Extracting quantitative biological information from brightfield cell images using deep learning on ArXiv

Virtually-stained generated image for lipid-droplet.
Extracting quantitative biological information from brightfield cell images using deep learning
Saga Helgadottir, Benjamin Midtvedt, Jesús Pineda, Alan Sabirsh, Caroline B. Adiels, Stefano Romeo, Daniel Midtvedt, Giovanni Volpe
arXiv: 2012.12986

Quantitative analysis of cell structures is essential for biomedical and pharmaceutical research. The standard imaging approach relies on fluorescence microscopy, where cell structures of interest are labeled by chemical staining techniques. However, these techniques are often invasive and sometimes even toxic to the cells, in addition to being time-consuming, labor-intensive, and expensive. Here, we introduce an alternative deep-learning-powered approach based on the analysis of brightfield images by a conditional generative adversarial neural network (cGAN). We show that this approach can extract information from the brightfield images to generate virtually-stained images, which can be used in subsequent downstream quantitative analyses of cell structures. Specifically, we train a cGAN to virtually stain lipid droplets, cytoplasm, and nuclei using brightfield images of human stem-cell-derived fat cells (adipocytes), which are of particular interest for nanomedicine and vaccine development. Subsequently, we use these virtually-stained images to extract quantitative measures about these cell structures. Generating virtually-stained fluorescence images is less invasive, less expensive, and more reproducible than standard chemical staining; furthermore, it frees up the fluorescence microscopy channels for other analytical probes, thus increasing the amount of information that can be extracted from each cell.

Diagnosis of a genetic disease improves with machine learning, a summary in Swedish published in Fysikaktuellt

Neural networks consist of a series of connected layers of neurons, whose connection weights are adjusted to learn how to determine the diagnosis from the input data.

A summary in Swedish of our previously published article “Virtual genetic diagnosis for familial hypercholesterolemia powered by machine learning” has been published in Fysikaktuellt, the journal of the Swedish Physical Society (Svenska fysikersamfundet).

Article: “Diagnostisering av sjukdomar förbättras med maskininlärning”, Saga Helgadottir, Giovanni Volpe and Stefano Romeo (in Swedish)

Original article: Virtual genetic diagnosis for familial hypercholesterolemia powered by machine learning

Press release: 
Algoritm lär sig diagnostisera genetisk sjukdom (in Swedish)
An algorithm that learns to diagnose genetic disease (in English)

Virtual genetic diagnosis for familial hypercholesterolemia powered by machine learning published in European Journal of Preventive Cardiology

Neural networks consist of a series of connected layers of neurons, whose connection weights are adjusted to learn how to determine the diagnosis from the input data.

Virtual genetic diagnosis for familial hypercholesterolemia powered by machine learning
Anna Pina, Saga Helgadottir, Rosellina Margherita Mancina, Chiara Pavanello, Carlo Pirazzi, Tiziana Montalcini, Roberto Henriques, Laura Calabresi, Olov Wiklund, M Paula Macedo, Luca Valenti, Giovanni Volpe, Stefano Romeo
European Journal of Preventive Cardiology (2020)
doi: https://doi.org/10.1177/2047487319898951

Aims

Familial hypercholesterolemia (FH) is the most common genetic disorder of lipid metabolism. The gold standard for FH diagnosis is genetic testing, available, however, only in selected university hospitals. Clinical scores – for example, the Dutch Lipid Score – are often employed as alternative, more accessible, albeit less accurate FH diagnostic tools. The aim of this study is to obtain a more reliable approach to FH diagnosis by a “virtual” genetic test using machine-learning approaches.

Methods and results

We used three machine-learning algorithms (a classification tree (CT), a gradient boosting machine (GBM), a neural network (NN)) to predict the presence of FH-causative genetic mutations in two independent FH cohorts: the FH Gothenburg cohort (split into training data (N = 174) and internal test (N = 74)) and the FH-CEGP Milan cohort (external test, N = 364). By evaluating their area under the receiver operating characteristic (AUROC) curves, we found that the three machine-learning algorithms performed better (AUROC 0.79 (CT), 0.83 (GBM), and 0.83 (NN) on the Gothenburg cohort, and 0.70 (CT), 0.78 (GBM), and 0.76 (NN) on the Milan cohort) than the clinical Dutch Lipid Score (AUROC 0.68 and 0.64 on the Gothenburg and Milan cohorts, respectively) in predicting carriers of FH-causative mutations.

Conclusion

In the diagnosis of FH-causative genetic mutations, all three machine-learning approaches we have tested outperform the Dutch Lipid Score, which is the clinical standard. We expect these machine-learning algorithms to provide the tools to implement a virtual genetic test of FH. These tools might prove particularly important for lipid clinics without access to genetic testing.