Benjamin Midtvedt defended his Master Thesis on June 15, 2020. Congrats!

Benjamin Midtvedt defended his Master Thesis in Engineering Mathematics and Computer Science at Chalmers University of Technology on 15 June 2020. Congrats!

Screenshot of Benjamin Midtvedt’s Master Thesis defence.
Title: DeepTrack: A comprehensive deep learning framework for digital microscopy

Despite the rapid advancement of deep-learning methods for image analysis, they remain underutilized for the analysis of microscopy images. State of the art methods require expertise in deep-learning to implement, disconnecting the development of new methods from end-users. The packages that are available are typically highly specialized, challenging to reappropriate, and almost impossible to interface with other methods. Finally, training deep-learning models often requires large datasets of manually annotated images, making it prohibitively difficult to procure training data that accurately represents the problem.

DeepTrack is a deep-learning framework targeting optical microscopy, designed to account for each of these issues. Firstly, it is packaged with an easy-to-use graphical user interface, solving standard microscopy problems with no required programming experience. Secondly, it bypasses the need for manually annotated experimental data by providing a comprehensive programming API for creating representative synthetic data, designed to exactly suit the problem. DeepTrack creates physical simulations of samples described by refractive index or fluorophore distributions, using fully customizable optical systems. To accurately represent the data to be analyzed, DeepTrack supports arbitrary optical aberration and experimental noise. Thirdly, many standard deep-learning methods are packaged with DeepTrack, including architectures such as U-NET, and regularization techniques such as augmentations, decreasing the barrier to entry. Finally, the framework is fully modular and easily extendable to implement new methods, providing both longevity and a centralized foundation to deploy new deep-learning solutions.

We demonstrate the versatility of DeepTrack by training networks to solve a broad range of common microscopy problems, including particle tracking, cell-counting in dense biological samples, multi-particle 3-dimensional tracking, and cell segmentation and classification.

Master Programme: Engineering Mathematics and Computer Science
Supervisor: Giovanni Volpe
Examiner: Giovanni Volpe
Opponents: Aykut Argun and Saga Helgadóttir

Time: 15 June 2020, 16:00
Place: Online via Zoom

Tobias Sandström and Lars Jansson defended their Master Thesis on 15 June, 2020. Congrats!

Tobias Sandström and Lars Jansson defended their Master Thesis in Complex Adaptive Systems at Chalmers University of Technology on 15 June 2020. Congrats!

Screenshot of Tobias Sandström and Lars Jansson’s Master Thesis defence.
Title: Graph Convolutional Neural Networks for Brain Connectivity Analysis​​

We explore the strengths and limitations of Graph Convolutional Neural Networks (GCNs) for classification of graph structured data. GCNs differs from regular Artificial Neural Networks (ANNs) in that they operate directly on graph structures by defining convolutional operators in a non-euclidean space. We show that GCNs perform well on graph structured data, where regular ANNs typically fail due to the arbitrary ordering of nodes. Different GCN architectures are examined and compared to simplistic ANNs. Tests are initially performed on simulated data sets with implicit class-dissimilarities in regards to graph structures. We demonstrate that GCNs is vital in accurately classifying the simulated data. Network performance is later evaluated on structured MRI-data, displaying cortical thicknesses for 68 regions in the brain of patients with Alzheimer’s disease and a healthy control group. On the structured MRI-data, both GCNs and regular ANNs are shown to be able classifiers. However, it is crucial for the performance of ANNs that an order of nodes can be imposed on the MRI-data from labeled brain regions.

Supervisors: Jonas Andersson & Alice Deimante Neimantaite, Syntronic AB
Examiner: Giovanni Volpe, Department of Physics, University of Gothenburg
Opponent: Jonathan Bergqvist

Time: 15 June, 2020, 14:00
Place: Online via Zoom

Hillevi Wachtmeister defended her Master Thesis on June 11, 2020. Congrats!

Hillevi Wachmeister defend her Master Thesis in Physics at Chalmers University of Technology on 11 June 2020. Congrats!

Screenshot of Hillevi Wachmeister’s Master Thesis defence.
Title: Tracking marine micro organisms using deep learning

The goal of this project is to develop a software that can be used to study swimming patterns of marine micro organisms. The software is based on a neural network, which is trained to recognize different types of plankton. The predictions from the network are then used to find the positions of the plankton, and then track their movements.

