Convolutional neural network for classification of two-dimensional array images generated from clinical information may support diagnosis of rheumatoid arthritis.

This research aimed to study the application of deep learning to the diagnosis of rheumatoid arthritis (RA). Definite criteria or direct markers for diagnosing RA are lacking. Rheumatologists diagnose RA according to an integrated assessment based on scientific evidence and clinical experience. Our novel idea was to convert various clinical information from patients into simple two-dimensional images and then use them to fine-tune a convolutional neural network (CNN) to classify RA or nonRA. We semi-quantitatively converted each type of clinical information to four coloured square images and arranged them as one image for each patient. One rheumatologist modified each patient's clinical information to increase learning data. In total, 1037 images (252 RA, 785 nonRA) were used to fine-tune a pretrained CNN with transfer learning. For clinical data (10 RA, 40 nonRA), which were independent of the learning data and were used as testing data, we compared the classification ability of the fine-tuned CNN with that of three expert rheumatologists. Our simple system could potentially support RA diagnosis and therefore might be useful for screening RA in both specialised hospitals and general clinics. This study paves the way to enabling deep learning in the diagnosis of RA.

Incidence and risk factors for reactivation from resolved hepatitis B virus in rheumatoid arthritis patients treated with biological disease-modifying antirheumatic drugs.

AIM: To identify the incidence and risk factors for hepatitis B virus (HBV) reactivation in rheumatoid arthritis (RA) patients with resolved HBV receiving biological disease-modifying antirheumatic drugs (bDMARDs). METHOD: Rheumatoid arthritis patients in whom bDMARD therapy was initiated in our departments from April 2009 to July 2016 were reviewed. The patients diagnosed with resolved HBV and whose HBV-DNA levels had been repeatedly measured were enrolled. The endpoint was HBV reactivation (a positive conversion of HBV-DNA or unquantifiable cases with positivity <20 IU/mL). Nucleic acid analogues (NAAs) were administered when the HBV-DNA levels increased beyond 20 IU/mL. The associations between HBV reactivation and the clinical findings were retrospectively analyzed. RESULTS: One hundred and fifty-two RA patients with resolved HBV were enrolled; 133 (88%) patients had antibodies against HBV surface antigen (anti-HBs). The medicines that were administered included: abatacept (n = 29), golimumab (n = 26), etanercept (n = 25), tocilizumab (n = 25), adalimumab (n = 19), infliximab (n = 17) and certolizumab pegol (n = 11). During the observation period (15 [interquartile range 4.0-34] months), 7 (4.6%) patients developed HBV reactivation. In 5 of these patients, the HBV-DNA levels became negative or remained at <20 IU/mL (+) without NAA therapy. HBV-DNA levels of >20 IU/mL were observed in 2 patients but the HBV-DNA levels became negative after NAA treatment. Patients who were negative for anti-HBs showed a significantly higher incidence of HBV reactivation (P = 0.013). CONCLUSION: HBV reactivation occurred in 4.6% of RA patients with resolved HBV during the treatment with bDMARDs and the absence of anti-HBs may be a risk factor for the reactivation of resolved HBV.

Active synovitis in the presence of osteitis predicts residual synovitis in patients with rheumatoid arthritis with a clinical response to treatment.

AIM: To clarify the relationship between active synovitis/osteitis and subsequent residual synovitis (R-synovitis) in patients with rheumatoid arthritis (RA). METHODS: Three hundred and twenty finger joints of 16 patients with active RA at baseline (Disease Activity Score with 28 joints - erythrocyte sedimentation rate > 3.2) who subsequently achieved clinical low disease activity or remission afterwards were analyzed. Synovial vascularity (SV) was assessed according to a semi-quantitative ultrasound score (grades 0-3). Active synovitis was defined by SV positivity at baseline. R-synovitis was defined by the presence of grade > 2 SV at the 24th week. Osteitis was detected by magnetic resonance imaging (MRI) at baseline as trabecular bone lesions with water content and indistinct margins. RESULTS: Ultrasonography detected active synovitis in 116 joints at baseline. Forty-seven joints had R-synovitis at the 24th week. MRI detected osteitis in 12 joints at baseline. The presence of active synovitis with osteitis at baseline was significantly correlated with R-synovitis at the 24th week. CONCLUSIONS: Active synovitis in the presence of osteitis predicted R-synovitis regardless of whether there was a clinical improvement in RA.

Structural deterioration of finger joints with ultrasonographic synovitis in rheumatoid arthritis patients with clinical low disease activity.

