PURPOSE: A classification-based segmentation method is proposed to quantify synovium in rheumatoid arthritis (RA) patients using a deep learning (DL) method based on time-intensity curve (TIC) analysis in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). MATERIALS AND METHODS: This retrospective study analyzed a hand MR dataset of 28 RA patients (six males, mean age 53.7 years). A researcher, under expert guidance, used in-house software to delineate regions of interest (ROIs) for hand muscles, bones, and synovitis, generating a dataset with 27,255 pixels with corresponding TICs (muscle: 11,413, bone: 8502, synovitis: 7340). One experienced musculoskeletal radiologist performed ground truth segmentation of enhanced pannus in the joint bounding box on the 10th DCE phase, or around 5 min after contrast injection. Data preprocessing included median filtering for noise reduction, phase-only correlation algorithm for motion correction, and contrast-limited adaptive histogram equalization for improved image contrast and noise suppression. TIC intensity values were normalized using zero-mean normalization. A DL model with dilated causal convolution and SELU activation function was developed for enhanced pannus segmentation, tested using leave-one-out cross-validation. RESULTS: 407 joint bounding boxes were manually segmented, with 129 synovitis masks. On the pixel-based level, the DL model achieved sensitivity of 85%, specificity of 98%, accuracy of 99% and precision of 84% for enhanced pannus segmentation, with a mean Dice score of 0.73. The false-positive rate for predicting cases without synovitis was 0.8%. DL-measured enhanced pannus volume strongly correlated with ground truth at both pixel-based (r = 0.87, p < 0.001) and patient-based levels (r = 0.84, p < 0.001). Bland-Altman analysis showed the mean difference for hand joints at the pixel-based and patient-based levels were -9.46 mm3 and -50.87 mm3, respectively. CONCLUSION: Our DL-based DCE-MRI TIC shape analysis has the potential for automatic segmentation and quantification of enhanced synovium in the hands of RA patients.
BACKGROUND: Challenges persist in achieving automatic and efficient inflammation quantification using dynamic contrast-enhanced (DCE) MRI in rheumatoid arthritis (RA) patients. PURPOSE: To investigate an automatic artificial intelligence (AI) approach and an optimized dynamic MRI protocol for quantifying disease activity in RA in whole hands while excluding arterial pixels. STUDY TYPE: Retrospective. SUBJECTS: Twelve RA patients underwent DCE-MRI with 27 phases for creating the AI model and tested on images with a variable number of phases from 35 RA patients. FIELD STRENGTH/SEQUENCE: 3.0 T/DCE T1-weighted gradient echo sequence (mDixon, water image). ASSESSMENT: The model was trained with various DCE-MRI time-intensity number of phases. Evaluations were conducted for similarity between AI segmentation and manual outlining in 51 ROIs with synovitis. The relationship between synovial volume via AI segmentation with rheumatoid arthritis magnetic resonance imaging scoring (RAMRIS) across whole hands was then evaluated. The reference standard was determined by an experienced musculoskeletal radiologist. STATISTICAL TEST: Area under the curve (AUC) of receiver operating characteristic (ROC), Dice and Spearman's rank correlation coefficients, and interclass correlation coefficient (ICC). A P-value <0.05 was considered statistically significant. RESULTS: A minimum of 15 phases (acquisition time at least 2.5 minutes) was found to be necessary. AUC ranged from 0.941 ± 0.009 to 0.965 ± 0.009. The Dice score was 0.557-0.615. Spearman's correlation coefficients between the AI model and ground truth were 0.884-0.927 and 0.736-0.831, for joint ROIs and whole hands, respectively. The Spearman's correlation coefficient for the additional test set between the model trained with 15 phases and RAMRIS was 0.768. CONCLUSION: The AI-based classification model effectively identified synovitis pixels while excluding arteries. The optimal performance was achieved with at least 15 phases, providing a quantitative assessment of inflammatory activity in RA while minimizing acquisition time. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.
