![mrxiv gitx mrxiv gitx](https://i.pinimg.com/originals/e8/84/cc/e884ccfbbf94ff552573d24cc43c594f.png)
Neural networks can be successfully trained to distinguish MRI inflammation related to seropositive RA, seronegative RA, and PsA. Psoriasis patients were mostly assigned to PsA by the neural networks, suggesting that a PsA-like MRI pattern may be present early in the course of psoriatic disease. The addition of demographic and clinical data to the networks did not provide significant improvements for classification. All MRI sequences were relevant for classification, however, when deleting contrast agent-based sequences the loss of performance was only marginal. MRI scans from 649 patients (135 seronegative RA, 190 seropositive RA, 177 PsA, 147 psoriasis) were fed into ResNet neural networks. Additionally, the trained networks were applied to psoriasis patients without clinical arthritis. The performance of such trained networks was analyzed by the area-under-the-receiver-operating-characteristic curve (AUROC) with and without presentation of demographic and clinical parameters. Results from T1 coronal, T2 coronal, T1 coronal and axial fat suppressed contrast-enhanced (CE) and T2 fat suppressed axial sequences were used. seronegative RA with respect to hand MRI data. ResNet neural networks were utilized to compare (i) seropositive RA vs. To evaluate whether neural networks can distinguish between seropositive rheumatoid arthritis (RA), seronegative RA and psoriatic arthritis (PsA) based on inflammatory patterns from hand MRI and to test how psoriasis patients with subclinical inflammation fit into such patterns. 8 Department of Radiology, Boston University School of Medicine (BUSM), Boston, MA, USA.7 Department of Dermatology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, Germany.6 Department of Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.5 Medical Center for Information and Communication Technology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, Germany.4 Institute of Radiology, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, Germany.3 Deutsches Zentrum für Immuntherapie (DZI), Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and Universitätsklinikum Erlangen, Erlangen, Germany.2 Department of Internal Medicine 3, Friedrich-Alexander-University Erlangen-Nürnberg (FAU) and, Universitätsklinikum Erlangen, Erlangen, Germany.1 Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Erlangen, Germany.