RESUMEN
Pathogenic missense and truncating variants in the GABRG2 gene cause a spectrum of epilepsies, from Dravet syndrome to milder simple febrile seizures. In most cases, pathogenic missense variants in the GABRG2 gene segregate with a febrile seizure phenotype. In this case series, we report a recurrent, de novo missense variant (c0.316 G > A; p.A106T) in the GABRG2 gene that was identified in five unrelated individuals. These patients were described to have a more severe phenotype than previously reported for GABRG2 missense variants. Common features include variable early-onset seizures, significant motor and speech delays, intellectual disability, hypotonia, movement disorder, dysmorphic features and vision/ocular issues. Our report further explores a recurrent pathogenic missense variant within the GABRG2 variant family and broadens the spectrum of associated phenotypes for GABRG2-associated disorders.
Asunto(s)
Anomalías Múltiples/patología , Mutación Missense , Receptores de GABA-A/genética , Índice de Severidad de la Enfermedad , Anomalías Múltiples/genética , Adolescente , Niño , Epilepsia/genética , Epilepsia/patología , Femenino , Humanos , Lactante , Discapacidad Intelectual/genética , Discapacidad Intelectual/patología , Masculino , Trastornos Motores/genética , Trastornos Motores/patología , Trastornos del Movimiento/genética , Trastornos del Movimiento/patología , Hipotonía Muscular/genética , Hipotonía Muscular/patología , Linaje , Fenotipo , Trastornos del Habla/genética , Trastornos del Habla/patologíaRESUMEN
Deep learning has attracted great attention in the medical imaging community as a promising solution for automated, fast and accurate medical image analysis, which is mandatory for quality healthcare. Convolutional neural networks and its variants have become the most preferred and widely used deep learning models in medical image analysis. In this paper, concise overviews of the modern deep learning models applied in medical image analysis are provided and the key tasks performed by deep learning models, i.e. classification, segmentation, retrieval, detection, and registration are reviewed in detail. Some recent researches have shown that deep learning models can outperform medical experts in certain tasks. With the significant breakthroughs made by deep learning methods, it is expected that patients will soon be able to safely and conveniently interact with AI-based medical systems and such intelligent systems will actually improve patient healthcare. There are various complexities and challenges involved in deep learning-based medical image analysis, such as limited datasets. But researchers are actively working in this area to mitigate these challenges and further improve health care with AI.