The project is divided into two parts. First, videos containing only one type of plankton, Lingulodinium polyedra and Alexandrium tamarense respectively, are analyzed. A type of neural network, called U-net, is trained to segment the input images into background and plankton sections. From the segmented images, positions can be obtained and then connected to form a trajectory for each plankton. The drift of the plankton movements is calculated and subtracted from the trajectories, and finally the speed and net displacement is calculated. The results from the single plankton experiments are compared to a previous analysis that was made using the algorithmic method TrackMate.

Secondly, videos containing two types of plankton are analyzed. Two experiments are conducted using Strombidium arenicola and Rhodomonas baltica in the first experiment, and Alexandrium tamarense and Rhodomonas baltica in the second. The segmented images, obtained from the U-net, consists of an additional plankton section for the second type of plankton present in the experiment.

The analysis of the single plankton experiments yields longer and fewer trajectories using the U-net method, compared to the previous TrackMate results. This shows that the TrackMate method is losing plankton at more positions, compared to the U-net method. The U-net method is therefore able to track each plankton for a longer time. The multi-plankton experiments proves the network’s ability to distinguish and track multiple plankton at the same time.

Master programme: MPPHYS – Physics
Supervisor: Daniel Midtvedt
Examiner: Giovanni Volpe
Opponent: Frida Eriksson

Date: 11 June 2020, 9:00
Place: Nexus + Online via Zoom

Sofia Lundborg defended her Master Thesis on June 4, 2020. Congrats!

Sofia Lundborg defended her Master Thesis in Complex Adaptive Systems at Chalmers University of Technology on 4 June 2020. Congrats!

Screenshot of Sofia Lundborg’s Master Thesis defence.
Title: Training Binary Deep Neural Networks Using Knowledge Distillation

Binary networks can be used to speed up inference time and make image analysis possible on less powerful devices. When binarizing a network the accuracy drops.
The thesis aimed to investigate how the accuracy of a binary network can be improved by using knowledge distillation.
Three different knowledge distillation methods were tested for various network types. Additionally, different architectures of a residual block in ResNet were suggested and tested. Test on CIFAR10 showed an 1.5% increase in accuracy when using knowledge distillation and an increase of 1.1% when testing on ImageNet dataset. The results indicate that the suggested knowledge distillation method can improve the accuracy of a binary network. Further testing needs to be done to verify the results, especially longer training. However, there is great potential that knowledge distillation can be used to boost the accuracy of binary networks.

Master programme: MPCAS – Complex Adaptive Systems
Supervisor: Giovanni Volpe
Supervisors @ Bit Addict: Karl Svensson, Fredrik Ring and Niclas Wikström
Examiner: Giovanni Volpe
Opponent: Viktor Olsson, Wilhelm Tranheden

Time: June 4, 2020 at 15:00
Place: Online via Zoom

Dennis Kristiansson, Adrian Lundell, Fredrik Meisingseth, David Tonderski defended their Bachelor Thesis. Congrats!

Dennis Kristiansson, Adrian Lundell, Fredrik Meisingseth and David Tonderski defended their Bachelor Thesis at Chalmers University of Technology on 27 May 2020. Congrats!

Title: Deep learning for particle tracking

Abstract: The use of machine learning for classication has in recent years spread into a wide range of disciplines, amongst them the detection of particles for particle tracking on microscopy data. We modified the Python package DeepTrack, which makes use of deep learning to detect particles, creating a package called U-Track. By using a new network architecture based on a U-Net, better performance and higher computational efficiency than DeepTrack was achieved on images with multiple particles. Furthermore, functionality to track detected particles over series of frames was developed. The application of U-Track on experimental data from two-dimensional flow nanometry produced tracks consistent with theory, as well as tracking larger quantities of particles over longer periods of time compared to a digital filter based benchmark algorithm.

Supervisors: Daniel Midtvedt, Department of Physics, University of Gothenburg
Examiner: Lena Falk, Department of Physics, University of Gothenburg
Opponents: Patrik Wallin, Isak Pettersson, Alexei Orekhov, Anna Wisakanto

Place: Online Meeting
Time: 27 May, 2020, 9:00


Fatemeh Kalantarifard defended her PhD Thesis on 10 June 2019. Congrats!

