Reliable identification and quantification of neural cells in microscopic images of neurospheres.

Neurosphere cultures consisting of primary human neural stem/progenitor cells (hNPC) are used for studying the effects of substances on early neurodevelopmental processes in vitro. Differentiating hNPCs migrate and differentiate into radial glia, neurons, astrocytes, and oligodendrocytes upon plating on a suitable extracellular matrix and thus model processes of early neural development. In order to characterize alterations in hNPC development, it is thus an essential task to reliably identify the cell type of each migrated cell in the migration area of a neurosphere. To this end, we introduce and validate a deep learning approach for identifying and quantifying cell types in microscopic images of differentiated hNPC. As we demonstrate, our approach performs with high accuracy and is robust against typical potential confounders. We demonstrate that our deep learning approach reproduces the dose responses of well-established developmental neurotoxic compounds and controls, indicating its potential in medium or high throughput in vitro screening studies. Hence, our approach can be used for studying compound effects on neural differentiation processes in an automated and unbiased process.

A representation learning approach for recovering scatter-corrected spectra from Fourier-transform infrared spectra of tissue samples.

Infrared spectra obtained from cell or tissue specimen have commonly been observed to involve a significant degree of scattering effects, often Mie scattering, which probably overshadows biochemically relevant spectral information by a nonlinear, nonadditive spectral component in Fourier transform infrared (FTIR) spectroscopic measurements. Correspondingly, many successful machine learning approaches for FTIR spectra have relied on preprocessing procedures that computationally remove the scattering components from an infrared spectrum. We propose an approach to approximate this complex preprocessing function using deep neural networks. As we demonstrate, the resulting model is not just several orders of magnitudes faster, which is important for real-time clinical applications, but also generalizes strongly across different tissue types. Using Bayesian machine learning approaches, our approach unveils model uncertainty that coincides with a band shift in the amide I region that occurs when scattering is removed computationally based on an established physical model. Furthermore, our proposed method overcomes the trade-off between computation time and the corrected spectrum being biased towards an artificial reference spectrum.

Deep representation learning for domain adaptable classification of infrared spectral imaging data.

MOTIVATION: Applying infrared microscopy in the context of tissue diagnostics heavily relies on computationally preprocessing the infrared pixel spectra that constitute an infrared microscopic image. Existing approaches involve physical models, which are non-linear in nature and lead to classifiers that do not generalize well, e.g. across different types of tissue preparation. Furthermore, existing preprocessing approaches involve iterative procedures that are computationally demanding, so that computation time required for preprocessing does not keep pace with recent progress in infrared microscopes which can capture whole-slide images within minutes. RESULTS: We investigate the application of stacked contractive autoencoders as an unsupervised approach to preprocess infrared microscopic pixel spectra, followed by supervised fine-tuning to obtain neural networks that can reliably resolve tissue structure. To validate the robustness of the resulting classifier, we demonstrate that a network trained on embedded tissue can be transferred to classify fresh frozen tissue. The features obtained from unsupervised pretraining thus generalize across the large spectral differences between embedded and fresh frozen tissue, where under previous approaches separate classifiers had to be trained from scratch. AVAILABILITY AND IMPLEMENTATION: Our implementation can be downloaded from https://github.com/arnrau/SCAE_IR_Spectral_Imaging. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.