OBJECTIVES: We investigated whether our in-house software equipped with partial image phase-only correlation (PIPOC) can detect subtle radiographic joint space narrowing (JSN) progression at six months and predict JSN progression in rheumatoid arthritis (RA) patients receiving Tocilizumab. METHODS: The study included 39 RA patients who were treated with Tocilizumab. Radiological progression of the metacarpophalangeal and the proximal interphalangeal joints was evaluated according to the Genant-modified Sharp score (GSS) at 0, 6, and 12 months. Automatic measurements were performed with the software. We validated the software in terms of accuracy in detecting the JSN progression. RESULTS: The success rate of the software for joint space width (JSW) measurement was 96.8% (449/464). The 0-12-month JSW change by the software was significantly greater in joints with the 0-6-month PIPOC (+) group than the 0-6-month PIPOC (-) group (p < 0.001). The 0-12-month JSW change by the software was 0-12-month GSS (+) than with 0-12-month GSS (-) (p = 0.02). Here, "(+)" indicates the JSN progression during the follow-up period. Meanwhile, "(-)" indicates no JSN progression during the follow-up period. Linear regression tests showed significant correlations between the 0-6-month and the 0-12-month PIPOC in the left 2nd and 3rd MCP joints (R2 = 0.554 and 0.420, respectively). CONCLUSIONS: Our in-house software equipped with PIPOC could predict subsequent JSN progression with only short-term observations.
Presents corrections to the article "A Sub-Pixel Accurate Quantification of Joint Space Narrowing Progression in Rheumatoid Arthritis".
Early diagnosis and initiation of treatment for fresh osteoporotic lumbar vertebral fractures (OLVF) are crucial. Magnetic resonance imaging (MRI) is generally performed to differentiate between fresh and old OLVF. However, MRIs can be intolerable for patients with severe back pain. Furthermore, it is difficult to perform in an emergency. MRI should therefore only be performed in appropriately selected patients with a high suspicion of fresh fractures. As radiography is the first-choice imaging examination for the diagnosis of OLVF, improving screening accuracy with radiographs will optimize the decision of whether an MRI is necessary. This study aimed to develop a method to automatically classify lumbar vertebrae (LV) conditions such as normal, old, or fresh OLVF using deep learning methods with radiography. A total of 3481 LV images for training, validation, and testing and 662 LV images for external validation were collected. Visual evaluation by two radiologists determined the ground truth of LV diagnoses. Three convolutional neural networks were ensembled. The accuracy, sensitivity, and specificity were 0.89, 0.83, and 0.92 in the test and 0.84, 0.76, and 0.89 in the external validation, respectively. The results suggest that the proposed method can contribute to the accurate automatic classification of LV conditions on radiography.
Rheumatoid arthritis (RA) is a chronic autoimmune inflammatory disease that leads to progressive articular destruction and severe disability. Joint space narrowing (JSN) has been regarded as an important indicator for RA progression and has received significant attention. Radiology plays a crucial role in the diagnosis and monitoring of RA through the assessment of joint space. A new framework for monitoring joint space by quantifying joint space narrowing (JSN) progression through image registration in radiographic images has emerged as a promising research direction. This framework offers the advantage of high accuracy; however, challenges still exist in reducing mismatches and improving reliability. In this work, we utilize a deep intra-subject rigid registration network to automatically quantify JSN progression in the early stages of RA. In our experiments, the mean-square error of the Euclidean distance between the moving and fixed images was 0.0031, the standard deviation was 0.0661 mm and the mismatching rate was 0.48%. Our method achieves sub-pixel level accuracy, surpassing manual measurements significantly. The proposed method is robust to noise, rotation and scaling of joints. Moreover, it provides misalignment visualization, which can assist radiologists and rheumatologists in assessing the reliability of quantification, exhibiting potential for future clinical applications. As a result, we are optimistic that our proposed method will make a significant contribution to the automatic quantification of JSN progression in RA. Code is available at https://github.com/pokeblow/Deep-Registration-QJSN-Finger.git.
Arthritis, Rheumatoid , Humans , Reproducibility of Results , Arthritis, Rheumatoid/diagnostic imaging , Radiography , Disease Progression
Rheumatoid arthritis (RA) is a chronic autoimmune disease that primarily affects peripheral synovial joints, like fingers, wrists and feet. Radiology plays a critical role in the diagnosis and monitoring of RA. Limited by the current spatial resolution of radiographic imaging, joint space narrowing (JSN) progression of RA for the same reason above can be less than one pixel per year with universal spatial resolution. Insensitive monitoring of JSN can hinder the radiologist/rheumatologist from making a proper and timely clinical judgment. In this paper, we propose a novel and sensitive method that we call partial image phase-only correlation which aims to automatically quantify JSN progression in the early RA. The majority of the current literature utilizes the mean error, root-mean-square deviation and standard deviation to report the accuracy at pixel level. Our work measures JSN progression between a baseline and its follow-up finger joint images by using the phase spectrum in the frequency domain. Using this study, the mean error can be reduced to 0.0130 mm when applied to phantom radiographs with ground truth, and 0.0519 mm standard deviation for clinical radiography. With the sub-pixel accuracy far beyond usual manual measurements, we are optimistic that the proposed work is a promising scheme for automatically quantifying JSN progression.
