Artificial Intelligence Quantification of Enhanced Synovium Throughout the Entire Hand in Rheumatoid Arthritis on Dynamic Contrast-Enhanced MRI.

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.

Fully automatic quantification for hand synovitis in rheumatoid arthritis using pixel-classification-based segmentation network in DCE-MRI.

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.

A deep registration method for accurate quantification of joint space narrowing progression in rheumatoid arthritis.

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.

Quantification of Joint Space Width Difference on Radiography Via Phase-Only Correlation (POC) Analysis: a Phantom Study Comparing with Various Tomographical Modalities Using Conventional Margin-Contouring.

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.

Quick and accurate selection of hand images among radiographs from various body parts using deep learning.

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.