RESUMEN
BACKGROUND AND PURPOSE: Cortical amyloid quantification on PET by using the standardized uptake value ratio is valuable for research studies and clinical trials in Alzheimer disease. However, it is resource intensive, requiring co-registered MR imaging data and specialized segmentation software. We investigated the use of deep learning to automatically quantify standardized uptake value ratio and used this for classification. MATERIALS AND METHODS: Using the Alzheimer's Disease Neuroimaging Initiative dataset, we identified 2582 18F-florbetapir PET scans, which were separated into positive and negative cases by using a standardized uptake value ratio threshold of 1.1. We trained convolutional neural networks (ResNet-50 and ResNet-152) to predict standardized uptake value ratio and classify amyloid status. We assessed performance based on network depth, number of PET input slices, and use of ImageNet pretraining. We also assessed human performance with 3 readers in a subset of 100 randomly selected cases. RESULTS: We have found that 48% of cases were amyloid positive. The best performance was seen for ResNet-50 by using regression before classification, 3 input PET slices, and pretraining, with a standardized uptake value ratio root-mean-square error of 0.054, corresponding to 95.1% correct amyloid status prediction. Using more than 3 slices did not improve performance, but ImageNet initialization did. The best trained network was more accurate than humans (96% versus a mean of 88%, respectively). CONCLUSIONS: Deep learning algorithms can estimate standardized uptake value ratio and use this to classify 18F-florbetapir PET scans. Such methods have promise to automate this laborious calculation, enabling quantitative measurements rapidly and in settings without extensive image processing manpower and expertise.
Asunto(s)
Enfermedad de Alzheimer/diagnóstico por imagen , Aprendizaje Profundo , Neuroimagen/métodos , Placa Amiloide/diagnóstico por imagen , Tomografía de Emisión de Positrones/métodos , Anciano , Compuestos de Anilina , Encéfalo/diagnóstico por imagen , Glicoles de Etileno , Femenino , Radioisótopos de Flúor , Humanos , Procesamiento de Imagen Asistido por Computador/métodos , Masculino , RadiofármacosRESUMEN
The bacterium Cupriavidus metallidurans is capable of reducing toxic Au(i/iii)-complexes into metallic gold (Au) nano-particles, thereby mediating the (trans)formation of Au nuggets in Earth surface environments. In this study we describe a novel detoxification pathway, which prevents synergistic copper (Cu)/Au-toxicity. Gold-complexes and Cu-ions exert cooperative toxicity, because cellular uptake of Au(i/iii)-complexes blocks Cu(i) export from the cytoplasm by the Cu-efflux pump CupA. Using a combination of micro-analytical and biochemical methods we show that inducible resistance to these Cu/Au mixtures is mediated by the periplasmic Cu(i)-oxidase CopA, which functions as an oxygen-consuming Au(i)-oxidase. With high Au-complex loads the enzymatic activity of CopA detoxifies the reduction pathway of Au(iii)-complexes via Au(i)-intermediates to Au(0) nanoparticles in the periplasm. Thereby the concentration of highly toxic Au(i) in the cytoplasm is diminished, while allowing direct reduction of Au(iii) to Au nanoparticles in the periplasm. This permits C. metallidurans to thrive in Au-rich environments and biomineralise metallic Au.
Asunto(s)
Biomineralización , Cobre/química , Cupriavidus/efectos de los fármacos , Farmacorresistencia Bacteriana , Oro/química , Inactivación Metabólica , Nanopartículas del Metal/química , Proteínas Bacterianas/metabolismo , Biodegradación Ambiental , Cobre/toxicidad , Cupriavidus/crecimiento & desarrollo , Oro/toxicidadRESUMEN
Cupriavidus metallidurans, a bacterium capable of reductively precipitating toxic, aqueous gold(I/III)-complexes, dominates biofilm communities on gold (Au) grains from Australia. To examine the importance of C. metallidurans biofilms in secondary Au formation, we assessed the biomineralization potential of biofilms growing in quartz-sand-packed columns to periodic amendment with Au(I)-thiosulfate. In these experiments, >99 wt % of Au, was retained compared to <30 wt % in sterilized and abiotic controls. Biomineralization of Au occurred in the presence of viable biofilms via the formation of intra- and extra-cellular spherical nanoparticles, which aggregated into spheroidal and framboidal microparticles of up to 2 µm in diameter. Aggregates of Au formed around cells, eventually encapsulating and ultimately replacing them. These particles were morphologically analogous to Au-particles commonly observed on natural Au grains. Bacterial cells were connected via exopolymer or nanowires to µm-sized, extracellular Au-aggregates, which would intuitively improve the flow of electrons through the biofilm. This study demonstrates the importance of C. metallidurans biofilms for the detoxification of Au-complexes and demonstrates a central role for bacterial biomineralization in the formation of highly pure Au in surface environments.