Arthritis, Rheumatoid , Humans , Arthritis, Rheumatoid/diagnostic imaging , Radiography , Finger Joint , Wrist , Disease Progression
PURPOSE: We have developed an in-house software equipped with partial image phase-only correlation (PIPOC) which can automatically quantify radiographic joint space narrowing (JSN) progression. The purpose of this study was to evaluate the software in phantom and clinical assessments. MATERIALS AND METHODS: In the phantom assessment, the software's performance on radiographic images was compared to the joint space width (JSW) difference using a micrometer as ground truth. A phantom simulating a finger joint was scanned underwater. In the clinical assessment, 15 RA patients were included. The software measured the radiological progression of the finger joints between baseline and the 52nd week. The cases were also evaluated with the Genant-modified Sharp score (GSS), a conventional visual scoring method. We also quantitatively assessed these joints' synovial vascularity (SV) on power Doppler ultrasonography (0, 8, 20 and 52 weeks). RESULTS: In the phantom assessment, the PIPOC software could detect changes in JSN with a smallest detectable difference of 0.044 mm at 0.1 mm intervals. In the clinical assessment, the JSW change of the joints with GSS progression detected by the software was significantly greater than those without GSS progression (p = 0.004). The JSW change of joints with positive SV at baseline was significantly higher than those with negative SV (p = 0.024). CONCLUSION: Our in-house software equipped with PIPOC can automatically and quantitatively detect slight radiographic changes of JSW in clinically inactive RA patients.
Arthritis, Rheumatoid , Humans , Arthritis, Rheumatoid/diagnostic imaging , Radiography , Finger Joint/diagnostic imaging , Software , Ultrasonography , Disease Progression
BACKGROUND: This study examined the prevalence of visceral obesity in Chinese adults across different body mass index (BMI) groups and their associated lipid profiles and demographic risk factors. METHODS: A total of 1653 Chinese adults were recruited for the study. Abdominal quantitative computed tomography (CT) imaging was performed to derive the visceral adipose tissue (VAT) at the lumbar vertebrae (L2-L3) levels. Visceral obesity was defined using established cutoff values. Fasting serum total cholesterol, total glucose, high-density lipoprotein, and low-density lipoprotein were measured. RESULTS: Visceral obesity was prevalent in 35% of men and 22% of women with normal BMI (18.5-24 kg/m2) and 86% of men and 78% of women with high BMI (≥24 kg/m2). In both sexes, participants with normal BMI and visceral obesity had higher levels of TC, TG and LDL and lower HDL compared to those with normal VAT. The risk factors for visceral obesity in women with normal BMI were an age ≥50 years and BMI ≥22.3 kg/m2 and in men included a BMI ≥22.5 kg/m2. CONCLUSION: Visceral obesity was observed in the participants with normal BMI and was associated with an adverse lipid profile. The BMI cutoff points were lower than the normally accepted values.
This study was conducted to measured talar displacement using ultrasound during an anterior drawer test (ADT) with a Telos device. Five adults (3 men and 2 women; 8 ankles; mean age: 23.2 y) with a history of ankle sprain and eight adults (5 men and 3 women; 16 ankles; mean age: 22.1 y) without a history of ankle sprain were recruited into a history of ankle sprain (HAS) and a control group, respectively. Talar displacement was observed in response to load forces applied by a Telos device during the ultrasound stress imaging test. The ultrasound probe was placed 5 mm inside from the center of the Achilles tendon on the posterior ankle along the direction of the major axis. The inter-rater reliability for the present method was classified as good and excellent (ICC(2,2) = 0.858 and 0.957 at 120 N and 150 N, respectively) in the control group and excellent (ICC(2,2) = 0.940 and 0.905 at 120 N and 150 N, respectively) in the HAS group, according to specific intraclass correlation coefficient values. We found that talar displacement during the ADT was lower in the HAS group than in the control group. Analysis of the receiver operating characteristic curve revealed that the quantitative ultrasound-based ADT using a Telos device was superior to the X-ray-based test in detecting reduced ankle joint mobility during the ADT (area under the curve of 0.905 and 0.726 at a force of 150 N using ultrasound-based and X-ray-based tests, respectively). Further investigation is needed; nevertheless, this preliminary study suggests that the ultrasound-based quantitative ADT using a Telos device might detect talar displacement more sensitively than the conventional stress X-ray.
