Concurrent NMDAR and GFAP Antibody Encephalitis During Pregnancy.

Anti-N-methyl-D-aspartate receptor (NMDAR) encephalitis is an autoimmune antibody encephalitis, commonly affecting young women with comorbid ovarian teratoma. It typically presents with alteration of consciousness, psychosis, movement disorders eventually deteriorating with seizures, dysautonomia and central hypoventilation requiring critical level of care that may last weeks to months. Removal of teratoma and immunosuppressant therapy support can led to a dramatic recovery.To our knowledge, this is the first illustrated case in the literature of a pregnant woman presenting with concurrent autoimmune NMDAR and anti-glial gibrillary acidic protein(GFAP) antibody encephalitis in the setting of an ovarian teratoma. Despite the teratoma removal and receiving various forms of immunosuppressant therapy, a meaningful neurological improvement was observed following the delivery. After a prolonged hospitalisation and recovery period, the patient and her offspring made an excellent recovery highlighting the significance of early diagnosis and management.

Combating data incompetence in pollen images detection and classification for pollinosis prevention.

Automatic pollen images recognition is crucial for pollinosis symptoms prevention and treatment. The problem of pollen recognition can be efficiently solved using deep learning, however neural networks require tens of thousands of images to generalize. At the same time, the existing open pollen images datasets are very small. In this paper, we present a novel open pollen dataset annotated for both detection and classification tasks. Based on our dataset we study learning from a small data using different state-of-the-art approaches. For the detection task we propose to use our new Bayesian RetinaNet network, which models aleatoric uncertainty. We compare it with the baseline RetinaNet and demonstrate that our model allows for higher detection precision. For the classification task we compare the impact of pre-training on the synthetic images from generative adversarial networks (GANs) and metric-based few-shot learning. Namely, we pre-trained our small convolutional neural network and Siamese neural network classifiers on synthetic pollen images generated by two GANs: StyleGAN and Self-attention GAN. The best classifier is the convolutional neural network pre-trained on StyleGAN images. Our best models achieved 96.3% of mean average precision for the detection task and 97.7% of F1 measure for the classification task on 13 pollen plant species. We have implemented the best models in our pollen recognition web service, which is available for palynologists on request.