Category: Presentation

Presentation by H. Klein Moberg at SPIE-ETAI, San Diego, 23 August 2022

A convolutional neural network characterizes the properties of very small biomolecules without requiring prior detection. (Image by H. Klein Moberg.)
Seeing the invisible: deep learning optical microscopy for label-free biomolecule screening in the sub-10 kDa regime
Henrik Klein Moberg, Christoph Langhammer, Daniel Midtvedt, Barbora Spackova, Bohdan Yeroshenko, David Albinsson, Joachim Fritzsche, Giovanni Volpe
Submitted to SPIE-ETAI
Date: 23 August 2022
Time: 9:15 (PDT)

We show that a custom ResNet-inspired CNN architecture trained on simulated biomolecule trajectories surpasses the performance of standard algorithms in terms of tracking and determining the molecular weight and hydrodynamic radius of biomolecules in the low-kDa regime in NSM optical microscopy. We show that high accuracy and precision is retained even below the 10-kDa regime, constituting approximately an order of magnitude improvement in limit of detection compared to current state-of-the-art, enabling analysis of hitherto elusive species of biomolecules such as cytokines (~5-25 kDa) important for cancer research and the protein hormone insulin (~5.6 kDa), potentially opening up entirely new avenues of biological research.

Poster Presentation by F. Skärberg at SPIE-ETAI, San Diego, 22 August 2022

411nm Silica particles inside living cells. (Image by F. Skärberg.)
Holographic characterisation of biological nanoparticles using deep learning
Fredrik Skärberg, Erik Olsén, Benjamin Midtvedt, Emelie V. Wesén, Elin K. Esbjörner, Giovanni Volpe, Fredrik Höök, Daniel Midtvedt
Submitted to SPIE-ETAI
Date: 22 August 2022
Time: 17:30 (PDT)

Optical characterization of nanoparticles in/outside cells is a challenging task, as the scattering from the nanoparticles is distorted by the scattering from the cells. In this work, we demonstrate a framework for optical mass quantification of intra- and extracellular nanoparticles by leveraging a novel deep learning method, LodeSTAR, in combination with off-axis twilight holography. The result provides new means for the exploration of nanoparticle/cell interactions.

Poster Presentation by Z. Korczak at SPIE-ETAI, San Diego, 22 August 2022

Phase-contrast image before virtual staining. (Image by the Authors.)
Dynamic virtual live/apoptotic cell assay using deep learning
Zofia Korczak, Jesús D. Pineda, Saga Helgadottir, Benjamin Midtvedt, Mattias Goksör, Giovanni Volpe, Caroline B. Adiels
Submitted to SPIE-ETAI
Date: 22 August 2022
Time: 17:30 (PDT)

In vitro cell cultures rely on that the cultured cells thrive and behave in a physiologically relevant way. A standard approach to evaluate cells behaviour is to perform chemical staining in which fluorescent probes are added to the cell culture for further imaging and analysis. However, such a technique is invasive and sometimes even toxic to cells, hence, alternative methods are requested. Here, we describe an analysis method for the detection and discrimination of live and apoptotic cells using deep learning. This approach is less labour-intensive than traditional chemical staining procedures and enables cell imaging with minimal impact.

Soft Matter Lab members present at SPIE Optics+Photonics conference in San Diego, 21-25 August 2022

The Soft Matter Lab participates to the SPIE Optics+Photonics conference in San Diego, CA, USA, 21-25 August 2022, with the presentations listed below.