Exercise Test , Joint Instability , Adult , Ankle Joint/diagnostic imaging , Feasibility Studies , Female , Humans , Male , Reproducibility of Results , Young Adult
Connectedness among older people is essential for healthy communities, especially among rural populations where limited social interaction and associated health effects may be cause for concern. In this qualitative descriptive study, we explored older rural people's perception of connectedness through a communication application. The study assessed 10 participants (mean age = 76.2 years) living in rural Japan who regularly participated in a senior citizens' club. From July 2019 to January 2020, the participants used a social media application developed by our research team to meet the needs of older people. Semi-structured interviews were conducted. Six themes representing older rural people's perception of connectedness were identified: (1) thoughtful consideration for members strengthened even without them meeting face-to-face, (2) encouragement received from familiar members, (3) joy in sharing daily routine with neighbors, (4) courage to advance through face-to-face interaction, (5) willingness to continue club membership, and (6) fear of disrupting club's harmony. Participants who used the application felt compensated for the lack of social interaction opportunities in rural settings and strengthened their existing relationships.
Health Status , Rural Population , Aged , Communication , Humans , Perception , Qualitative Research
Several visual scoring methods are currently used to assess progression of rheumatoid arthritis (RA) on radiography. However, they are limited by its subjectivity and insufficient sensitivity. We have developed an original measurement system which uses a technique called phase-only correlation (POC). The purpose of this study is to validate the system by using a phantom simulating the joint of RA patients.A micrometer measurement apparatus that can adjust arbitrary joint space width (JSW) in a phantom joint was developed to define true JSW. The phantom was scanned with radiography, 320 multi detector CT (MDCT), high-resolution peripheral quantitative CT (HR-pQCT), cone beam CT (CBCT), and tomosynthesis. The width was adjusted to the average size of a women's metacarpophalangeal joint, from 1.2 to 2.2 mm with increments of 0.1 mm and 0.01 mm. Radiographical images were analyzed by the POC-based system and manual method, and images from various tomographical modalities were measured via the automatic margin detection method. Correlation coefficients between true JSW difference and measured JSW difference were all strong at 0.1 mm intervals with radiography (POC-based system and manual method), CBCT, 320MDCT, HR-pQCT, and tomosynthesis. At 0.01 mm intervals, radiography (POC-based system), 320MDCT, and HR-pQCT had strong correlations, while radiography (manual method) and CBCT had low correlations, and tomosynthesis had no statistically significant correlation. The smallest detectable changes for radiography (POC-based system), radiography (manual method), 320MDCT, HR-pQCT, CBCT, and tomosynthesis were 0.020 mm, 0.041 mm, 0.076 mm, 0.077 mm, 0.057 mm, and 0.087 mm, respectively. We conclude that radiography analyzed with the POC-based system might sensitively detect minute joint space changes of the finger joint.
