Abstract
Axial spondyloarthritis (axSpA) is a chronic inflammatory disease of the sacroiliac joints. In this study, we develop a method for detecting bone marrow edema by magnetic resonance (MR) imaging of the sacroiliac joints and a deep-learning network. A total of 815 MR images of the sacroiliac joints were obtained from 60 patients diagnosed with axSpA and 19 healthy subjects. Gadolinium-enhanced fat-suppressed T1-weighted oblique coronal images were used for deep learning. Active sacroiliitis was defined as bone marrow edema, and the following processes were performed: setting the region of interest (ROI) and normalizing it to a size suitable for input to a deep-learning network, determining bone marrow edema using a convolutional-neural-network-based deep-learning network for individual MR images, and determining sacroiliac arthritis in subject examinations based on the classification results of individual MR images. About 70% of the patients and normal subjects were randomly selected for the training dataset, and the remaining 30% formed the test dataset. This process was repeated five times to calculate the average classification rate of the five-fold sets. The gradient-weighted class activation mapping method was used to validate the classification results. In the performance analysis of the ResNet18-based classification network for individual MR images, use of the ROI showed excellent detection performance of bone marrow edema with 93.55 ± 2.19% accuracy, 92.87 ± 1.27% recall, and 94.69 ± 3.03% precision. The overall performance was additionally improved using a median filter to reflect the context information. Finally, active sacroiliitis was diagnosed in individual subjects with 96.06 ± 2.83% accuracy, 100% recall, and 94.84 ± 3.73% precision. This is a pilot study to diagnose bone marrow edema by deep learning based on MR images, and the results suggest that MR analysis using deep learning can be a useful complementary means for clinicians to diagnose bone marrow edema.
Highlights
Spondyloarthritis (SpA) refers to a set of interrelated rheumatic diseases comprising ankylosing spondylitis, psoriatic arthritis, spondylitis with inflammatory bowel disease, and reactive arthritis [1]
The results of all magnetic resonance (MR) slices for a single subject were stored in the form of a vector, and the final diagnosis of active sacroiliitis was determined for the subject through one-dimensional spatial filtering [46]
Since the slices corresponding to the adjacent indexes are the results of scanning adjacent parts, as shown in Figure 6, it is relatively likely that bone marrow edema is simultaneously found in adjacent slices containing the corresponding areas if bone marrow edema occurs in one area of the sacroiliac joints (SIJs)
Summary
Spondyloarthritis (SpA) refers to a set of interrelated rheumatic diseases comprising ankylosing spondylitis, psoriatic arthritis, spondylitis with inflammatory bowel disease, and reactive arthritis [1]. Axial SpA is a chronic inflammatory disease that predominantly presents as inflammation of the sacroiliac joints (SIJs) accompanied by inflammation of the spine and entheses. SpA can be divided into radiographic and non-radiographic axSpA depending on whether definitive structural changes are evident in the SIJs on plain radiographs [2]. Radiographic axSpA indicates an advanced status with bony changes in the SIJs; these bony changes are irreversible, so early diagnosis and early treatment of SpA are important [3]. Diagnosis of sacroiliitis from plain radiographs has several critical limitations, the most important being that diagnosis and grading of structural changes in the SIJs show poor reproducibility and inconsistent outcomes among rheumatologists and radiologists [2,4]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
