Deep Learning for Estimating Synaptic Health of Primary Neuronal Cell Culture

Abstract

Understanding the morphological changes of primary neuronal cells induced by chemical compounds is essential for drug discovery. Using the data from a single high-throughput imaging assay, a classification model for predicting the biological activity of candidate compounds was introduced. The image recognition model which is based on deep convolutional neural network (CNN) architecture with residual connections achieved accuracy of 99.6$\%$ on a binary classification task of distinguishing untreated and treated rodent primary neuronal cells with Amyloid-${\beta }_{(25-35)}$.

arXiv comment11 pages, 5 figures

References in corpus (14)

• Improving neural networks by preventing co-adaptation of feature detectors
• Machine learning methods for histopathological image analysis
• A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay
• Searching for Activation Functions
• Deep learning-based virtual histology staining using auto-fluorescence of label-free tissue
• Detecting Cancer Metastases on Gigapixel Pathology Images
• Sparse arrays of signatures for online character recognition
• Rough paths, Signatures and the modelling of functions on streams
• Learning from the past, predicting the statistics for the future, learning an evolving system
• Extracting information from the signature of a financial data stream
• Using path signatures to predict a diagnosis of Alzheimer's disease
• Application of the Signature Method to Pattern Recognition in the CEQUEL Clinical Trial
• Detecting early signs of depressive and manic episodes in patients with bipolar disorder using the signature-based model
• Derivatives pricing using signature payoffs