Metacarpophalangeal Joint , Tomography, X-Ray Computed , Female , Finger Joint , Humans , Phantoms, Imaging , Radiography
BACKGROUND: Fibroma of tendon sheath (FTS) is a rare benign soft tissue tumor that often occurs in the upper extremities. It manifests as a slow-growing mass, often without tenderness or spontaneous pain. FTS occurs most commonly in people aged 20-40 years and is extremely rare in young children. Because FTS presents with atypical physical and imaging findings, it might be misdiagnosed as another soft tissue tumor such as a ganglion cyst or tenosynovial giant cell tumor (TSGCT). Although marginal resection is usually performed, a high rate of local recurrence is reported. CASE PRESENTATION: A boy aged 3 years and 1 month visited our outpatient clinic with a complaint of a mass of the left hand. An elastic hard mass approximately 20 mm in diameter could be palpated on the volar side of his left little finger. This mass was initially diagnosed as a ganglion cyst at another hospital. Ultrasonography revealed a well-circumscribed hypoechoic mass with internal heterogeneity on the flexor tendon. On magnetic resonance imaging (MRI), the mass showed iso signal intensity to muscle on T1-weighted images, and homogeneously low signal intensity to muscle on T2-weighted images. The mass was peripherally enhanced after contrast administration. FTS was initially suspected as the diagnosis on the basis of these imaging features. Because of the limited range of motion of his little finger, surgery was performed when he was 4 years old. Histopathological findings indicated the mass was well-circumscribed and contained scattered spindle cells embedded in a prominent collagenous matrix. The spindle cells contained elongated and cytologically bland nuclei with a fine chromatin pattern. Nuclear pleomorphism and multinucleated giant cells were not observed. On the basis of these findings, we made a diagnosis of FTS. One year after surgery, no signs of local recurrence were observed. CONCLUSIONS: We experienced an extremely rare case of FTS in the hand of a 3-year-old child. We especially recommend ultrasonography for hand tumors of young children to diagnose or eliminate ganglion cysts. MRI helped differentially diagnose FTS from TSGCT. Although marginal resection can be performed as a treatment, great care should be taken postoperatively because FTS has a high possibility of local recurrence.
Fibroma , Giant Cell Tumor of Tendon Sheath , Soft Tissue Neoplasms , Adult , Child, Preschool , Humans , Magnetic Resonance Imaging , Male , Neoplasm Recurrence, Local , Soft Tissue Neoplasms/diagnostic imaging , Soft Tissue Neoplasms/surgery , Tendons/diagnostic imaging , Tendons/surgery , Young Adult
BACKGROUND: Although rheumatoid arthritis (RA) causes destruction of articular cartilage, early treatment significantly improves symptoms and delays progression. It is important to detect subtle damage for an early diagnosis. Recent software programs are comparable with the conventional human scoring method regarding detectability of the radiographic progression of RA. Thus, automatic and accurate selection of relevant images (e.g. hand images) among radiographic images of various body parts is necessary for serial analysis on a large scale. OBJECTIVE: In this study we examined whether deep learning can select target images from a large number of stored images retrieved from a picture archiving and communication system (PACS) including miscellaneous body parts of patients. METHODS: We selected 1,047 X-ray images including various body parts and divided them into two groups: 841 images for training and 206 images for testing. The training images were augmented and used to train a convolutional neural network (CNN) consisting of 4 convolution layers, 2 pooling layers and 2 fully connected layers. After training, we created software to classify the test images and examined the accuracy. RESULTS: The image extraction accuracy was 0.952 and 0.979 for unilateral hand and both hands, respectively. In addition, all 206 test images were perfectly classified into unilateral hand, both hands, and the others. CONCLUSIONS: Deep learning showed promise to enable efficiently automatic selection of target X-ray images of RA patients.
Deep Learning , Radiographic Image Interpretation, Computer-Assisted/methods , Radiography/methods , Arthritis, Rheumatoid/diagnostic imaging , Hand/diagnostic imaging , Humans
OBJECTIVES: This study examines the structure of the process that public health professionals (PHPs) use to organize preventive care groups for older adults and the elements that strengthen this process. DESIGN AND SAMPLE: The study was conducted using a quantitative descriptive design. Anonymous self-administered questionnaires were distributed by mail to 919 PHPs, including nurses and social workers employed by local governments in a Japanese prefecture, who facilitated recreational groups for older adults for the purposes of preventive care. Measures Items related to the process and the awareness of support were based on previous research. The process structure was examined using exploratory factor analysis, while multiple logistic regression analysis was used to study strengthening elements. RESULTS: The process yielded six factors (encouraging clarity with respect to the group's activity policy; creating connections with other resources; fostering independence; encouraging activity evaluation; creating relationships with group members; understanding the strengths and weaknesses of communities and individuals) with a total of 23 items. Two of three indicators of awareness of support were significantly related to the process. CONCLUSIONS: Understanding the importance of strengthening elements might improve support groups for older adults.
Health Personnel , Public Health , Aged , Factor Analysis, Statistical , Humans , Self-Help Groups , Surveys and Questionnaires