Fatemeh Kalantarifard defended her PhD Thesis on 10 June 2019 in the Department of Physics Seminar Room SA-240 – Bilkent University.
Her Ph.D. Thesis Defense was live streamed on 10 June 2019 at 15:30 CEST in the Raven & Fox room.

Assoc. Prof. Ömer Ilday (UNAM, Bilkent University),  Assoc. Prof. Alpan Bek (Middle-East Technical University), Assist. Prof. Burcin Ünlü (Bogazici University), Dr. Seymour Jahangirov (UNAM), Prof. Oguz Gülseren (Bilkent University) and Assist. Prof. Giovanni Volpe (Bilkent University) will be the thesis committee members.

Thesis title: Intra-cavity optical trapping with fiber laser

Thesis abstract: Standard optical tweezers rely on optical forces arising when a focused laser beam interacts with a microscopic particle: scattering forces, pushing the particle along the beam direction, and gradient forces, attracting it towards the high-intensity focal spot. Importantly, the incoming laser beam is not affected by the particle position because the particle is outside the laser cavity. Here, we demonstrate that intra-cavity nonlinear feedback forces emerge when the particle is placed inside the optical cavity, resulting in orders-of-magnitude higher confinement along the three axes per unit laser intensity on the sample. This scheme allows trapping at very low numerical apertures and reduces the laser intensity to which the particle is exposed by two orders of magnitude compared to a standard 3D optical tweezers. These results are highly relevant for many applications requiring manipulation of samples that are subject to photodamage, such as in biophysics and nano-sciences.

Thesis Advisor  Giovanni Volpe, Department of Physics, Bilkent University

Place: Physics Department seminar room (SA240), Bilkent University
Time: 10 June, 2019, 16:30 TRT (Turkey Time)

Place: Meeting room Raven & Fox, Gothenburg University
Time: 10 June, 2019, 15:30 CEST


Martin Selin defended his Master Thesis. Congrats!

Martin Selin defended his Master thesis in Physics at Chalmers University of Technology on 5 June 2019

Title: Growing Artificial Neural Networks. Novel approaches to Deep Learning for Image Analysis and Particle Tracking

Deep-learning has recently emerged as one of the most successful methods for an- alyzing large amounts of data and constructing models from it. It has virtually revolutionized the field of image analysis and the algorithms are now being employed in research field outside of computer science. The methods do however suffer from several drawbacks such as large computational costs.

In this thesis alternative methods for training the networks underlying networks are evaluated based on gradually growing networks during training using layer-by- layer training as well as a method based on increasing network width dubbed breadth training.

These training methods lends themselves to easily implementing networks of tune- able size allowing for choice between high accuracy or fast execution or the construc- tion of modular network in which one can chose to execute only a small part of the network to get a very fast prediction at the cost of some accuracy. The layer-by-layer method is applied to multiple different image analysis tasks and the performance is evaluated and compared to that of regular training. Both the layer by layer training and the breadth training comparable to normal training in performance and in some cases slightly superior while in others slightly inferior. The modular nature of the networks make them suitable for applications within multi-particle tracking.

​Name of the master programme: MPPHYS – Physics
Supervisor: Giovanni Volpe, Department of Physics, University of Gothenburg
Examiner: Giovanni Volpe, Department of Physics, University of Gothenburg
Opponent: Henry Yang, MP Complex Adaptive Systems, Department of Physics, Chalmers University of Technology

Place: Raven & Fox room
Time: 5 June, 2019, 15:00

Adrian Leidegren defended his Master Thesis. Congrats!

Adrian Leidegren defended his Master thesis in Physics at the University of Gothenburg on 5 June 2019

Title: Estimating the validity of synthetic data using neural network ensembles

The use of synthetic data has the potential to yield unlimited amounts of resources for use in training neural networks. This is however contin- gent on finding the right parameters to use with the data-generating system. As a worst-case scenario this would be done by careful guesswork. Herein is presented an alternative that has the potential to automate this work. The Deeptrack system for particle tracking in digital video microscopy was used as a framework, due to its ability to generate synthetic data from a handful of parameters. An ensemble was trained according to one set of parameter values and tested against a set of test data generated by the same parameters except for one, which was made to vary over a wide range. To contrast this, using a new parameter set, another set of test data was generated alongside several ensembles where one parameter was varied for each ensemble’s training data.

