An algorithm that learns to diagnose a genetic disease

Researchers at the University of Gothenburg, together with researchers from Portugal, have now found a way to estimate the probability that a patient will suffer from a common genetic disease by training an algorithm using patient data. Continue reading (in English)

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

Article: Virtual genetic diagnosis for familial hypercholesterolemia powered by machine learning

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.

DeepTrack selected by Optics & Photonics News as one of the most exciting optics discoveries in 2019

Optics & Photonics News has picked Saga Helgadóttir and Aykut Argun’s work on deep learning for particle tracking (DeepTrack) as a top break-through of the year.

“This has been a really good year for me, research-wise. My publication, presenting a new AI method, garnered a lot of attention,” says Saga Helgadóttir, PhD at the Department of Physics.

The research article in question, which is now included in Optics & Photonics News’ best-of-2019 list, identifies a new way of implementing neural networks and machine learning in order to track particle motion and study surrounding microenvironments.

After the publication in mid-April, Saga Helgadóttir was contacted by both national and international press to talk about her discoveries. She has also been invited to visit research groups abroad and was a speaker at the AI in Health and Health in AI conference held in Gothenburg in August.

Currently, Saga Helgadottir is collaborating with a group of scientists at Sahlgrenska’s Wallenberg Laboratory. They are working on new ways of using deep learning in the medical field.

“I started my PhD research studying bio-hybrid microswimmers, but ended up more within the area of artificial intelligence and optics. I like this work a lot, and the positive response to my publication earlier this year has allowed me to establish myself in the AI-field.”

Text: Carolina Svensson

List of highlighted research from 2019: Optics in 2019

Saga Helgadottir’s featured summary: Deep Learning for Particle Tracking

Original press release about the research: She has discovered a new method of using AI

Saga Helgadottir interviewed by Curie, a magazine issued by the Swedish Research Council

Saga Helgadottir discussed her research with Curie, a magazine issued by the Swedish Research Council. The article gives examples of how AI is used in many research disciplines. Read the article on Curie’s webpage here.

Presentation by Saga Helgadottir at the CECAM Workshop “Active Matter and Artificial Intelligence”, Lausanne, Switzerland, 30 September 2019

Digital video microscopy enhanced by deep learning

Saga Helgadottir, Aykut Argun & Giovanni Volpe
CECAM Workshop “Active Matter and Artificial Intelligence”, Lausanne, Switzerland
30 September 2019

Single particle tracking is essential in many branches of science and technology, from the measurement of biomolecular forces to the study of colloidal crystals. Standard methods rely on algorithmic approaches; by fine-tuning several user-defined parameters, these methods can be highly successful at tracking a well-defined kind of particle under low-noise conditions with constant and homogenous illumination. Here, we introduce an alternative data-driven approach based on a convolutional neural network, which we name DeepTrack. We show that DeepTrack outperforms algorithmic approaches, especially in the presence of noise and under poor illumination conditions. We use DeepTrack to track an optically trapped particle under very noisy and unsteady illumination conditions, where standard algorithmic approaches fail. We then demonstrate how DeepTrack can also be used to track multiple particles and non-spherical objects such as bacteria, also at very low signal-to-noise ratios. In order to make DeepTrack readily available for other users, we provide a Python software package, which can be easily personalized and optimized for specific applications.

Saga Helgadottir, Aykut Argun & Giovanni Volpe, Optica 6(4), 506—513 (2019)
doi: 10.1364/OPTICA.6.000506
arXiv: 1812.02653
GitHub: DeepTrack

03:40 PM–04:00 PM, Monday, September 30, 2019

Presentation by Saga Helgadottir at the AI for Health and Healthy AI conference, Gothenburg, Sweden, 30 August 2019

Digital video microscopy enhanced by deep learning

Saga Helgadottir, Aykut Argun & Giovanni Volpe
AI for Health and Healthy AI conference, Gothenburg, Sweden
30 August 2019

Single particle tracking is essential in many branches of science and technology, from the measurement of biomolecular forces to the study of colloidal crystals. Standard methods rely on algorithmic approaches; by fine-tuning several user-defined parameters, these methods can be highly successful at tracking a well-defined kind of particle under low-noise conditions with constant and homogenous illumination. Here, we introduce an alternative data-driven approach based on a convolutional neural network, which we name DeepTrack. We show that DeepTrack outperforms algorithmic approaches, especially in the presence of noise and under poor illumination conditions. We use DeepTrack to track an optically trapped particle under very noisy and unsteady illumination conditions, where standard algorithmic approaches fail. We then demonstrate how DeepTrack can also be used to track multiple particles and non-spherical objects such as bacteria, also at very low signal-to-noise ratios. In order to make DeepTrack readily available for other users, we provide a Python software package, which can be easily personalized and optimized for specific applications.

