RESUMEN
We present a case of a 42-year-old woman with paraneoplastic anti-N-Methyl-D-Aspartat (NMDA)-receptor encephalitis and concurrent neuroborreliosis that was initially misdiagnosed as post-COVID-19 syndrome. Clinically, the patient presented with a range of chronic and subacute neuropsychiatric symptoms and recalled a tick bite weeks prior to admission. The patient had undergone psychiatric and complementary medical treatments for 1 year before admission and was initially diagnosed with post-COVID-19 syndrome. Admission was performed because of acute worsening with fever, confusion, and unsteady gait. Cerebrospinal fluid (CSF) analysis revealed pleocytosis with elevated borrelia Immunoglobulin M (IgM) and Immunoglobulin M (IgG) CSF/blood antibody indices, indicating acute neuroborreliosis. Anti-NMDA receptor antibodies were identified in the CSF via a cell-based assay and were confirmed by an external laboratory. Other paraneoplastic antibodies were ruled out during in-house examination. Cranial Magnetic resonance imaging (MRI) revealed basal meningitis, rhomb- and limbic encephalitis. A subsequent pelvic Computer tomography (CT) scan identified an ovarian teratoma. The patient's clinical condition improved dramatically with antibiotic treatment and plasmapheresis, the teratoma was surgically removed and she was started on rituximab. Our case highlights that amidst the prevailing focus on COVID-19-related health concerns, other well-established, but rare neurological conditions should not be neglected. Furthermore, our case illustrates that patients may suffer from multiple, concurrent, yet pathophysiologically unrelated neuroinflammatory conditions.
RESUMEN
Foundational models, pretrained on a large scale, have demonstrated substantial success across non-medical domains. However, training these models typically requires large, comprehensive datasets, which contrasts with the smaller and more specialized datasets common in biomedical imaging. Here we propose a multi-task learning strategy that decouples the number of training tasks from memory requirements. We trained a universal biomedical pretrained model (UMedPT) on a multi-task database including tomographic, microscopic and X-ray images, with various labeling strategies such as classification, segmentation and object detection. The UMedPT foundational model outperformed ImageNet pretraining and previous state-of-the-art models. For classification tasks related to the pretraining database, it maintained its performance with only 1% of the original training data and without fine-tuning. For out-of-domain tasks it required only 50% of the original training data. In an external independent validation, imaging features extracted using UMedPT proved to set a new standard for cross-center transferability.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Bases de Datos Factuales , Diagnóstico por Imagen/métodos , Algoritmos , Aprendizaje AutomáticoRESUMEN
The alignment of tissue between histopathological whole-slide-images (WSI) is crucial for research and clinical applications. Advances in computing, deep learning, and availability of large WSI datasets have revolutionised WSI analysis. Therefore, the current state-of-the-art in WSI registration is unclear. To address this, we conducted the ACROBAT challenge, based on the largest WSI registration dataset to date, including 4,212 WSIs from 1,152 breast cancer patients. The challenge objective was to align WSIs of tissue that was stained with routine diagnostic immunohistochemistry to its H&E-stained counterpart. We compare the performance of eight WSI registration algorithms, including an investigation of the impact of different WSI properties and clinical covariates. We find that conceptually distinct WSI registration methods can lead to highly accurate registration performances and identify covariates that impact performances across methods. These results provide a comparison of the performance of current WSI registration methods and guide researchers in selecting and developing methods.