It was found that the limiting density of discreet points as a function of the vary- ing parameter had a local minimum around the region where the variable matched the same parameter’s value in the other data set, be it training or testing. This shows the possibility of using ensembles of neural networks to identify the most suitable parameter values in Deeptrack to ensure that the synthetic training data is represen- tative of the laboratory test data. There may also be a wider use case to this technique as a means of estimating confidence in the networks’ predictions.

​Name of the master programme: Physics
Supervisor: Saga Helgadottir, Department of Physics, University of Gothenburg
Examiner: Giovanni Volpe, Department of Physics, University of Gothenburg

Place: Faraday room
Time: 5 June, 2019, 15:00

Theo Berglin & Adam Liberda defended their Master Thesis. Congrats!

Theo Berglin & Adam Liberda defended their Master thesis in Complex Adaptive Systems at Chalmers University of Technology on 31 May 2019

Title: Generation of random connectivity matrices for BRAPH

The proportion of the population suffering from neurodegenerative diseases such as Alzheimer’s and Parkinson’s disease is increasing. Recent studies suggest that graph theory measures can be used as biomarkers in early stages of the diseases enabling researches to study spread and aiding inhibiting drug discovery. BRAPH is an object oriented and easy to use software for analyzing brain connectivity using graph theory. A bottleneck in the analyzis of brain connectivity using graph theory is a degree, strength and weight preserving randomization function. We have developed a new method with a speed improvement in the magnitude of 105 to 106 compared with the original method of Brain Connectivity Toolbox (BCT). The method is working for graphs consisting of up to 105 nodes and is verified to be equally random as the original method of BCT for sparse graphs. A speed improvement in the magnitude of 106 is equal to going from 1000 years to 8 hours.

​Name of the master programme: MPCAS – Complex Adaptive Systems
Supervisor: Giovanni Volpe, Department of Physics, University of Gothenburg
Examiner: Giovanni Volpe, Department of Physics, University of Gothenburg
Opponent: Jens Wilhelmsson, MP Complex Adaptive Systems, Department of Physics, Chalmers University of Technology

Place: Faraday room
Time: 31 May, 2019, 13:00

Kevin Andersson, Sofia Cvetkovic Destouni, Ebba Ekblom, Lilian Hee, Emil Jansson & Thomas Otting defended their Bachelor Thesis. Congrats!

Kevin AnderssonSofia Cvetkovic Destouni, Ebba EkblomLilian HeeEmil JanssonThomas Ottink defended their Bachelor Thesis at Chambers University of Technology on 29 May 2018.

Title: Agenters sökförmåga i komplexa miljöer

Abstract: Tendensen hos en aktiv Brownsk agent att svänga i en viss rikting benämns i denna studie som kiralitet och ger upphov till vad som kallas cirkulär Brownsk rörelse. Denna typ av rörelse förekommer i många både naturliga och tekniska sammanhang och har potentiella applikationer inom bland annat medicin, biologi och robotik. För att undersöka hur cirkulärt Brownska agenters sökförmåga påverkas av kiralitet utförs i detta kandidatarbete en kombination av simuleringar och experiment i olika miljöer. Simuleringarna baseras på en diskretisering av Langevins ekvationer i två rumsdimensioner och experimenten utförs med hjälp av vibrerande mikrorobotar. Studien visar att agenters sökförmåga minskar vid ökande kiralitet i homogen miljö och bestämmer kiralitetsoptimum för sökförmåga i cirkulärt begränsade miljöer. I ett fall där två agenter placeras i en cirkulärt begränsad miljö identifieras effektiva kiralitetskombinationer för korta mötestider samt en möjlig koppling mellan sökförmåga och mötestid.

Supervisors: Alessandro Magazzù & Giovanni Volpe, Department of Physics, University of Gothenburg
Examiner: Lena Falk, Department of Physics, University of Gothenburg
Opponent: Matilda Hanes & Kevin Rylander
Place: FL72
Time: 29 May, 2018, 9:35-10:20