Friday, August 30, 2019

Saga Helgadottir, Aykut Argun & Giovanni Volpe, Optica 6(4), 506—513 (2019)
doi: 10.1364/OPTICA.6.000506
arXiv: 1812.02653
GitHub: DeepTrack

Invited Seminar by Saga Helgadottir at the Max Planck Institute for the Science of Light, 10 May 2019

Digital video microscopy enhanced by deep learning

Saga Helgadottir
Sandoghdar Division, Max Planck Institute for the Science of Light, Erlangen, Germany
10 May 2019

Single particle tracking is essential in many branches of science and technology, from the measurement of biomolecular forces to the study of colloidal crystals. Standard methods rely on algorithmic approaches; by fine-tuning several user-defined parameters, these methods can be highly successful at tracking a well-defined kind of particle under low-noise conditions with constant and homogenous illumination. Here, we introduce an alternative data-driven approach based on a convolutional neural network, which we name DeepTrack. We show that DeepTrack outperforms algorithmic approaches, especially in the presence of noise and under poor illumination conditions. We use DeepTrack to track an optically trapped particle under very noisy and unsteady illumination conditions, where standard algorithmic approaches fail. We then demonstrate how DeepTrack can also be used to track multiple particles and non-spherical objects such as bacteria, also at very low signal-to-noise ratios. In order to make DeepTrack readily available for other users, we provide a Python software package, which can be easily personalized and optimized for specific applications.

Saga Helgadottir, Aykut Argun & Giovanni Volpe, Optica 6(4), 506—513 (2019)
doi: 10.1364/OPTICA.6.000506
arXiv: 1812.02653
GitHub: DeepTrack

Presentation by Saga Helgadottir at the OSA Biophotonics Congress, Tucson, 16 Apr 2019

Digital video microscopy enhanced by deep learning

Saga Helgadottir, Aykut Argun & Giovanni Volpe
OSA Biophotonics Congress, Tucson (AZ), USA
16 April 2019

Single particle tracking is essential in many branches of science and technology, from the measurement of biomolecular forces to the study of colloidal crystals. Standard methods rely on algorithmic approaches; by fine-tuning several user-defined parameters, these methods can be highly successful at tracking a well-defined kind of particle under low-noise conditions with constant and homogenous illumination. Here, we introduce an alternative data-driven approach based on a convolutional neural network, which we name DeepTrack. We show that DeepTrack outperforms algorithmic approaches, especially in the presence of noise and under poor illumination conditions. We use DeepTrack to track an optically trapped particle under very noisy and unsteady illumination conditions, where standard algorithmic approaches fail. We then demonstrate how DeepTrack can also be used to track multiple particles and non-spherical objects such as bacteria, also at very low signal-to-noise ratios. In order to make DeepTrack readily available for other users, we provide a Python software package, which can be easily personalized and optimized for specific applications.

Session: Biological Applications
10:30 AM–12:00 AM, Tuesday, April 16, 2019

More information can be found on the link: https://www.osapublishing.org/abstract.cfm?uri=OMA-2019-AT2E.5

 

Digital Video Microscopy Enhanced by Deep Learning published in Optica

Digital video microscopy enhanced by deep learning

Digital video microscopy enhanced by deep learning
(Cover article)
Saga Helgadottir, Aykut Argun & Giovanni Volpe
Optica 6(4), 506—513 (2019)
doi: 10.1364/OPTICA.6.000506
arXiv: 1812.02653
GitHub: DeepTrack

Single particle tracking is essential in many branches of science and technology, from the measurement of biomolecular forces to the study of colloidal crystals. Standard methods rely on algorithmic approaches; by fine-tuning several user-defined parameters, these methods can be highly successful at tracking a well-defined kind of particle under low-noise conditions with constant and homogenous illumination. Here, we introduce an alternative data-driven approach based on a convolutional neural network, which we name DeepTrack. We show that DeepTrack outperforms algorithmic approaches, especially in the presence of noise and under poor illumination conditions. We use DeepTrack to track an optically trapped particle under very noisy and unsteady illumination conditions, where standard algorithmic approaches fail. We then demonstrate how DeepTrack can also be used to track multiple particles and non-spherical objects such as bacteria, also at very low signal-to-noise ratios. In order to make DeepTrack readily available for other users, we provide a Python software package, which can be easily personalized and optimized for specific applications.

Featured in :
Deep Learning for Particle Tracking”, Optics & Photonics News (December 1, 2019)

Video 1:

Video 2:

Video 3:

Video 4:

Video 5:

Video 6:

Video 7:

Video 8:

Saga Helgadottir joins the Soft Matter Lab

Saga Helgadottir joins the Soft Matter Lab on 28 November 2017 as a PhD student at the Physics Department of the University of Gothenburg.

She has a Master degree in Physics from Chalmers University of Technology with a Master thesis on the study of the effect of plasma on biofilms.

She will work on he PhD thesis on the realisation of hybrid microswimmers and the study of bacterial dynamics in complex and crowded environments.