Giovanni Volpe is also co-author of the presentations:

Invited Talk by G. Volpe at UCLA, 19 August 2022

Quantitative Digital Microscopy with Deep Learning
Giovanni Volpe
19 August 2022, 14:40 (PDT)
At the intersection of Photonics, Neuroscience, and AI
Ozcan Lab, UCLA, 19 August 2022

Video microscopy has a long history of providing insights and breakthroughs for a broad range of disciplines, from physics to biology. Image analysis to extract quantitative information from video microscopy data has traditionally relied on algorithmic approaches, which are often difficult to implement, time consuming, and computationally expensive. Recently, alternative data-driven approaches using deep learning have greatly improved quantitative digital microscopy, potentially offering automatized, accurate, and fast image analysis. However, the combination of deep learning and video microscopy remains underutilized primarily due to the steep learning curve involved in developing custom deep-learning solutions. To overcome this issue, we have introduced a software, currently at version DeepTrack 2.1, to design, train and validate deep-learning solutions for digital microscopy. We use it to exemplify how deep learning can be employed for a broad range of applications, from particle localization, tracking and characterization to cell counting and classification. Thanks to its user-friendly graphical interface, DeepTrack 2.1 can be easily customized for user-specific applications, and, thanks to its open-source object-oriented programming, it can be easily expanded to add features and functionalities, potentially introducing deep-learning-enhanced video microscopy to a far wider audience.

Presentation by Murat Nurati Yesibolati, 4 August 2022

Measuring translational and rotational dynamics of colloid nanoparticles at the nanoscale with liquid-phase transmission electron microscopy
Murat Nulati Yesibolati, Assistant professor, Technical University of Denmark
4 August 2022, 10:30 CEST

How nanoparticles (NPs) in a liquid suspension grow, transport, and interact with each other and surrounding interfaces are of fundamental interest in the colloidal matter, biomedical applications, microfluidics, and artificial micro/nanoscopic motors. Traditionally, imaging of such liquid processes has been limited to optical microscopy (OM). Bulk-level methods such as conventional OM and light scattering methods such as dynamic light scattering (DLS) cannot deliver nanometer spatial resolution at the single-particle level. Recently, liquid-phase transmission electron microscopy (LPTEM) [1] has revolutionized the access to the nanoscale, label-free imaging of a wide variety of liquid processes. Typically, the liquid cells used for LPTEM consist of electron-transparent silicon nitride (SiNx) windows suspended on two Si chips, which enclose a liquid sample layer with a thickness ranging from a few hundred nanometers to a couple of microns. With LPTEM, NP dynamics, such as nucleation and growth, self-assembly, and interactions, have been studied with sub-nanometer spatial resolution and millisecond temporal resolution.
We demonstrate how LPTEM can be used to measure the motion of individual NPs and agglomerates. Only at low electron flux do we find that individual NPs exhibit Brownian motion consistent with optical control experiments and theoretical predictions for unhindered passive diffusive motion in bulk liquids [2]. For increasing electron flux, we find increasingly faster than passive motion that still appears effectively Brownian. We discuss the possible origins of this beam–sample interaction. This establishes conditions for the use of LPTEM as a reliable tool for imaging nanoscale hydrodynamics at the nanoscale.

Bio
Murat N. Yesibolati is an Assistant Professor at Technical University of Denmark (DTU), Denmark. Murat defended his Ph.D. thesis titled “Electron holography and particle dynamics in liquid phase transmission electron microscopy” at DTU in 06.2018 under the supervision of Prof. Kristian Mølhave, DTU. Currently, he is focusing on developing a novel nanochannel liquid cell and exploring mass transport in nanochannels using advanced transmission electron microscopy. His research was supported by the Technical University of Denmark, by the Danish Research Council for Technology, grant no. 12-126194, the Advanced Materials for Energy-Water Systems (AMEWS) Center, Office of Science, Basic Energy Sciences, USA, grant number DE-AC02-06CH11357, and the VILLUM foundation, grant number 00028273.

References
[1] de Jonge, N. and F.M. Ross, Electron microscopy of specimens in liquid. Nature Nanotechnology, 2011. 6: p. 695.
[2] Yesibolati, M.N., et al., Unhindered Brownian Motion of Individual Nanoparticles in Liquid-Phase Scanning Transmission Electron Microscopy. Nano Letters, 2020. 20(10): p. 7108-7115.