OBJECTIVE: In this study we investigated the relationship between synovial vascularity (SV) and structural alteration of finger joints in patients with RA and long-term sustained clinical low disease activity (CLDA). METHODS: RA patients with CLDA of >2 years (minimum 1 year of CLDA for study entry plus 1 year of observation) were analysed. Quantitative SV values were sequentially measured in each finger joint using power Doppler ultrasonography (0, 8, 20 and 52 weeks). Radiological progression of local finger joints was evaluated according to the Genant-modified Sharp score (0-52 weeks). RESULTS: Of the 25 patients enrolled, 15 patients were finally analysed after excluding 10 patients who failed to maintain CLDA during the observational period. Changes in radiological progression of MCP and PIP joints with positive SV were significantly greater than those in joints with negative SV. Joint space narrowing (JSN) was strongly related to structural alteration of finger joints. In joints with positive SV, changes in structural alteration did not relate to total SV values, which reflect total exposure to inflammation in an observational period. CONCLUSION: Even in patients with a long period of CLDA, finger joints with positive SV showed structural alteration, especially in the progression of JSN. TRIAL REGISTRATION: University Hospital Medical Information Network Clinical Trials Registry, http://www.umin.ac.jp/ctr/, UMIN000007305.

Positive synovial vascularity in patients with low disease activity indicates smouldering inflammation leading to joint damage in rheumatoid arthritis: time-integrated joint inflammation estimated by synovial vascularity in each finger joint.

OBJECTIVE: To investigate the relationship between synovial vascularity and joint damage progression in each finger joint of patients with RA under low disease activity during treatment with biologic agents. METHODS: We studied 310 MCP and 310 PIP joints of 31 patients with active RA who were administered adalimumab (ADA) or tocilizumab (TCZ). Patients were examined with clinical and laboratory assessments. Power Doppler sonography was performed at baseline and at weeks 8, 20 and 40. Synovial vascularity was evaluated according to quantitative measurement. Hand and foot radiography was performed at baseline and at week 50. RESULTS: Composite scores of the DAS with 28 joints and the Simplified Disease Activity Index (SDAI) were significantly decreased from baseline to week 8, being sustained at a low level by biologic agents during the observational period. MCP and PIP joints with positive synovial vascularity after week 8 showed more subsequent joint damage progression than joints without synovial vascularity throughout the follow-up. The changes in radiographic progression in these joints were independent of the sum of synovial vascularity from baseline to week 40 or the occasional occurrence of positive synovial vascularity. CONCLUSION: Smouldering inflammation reflected by positive synovial vascularity under low disease activity was linked to joint damage. The damage progressed irrespective of the severity of positive synovial vascularity. Even with a favourable overall therapeutic response, monitoring of synovial vascularity has the potential to provide useful joint information to tailor treatment strategies. Trial registration. University Hospital Medical Information Network Clinical Trials Registry; http://www.umin.ac.jp/ctr/; UMIN000004476.

Radiographic prognosis of finger joint damage predicted by early alteration in synovial vascularity in patients with rheumatoid arthritis: Potential utility of power doppler sonography in clinical practice.

OBJECTIVE: To investigate the relationship between synovial vascularity and progression of structural bone damage in each finger joint in patients with rheumatoid arthritis (RA) and to demonstrate synovial vascularity as a potential therapeutic marker. METHODS: We studied 250 metacarpophalangeal (MCP) and 250 proximal interphalangeal (PIP) joints of 25 patients with active RA who were administered adalimumab or tocilizumab. Patients were examined with clinical and laboratory assessments. Power Doppler sonography was performed at baseline and at the fourth and eighth weeks. Synovial vascularity was evaluated according to quantitative measurement. Hand and foot radiography was performed at baseline and the twentieth week. RESULTS: Clinical indices such as the 28-joint Disease Activity Score, the Clinical Disease Activity Index, and the Simplified Disease Activity Index were significantly decreased by biologic agents. The MCP and PIP joints with no response in synovial vascularity between baseline and the eighth week (vascularity improvement of ≤70% at the eighth week) showed a higher risk of radiographic progression compared with responsive joints (vascularity improvement of >70% at the eighth week; relative risk 2.33-9). Radiographic progression at the twentieth week was significantly lower in responsive joints than in nonresponsive joints. CONCLUSION: The improvement of synovial vascularity following treatment with biologic agents led to suppression of radiographic progression of RA in each finger joint. The alteration in synovial vascularity numerically reflected therapeutic efficacy. Using vascularity as a marker to determine the most suitable therapeutic approach would be beneficial for patients with active RA.

Simplified approach to MR image quantification of the rheumatoid wrist: a pilot study.

