CLASSIFICATION OF PSORIATIC ARTHRITIS, SERONEGATIVE RHEUMATOID ARTHRITIS, AND SEROPOSITIVE RHEUMATOID ARTHRITIS USING DEEP LEARNING ON MAGNETIC RESONANCE IMAGING

Folle L, Bayat S, Kleyer A, Fagni F, Kapsner L, Schlereth M, Meinderink T, Breininger K, Tascilar K, Krönke G, Uder M, Sticherling M, Bickelhaupt S, Maier A, Roemer F, Simon D, Schett G (2022)

Publication Language: English

Publication Type: Conference contribution, Abstract of lecture

Publication year: 2022

Publisher: BMJ Publishing Group

Series: Annals of Rheumatic Disease

Book Volume: 81

Pages Range: 194

Conference Proceedings Title: Supplement 1

Event location: Kopenhagen

URI: https://ard.bmj.com/content/81/Suppl_1/194.2

DOI: 10.1136/annrheumdis-2022-eular.966

Open Access Link: https://ard.bmj.com/content/81/Suppl_1/194.2

Abstract

Background: While MRI evaluation of joints has been primarily used to quantify inflammation at a cross-sectional and longitudinal level, less is known about the potential of MRI in distinguishing different patterns of inflammation in the various forms of arthritis.

Objectives: To evaluate (i) whether deep learning using neural networks can be trained to distinguish between seropositive rheumatoid arthritis (RA+), seronegative RA (RA-), and psoriatic arthritis (PsA) based on structural inflammatory patterns on hand magnetic resonance imaging and (ii) to assess if psoriasis patients with subclinical inflammation fit into such patterns.

Methods: ResNet 3D [1] neural networks were trained to distinguish (i) RA+ vs. PsA, (ii) RA- vs. PsA and (iii) RA+ vs. RA- with respect to hand MRI data. Diagnosis of patients was determined using the following guidelines: ACR/EULAR 2010 [2] for RA and CASPAR [3] for PsA. Results from T1 coronal, T2 coronal, T1 coronal and axial fat suppressed contrast-enhanced (CE) and T2 fat suppressed axial sequences were used. The performance of such trained networks was analyzed by the area-under-the-receiver-operating-characteristic curve (AUROC) with and without imputation of demographic and clinical parameters ( Figure 1A ). Additionally, the trained networks were applied to psoriasis patients without clinical signs of PsA.

Results: MRI scans from 649 patients (135 RA-, 190 RA+, 177 PsA, 147 psoriasis) were included ( Table 1 ). The AUROC for differentiation between disease entities was 75% (SD 3%) for RA+ vs. PsA, 74% (SD 8%) for RA- vs. PsA, and 67% (6%) for RA+ vs. RA-. All MRI sequences were relevant for classification, however, when deleting CE sequences, the loss of performance was only marginal. The addition of patient-specific data to the networks did not provide significant improvements. Increasing amounts of training data demonstrated improved performance of the networks ( Figure 1B ). Psoriasis patients were mostly assigned to PsA by the neural networks, suggesting that PsA-like MRI pattern may be present early in the course of psoriatic disease.

Conclusion: Deep learning can be successfully applied to differentiate MRI inflammatory patterns related to RA+, RA-, and PsA. Early changes in psoriasis patients can be recognized by neural networks and are characterized by a pattern that allowed the networks to classify them as PsA.

Authors with CRIS profile

How to cite

APA:

Folle, L., Bayat, S., Kleyer, A., Fagni, F., Kapsner, L., Schlereth, M.,... Schett, G. (2022, June). CLASSIFICATION OF PSORIATIC ARTHRITIS, SERONEGATIVE RHEUMATOID ARTHRITIS, AND SEROPOSITIVE RHEUMATOID ARTHRITIS USING DEEP LEARNING ON MAGNETIC RESONANCE IMAGING. Paper presentation at EULAR Congress, Kopenhagen, DK.

MLA:

Folle, Lukas, et al. "CLASSIFICATION OF PSORIATIC ARTHRITIS, SERONEGATIVE RHEUMATOID ARTHRITIS, AND SEROPOSITIVE RHEUMATOID ARTHRITIS USING DEEP LEARNING ON MAGNETIC RESONANCE IMAGING." Presented at EULAR Congress, Kopenhagen Ed. Prof Josef Smolen, BMJ Publishing Group, 2022.

BibTeX: Download