Place: Nexus
Date: 4 August 2022
Time: 10:30 CEST

Invited Talk by G. Volpe at Nordita, Stockholm, 2 August 2022

Interplay between active particles and their environment
Giovanni Volpe
2 August 2022, 10:30 (CEST)
Nordita workshop: Current and Future Themes in Soft and Biological Active Matter
Albano Building 3
Stockholm, 25 July-19 August 2022

In this seminar, I will present some examples of how the behaviour of active particles can be influenced by their environment. In particular, I’ll show the formation of active molecules and active droploids from passive colloidal building blocks; the emergence of non-Boltzmann statistics and active-depletion forces between plates in an active bath; and the environment topography alters the way to multicellularity in the bacterium Myxococcus xanthus.

Invited Talk by G. Volpe at MoLE Conference 2022, Donostia/San Sebastián, Spain, 27 July 2022

Artificial intelligence in microscopy, photonics, and active matter
Giovanni Volpe
27 July 2022, 12:40 (CEST)
MoLE Conference 2022
Donostia/San Sebastián, Spain, 25-29 July 2022

After a brief overview of artificial intelligence, machine learning and deep learning, I will present a series of recent works in which we have employed deep learning for applications in microscopy, optical tweezers, and active matter. In particular, I will explain how we employed deep learning to enhance digital video microscopy, to perform virtual staining of tissues, to estimate the properties of anomalous diffusion, to characterize microscopic force fields, to improve the calculation of optical forces, and to characterize nanoparticles. Finally, I will provide an outlook on the future for the application of deep learning in these fields.

Invited Talk by G. Volpe at Active and Intelligent Living Matter Conference, Erice, 30 June 2022

Artificial intelligence in microscopy, photonics, and active matter
Giovanni Volpe
30 June 2022, 16:20 (CEST)
Active and Intelligent Living Matter Conference
Erice, Italy, 26 June-1 July 2022

After a brief overview of artificial intelligence, machine learning and deep learning, I will present a series of recent works in which we have employed deep learning for applications in microscopy, optical tweezers, and active matter. In particular, I will explain how we employed deep learning to enhance digital video microscopy, to perform virtual staining of tissues, to estimate the properties of anomalous diffusion, to characterize microscopic force fields, to improve the calculation of optical forces, and to characterize nanoparticles. Finally, I will provide an outlook on the future for the application of deep learning in these fields.

Presentation by Vide Ramsten, 10 June 2022

Observer, Target Generation and Control Design in Robotics
Vide Ramsten
10 June 2022, 15:00 CET

Abstract
In this presentation, three topics related to Control Theory will be discussed together with practical examples from my Bachelor and Master thesis projects. First, the concept of state observers will be presented, where internal system states are estimated based on the measurable outputs of the system. Second, target generation will be discussed, in which the particular output or state trajectory of the system that is desired, is created. Lastly, we consider controller design, where we specify how to create the input given the previously defined parts such as target reference, measurable output and estimated system states. The theory will be applied to two projects. One in which a wheeled robot is developed for guiding purposes, so that the robot can show users the way to certain locations specified by the user. The project gives examples of state observers by localization algorithms, as well as target generation by path planning algorithms. The other example is a robotic testing system for passive prosthesis, where target generation through a motion-capture system is used as a reference for robot motion. A control strategy has been implemented in order to track this reference signal.

Short Bio
Vide Ramsten got his Bachelor degree in Automation and Mechatronic at the Chalmers University of Technology. After that, he continued his studies in a master programme in Systems, Control and Mechatronics at Chalmers. During his master, he did a double degree exchange with the University of Stuttgart, Germany in Engineering Cybernetics. While in Germany, he did a six-month internship at the robotics company BEC Gmbh focused on applications of control in robotics, as well as his master thesis at the Fraunhofer Institute of Manufacturing Engineering and Automation IPA.

Date: 10 June 2022
Time: 11:00
Place: Faraday