatory therapy was taken by 84.8% of patients (n=56), genetically engineered biological drugs were received by 28.7% (n=16). To assess the multicomponent nature of pain syndrome, the following were used: Pain Detect questionnaire — to verify neuropathic pain (NP), CSI questionnaire — to verify central sensitisation (CS). The EQ-5D-3L questionnaire was used to assess quality of life, and the Charlson index was used to assess comorbid pathology. Structural changes were assessed by modified Sharpe method on hand and foot radiographs, synovium vascularisation was assessed by joint ultrasound.Results. 84.8% of patients had pain syndrome of mixed nature. NP correlated with pain intensity by VAS (rSp=0.458, p&lt;0.001), DAS28-CRP (rSp=0.509, p&lt;0.001), number of peripheral arthritis (rSp=0, 414, p&lt;0.001), number of comorbidities (rSp=0.337, p=0.006), Charlson index (rSp=0.323, p=0.009), EQ-5D-3L (rSp= –0.268, p=0.031). CS–with VAS pain intensity (rSp=0.250, p=0.045), DAS28-CRP (rSp=0.251, p=0.044), number of painful joints (rSp=0.353, p=0.004), number of comorbidities (rSp=0.368, p=0.003), BMI (rSp=0.266, p=0.032), systolic blood pressure level (rSp=0.403, p&lt;0.001), number of erosions on hand and foot radiographs (rSp= –0.299, p=0.016), EQ-5D-3L (rCp= –0.408, p&lt;0.001). Patients with the presence of synovial vascularization by ultrasound had three-component pain in more than half of cases, and the combination of inflammatory pain and CS did not occur in them.Conclusions. 84.8% of patients had multicomponent pain, with pain associated only with clinical parameters of disease activity. Associated pathology and local chronic inflammation in the joint potentiate the development of other types of pain and have a mutual negative influence.

Cross-sectional and longitudinal analysis of bone age maturation during peri-pubertal growth in children with type I, III and IV osteogenesis imperfecta

Osteogenesis imperfecta (OI)is a rare genetically heterogeneous disorder caused by changes in the expression or processing of type I collagen. Clinical manifestations include bone fragility, decreased linear growth, and skeletal deformities that vary in severity. In typically growing children, skeletal maturation proceeds in a predictable pattern of changes in the size, shape, and mineralization on the hand and wrist bones that can be followed radiographically known at the bone age. Assessment of bone age can be clinically used to assess time remaining for linear growth, and the onset and duration of puberty, both of which can be useful in determining the timing of some surgeries or the interpretation of other imaging modalities such as bone densitometry. Additionally, deviations in the expected maturation process of the bone age may prompt or assist in the work up of a significant delay or advancement in a child's growth pattern. The primary aim of our study was to determine whether the bone age in children with a skeletal disorder such as OI follow the same pattern and rate of bone maturation compared to a control population. Using participants from the Natural History Study of the Brittle Bone Disorders Consortium, we analyzed 159 left hand and wrist radiographs (bone age) for a cross-sectional analysis and 55 bone ages repeated at approximately 24 months for a longitudinal analysis of skeletal maturation. Bone ages were read by a pediatric endocrinologist and by an automated analysis using a program called BoneXpert. Our results demonstrated that in children with mild-to-moderate OI (types I and IV), the skeletal maturation is comparable to chronological age-mated controls. For those with more severe forms of OI (type III), there is a delayed pattern of skeletal maturation of less than a year (10.5 months CI 5.1–16) P = 0.0012) at baseline and a delayed rate of maturation over the two-year follow up compared to type I (P = 0.06) and type III (P = 0.02). However, despite these parameters being statistically different, they may not be clinically significant. We conclude the bone age, with careful interpretation, can be used in the OI population in a way that is similar to the general pediatric population.