OBJECTIVES: To determine an optimal threshold in a simplified 3D-based volumetry of abnormal signals in rheumatoid wrists utilizing contrast and non-contrast MR data, and investigate the feasibility and reliability of this method. MATERIALS AND METHODS: MR images of bilateral hands of 15 active rheumatoid patients were assessed before and 5 months after the initiation of tocilizumab infusion protocol. The volumes of abnormal signals were measured on STIR and post-contrast fat-suppressed T1-weighted images. Three-dimensional volume rendering of the images was used for segmentation of the wrist by an MR technologist and a radiologist. Volumetric data were obtained with variable thresholding (1, 1.25, 1.5, 1.75, and 2 times the muscle signal), and were compared to clinical data and semiquantitative MR scoring (RAMRIS) of the wrist. Intra- and interobserver variability and time needed for volumetry measurements were assessed. RESULTS: The volumetric data correlated favorably with clinical parameters almost throughout the pre-determined thresholds. Interval differences in volumetric data correlated favorably with those of RAMRIS when the threshold was set at more than 1.5 times the muscle signal. The repeatability index was lower than the average of the interval differences in volumetric data when the threshold was set at 1.5-1.75 for STIR data. Intra- and interobserver variability for volumetry was 0.79-0.84. The time required for volumetry was shorter than that for RAMRIS. CONCLUSIONS: These results suggest that a simplified MR volumetric data acquisition may provide gross estimates of disease activity when the threshold is set properly. Such estimation can be achieved quickly by non-imaging specialists and without contrast administration.

Monitoring anti-interleukin 6 receptor antibody treatment for rheumatoid arthritis by quantitative magnetic resonance imaging of the hand and power Doppler ultrasonography of the finger.

OBJECTIVES: To compare quantitative magnetic resonance imaging (MRI) and power Doppler ultrasonography (PDUS) with conventional measures of disease activity in rheumatoid arthritis (RA) patients treated with the anti-interleukin 6 (anti-IL 6) receptor antibody tocilizumab in terms of responsiveness at a few months to disease activity and ability to predict structural damage at 1 year. METHODS: A cohort of patients with RA (n = 29) was evaluated clinically including disease activity score 28 (DAS28) and by semiquantitative (SQ-) and quantitative (Q-) PDUS (bilateral metacarpophalangeal joints) and MRI (one hand and wrist) at initiation of treatment with anti-IL 6 receptor antibody agents and after 2 and 5 months. Conventional radiography for both hands and wrists was performed at baseline and at 12 months. Responsiveness was assessed by standardized response means (SRM). Areas under the curve (AUC) for measures at baseline, 2 and 5 months were correlated with structural damage at 1 year. RESULTS: Among the laboratory and clinical parameters, DAS28-ESR was the most responsive with a large effect size of SRM. Structural damage progressions for radiography and MR erosion were correlated with AUC of MR bone erosion and Q-PDUS, respectively. CONCLUSIONS: In the evaluation of disease activity in RA patients in the first few months after starting anti-IL 6 receptor antibody tocilizumab treatment, the semiquantitative MR bone erosion score of the hand and quantitative value for power Doppler signal in the finger joint were both responsive and predictive of structural damage progression at 1 year.

Change of synovial vascularity in a single finger joint assessed by power doppler sonography correlated with radiographic change in rheumatoid arthritis: comparative study of a novel quantitative score with a semiquantitative score.

OBJECTIVE: To investigate the relationship between synovial vascularity assessed by quantitative power Doppler sonography (PDS) and progression of structural bone damage in a single finger joint in patients with rheumatoid arthritis (RA). METHODS: We studied 190 metacarpophalangeal (MCP) joints and 190 proximal interphalangeal (PIP) joints of 19 patients with active RA who had initial treatment with disease-modifying antirheumatic drugs (DMARDs). Patients were examined by clinical and laboratory assessments throughout the study. Hand and foot radiography was performed at baseline and the twentieth week. Magnetic resonance imaging (MRI) was performed at baseline. PDS was performed at baseline and the eighth week. Synovial vascularity was evaluated according to both quantitative and semiquantitative methods. RESULTS: Quantitative PDS was significantly correlated with the enhancement rate of MRI in each single finger joint. Comparing quantitative synovial vascularity and radiographic change in single MCP or PIP joints, the level of vascularity at baseline showed a significant positive correlation with radiographic progression at the twentieth week. The change of vascularity in response to DMARDs, defined as the percentage change in vascularity by the eighth week from baseline, was inversely correlated with radiographic progression in each MCP joint. The quantitative PDS method was more useful than the semiquantitative method for the evaluation of synovial vascularity in a single finger joint. CONCLUSION: The change of synovial vascularity in a single finger joint determined by quantitative PDS could numerically predict its radiographic progression. Using vascularity as a guide to consider a therapeutic approach would have benefits for patients with active RA.

