MRI-based classification of neuropsychiatric systemic lupus erythematosus patients with self-supervised contrastive learning

A bstract Introduction/Purpose Systemic lupus erythematosus (SLE) is a chronic auto-immune disease with a broad spectrum of clinical presentations, including heterogeneous and uncommon neuropsychiatric (NP) syndromes. Accurate diagnosis of neuropsychiatric SLE (NPSLE) is challenging due to lack of clinically useful biomarkers. Despite structural brain abnormalities on MRI in NPSLE being a common finding, a robust link between structural abnormalities and NPSLE has not been established, thus their contribution to the distinction between NPSLE patients and patients in which the NP symptoms are not primarily attributed to SLE is limited. Self-supervised contrastive learning algorithms do not require labels, and have been shown to be useful in classification tasks in rare diseases with limited number of datasets. The aim of our study was to apply self-supervised contrastive learning on T 1 -weighted images acquired from a well-defined cohort of SLE patients to distinguish between SLE patients with NP symptoms due to the disease (NPSLE) or and SLE patients with similar symptoms due to other causes (non-NPSLE). Subjects and Methods 163 patients were included. We used 3T MRI T 1 -weighted images registered to the MNI152 template. The training set comprised 68 non-NPSLE and 34 NPSLE patients. During the training procedure, we applied random geometric transformations (cropping, left-right flipping and rotations) between iterations to enrich our data sets. Our ML pipeline consisted of convolutional base encoder and linear projector. To test the classification task, the projector was removed and one linear layer was measured. We trained the encoder and projector with the Normalized Temperature-scaled Cross Entropy Loss (NT-xent) loss function. We performed a Monte Carlo validation that consisted of 6 repeated random sub-samplings each using a random selection of a small group of samples from each group. Results In the 6 trials described above, between 79% and 83% of the patients were correctly classified as NPSLE or non-NPSLE. For a qualitative evaluation of spatial distribution of the common features found in the NPSLE population, Gradient-weighted Class Activation Maps (Grad-CAM) were examined voxel-wise. Thresholded Grad-CAM maps show areas of common features identified for the NPSLE cohort, with no such communality found for the non-NPSLE group. Discussion/conclusion The self-supervised contrastive learning model was effective in capturing diagnostic brain MRI features from a limited but well-defined cohort of SLE patients with NP symptoms. The interpretation of the Grad-CAM results is not straightforward, but points to involvement of the lateral and third ventricles, periventricular white matter and basal cisterns. We believe that the common features found in the NPSLE population in this study indicate a combination of tissue loss, local atrophy and to some extent that of periventricular white matter lesions, which are commonly found in NPSLE patients and appear hypointense on T 1 -weighted images.