Semi-quantitative analysis of rheumatoid finger joint synovitis using power Doppler ultrasonography: when to perform follow-up study after treatment consisting mainly of antitumor necrosis factor alpha agent.

PURPOSE: To determine the timing for follow-up study of power Doppler ultrasonography (PDUS) by evaluating the response of finger joint synovitis in patients with rheumatoid arthritis (RA) to treatment including infliximab, an antitumor necrosis factor alpha agent. METHODS AND MATERIALS: Bilateral second/third metacarpo-phalangeal (MCP) joints and second proximal inter-phalangeal (PIP) joints (total of six joints) in 21 patients (18 women and three men; median age 53 years) with chronic active RA were assessed by PDUS before and after 2 weeks, 6 weeks, 14 weeks, 30 weeks, 38 weeks, 46 weeks, and 54 weeks of infliximab infusion. Pulse Doppler settings were standardized for each patient and optimized for the detection of synovial blood flow by adjustment of color gain, pulse repetition, and flow optimization. Power Doppler signal was graded for each joint [joint grade for power Doppler (JGPD) signals], and the sum of the grades of six joints was defined as the PDUS index [joint index for power Doppler signals (JIPD)] at each visit. PDUS and clinical parameters [28-joint disease activity score (DAS28), health assessment questionnaire, and C-reactive protein (CRP) level] were independently assessed and compared with baseline values. The American College of Rheumatology (ACR) core set responders and non-responders at week 54 were compared for clinical parameters and PDUS index at each visit. RESULTS: Fourteen patients completed the planned treatment for 1 year, while six patients dropped out for various reasons and one died suddenly. PDUS was performed a total of 146 times on 467 joints. DAS28 was assessed 127 times. Both DAS28 and JIPD had decreased at the follow-up. Comparative analysis between DAS28 and PDUS was available 125 times. The transverse correlation between the PDUS index and DAS28 was not significant throughout the follow-up period. When responders and non-responders were discriminated at week 54, a logistic regression model for the binary endpoint of responder vs non-responder, with PDUS index as explanatory variable at time point 0, and follow-up revealed statistical significance from week 38 and on. CONCLUSION: PDUS reflected infliximab's effect on pannus vascular signals; this effect was observed as early as 2 weeks after treatment had begun. Also, the responders to treatment at 54 weeks tended to have fewer JIPD than non-responders in the follow-up period. PDUS may be performed at week 38 or later to foresee the response to the treatment at week 54.

Screening for rheumatoid arthritis with finger joint power Doppler ultrasonography: quantification of conventional power Doppler ultrasonographic scoring.

Power Doppler ultrasonography (PD-US) has proved to be a useful technique to measure synovial vascularity due to its capability to provide data that can be used to evaluate the level of joint inflammation and assess rheumatoid arthritis (RA). We have developed a novel PD-US finger joint scoring method that introduces quantitative measurements into the conventional PD-US assessment method. A comparison of the two methods revealed that our novel PD-US method strongly correlates with the conventional method in terms of RA assessment. We performed finger joint PD-US on 69 patients with RA and 70 patients who had multiple joint pain but showed no evidence of inflammatory diseases (non-inflammatory disease, NI) and measured the synovial vascularity of the metacarpophalangeal joints 1-5 and proximal interphalangeal (PIP) joints 1-5 for each patient. We analyzed the data with receiver operating characteristic analysis and, based on the results for the total vascularity of 20 finger joints, defined a cut-off value of 36% as discriminating between RA and NI. This cut-off value was found to be a valuable tool in screening for RA. We conclude that our finger joint PD-US scoring system is both useful and applicable for diagnosing RA.

A case of interstitial pneumonia caused by bucillamine: a study using serological markers.

The patient was a 61-year-old man diagnosed with rheumatoid arthritis (RA) in 2001. He initially received treatment at a nearby clinic, but his condition could not be satisfactorily controlled. He subsequently consulted our hospital during the same year. Although his symptoms improved in response to treatment at our hospital, slight fever, cough, and then high fever and dyspnea subsequently developed. A diagnosis of interstitial pneumonia was made on the basis of findings of diagnostic imaging. The time course of changes in serological markers, including surfactant protein A (SP-A), surfactant protein D (SP-D), and KL-6, as well as markers of inflammatory reaction and lactate dehydrogenase was examined to determine the clinical significance of serological markers in the management of interstitial pneumonia.