Generalized automatic classification of cancer cell migratory patterns
(2021) BMEM01 20212Department of Biomedical Engineering
- Abstract
- Automated fluorescence microscopy is an emerging technique that enables researchers to generate large amounts of data which in turn allows for large scale quantitative studies. In previous small scale quantitative studies, migration modes found by qualitatively observing migrating lung cancer cells have been described. Since such a method starts from qualitative observations it might not generalize to other modes of migration or cells. Furthermore it is not obvious that this approach captures the full complexity of the system. In order to perform a fully quantitative study of cancer cell migration modes large data sets are needed which requires a method that allows us to detect cells of interest in low magnification. This way, larger... (More)
- Automated fluorescence microscopy is an emerging technique that enables researchers to generate large amounts of data which in turn allows for large scale quantitative studies. In previous small scale quantitative studies, migration modes found by qualitatively observing migrating lung cancer cells have been described. Since such a method starts from qualitative observations it might not generalize to other modes of migration or cells. Furthermore it is not obvious that this approach captures the full complexity of the system. In order to perform a fully quantitative study of cancer cell migration modes large data sets are needed which requires a method that allows us to detect cells of interest in low magnification. This way, larger samples can be scanned in an achievable time frame and high magnification data collected only on relevant cells. The aim of this thesis project was therefore to create a pipeline that extracts features from large data sets of low magnification live fluorescence imaging data and uses machine learning to cluster the cells into subpopulations that could be of interest for further study. Additionally, it would be of interest to see if such a method could recover the migration modes found in the previously mentioned small scale quantitative studies.
To run the pipeline a server and a database for storing metadata and analysis results were set up. I developed scripts for automated
analyses such as cell tracking and extraction of morphology data. For the purpose of interaction with the data, a web server serving both a
graphical and a programmatic interface was created.
The created infrastructure was successfully used for post-acquisition
analysis. The clustering methods that I have evaluated tend to cluster dead cells. Further analysis of the other clusters and more data acquired by real-time classification is required for a generalized automatic method. (Less) - Popular Abstract (Swedish)
- En metod för att studera cellers vandringsbeteenden genom automatiserad mikroskopi
Vår kropp byggs upp av flera olika celler som fyller specifika funktioner. Många celler måste kunna förflytta sig för att utföra sina funktioner. Våra
organ formas under fostrets utveckling genom att celler förflyttar sig och immunförsvarets celler vandrar genom kroppen för att jaga och bekämpa
smittämnen. Cellers förflyttning är även en central del av cancersjukdomars förlopp då just cancerns spridning till andra delar av kroppen ofta avgör om den blir livshotande. På grund av den centrala roll som cellvandring har bl.a. i cancer är det viktigt att förstå hur en cells vandringsbeteende förhåller sig till andra egenskaper.
I detta projekt utvecklade... (More) - En metod för att studera cellers vandringsbeteenden genom automatiserad mikroskopi
Vår kropp byggs upp av flera olika celler som fyller specifika funktioner. Många celler måste kunna förflytta sig för att utföra sina funktioner. Våra
organ formas under fostrets utveckling genom att celler förflyttar sig och immunförsvarets celler vandrar genom kroppen för att jaga och bekämpa
smittämnen. Cellers förflyttning är även en central del av cancersjukdomars förlopp då just cancerns spridning till andra delar av kroppen ofta avgör om den blir livshotande. På grund av den centrala roll som cellvandring har bl.a. i cancer är det viktigt att förstå hur en cells vandringsbeteende förhåller sig till andra egenskaper.
I detta projekt utvecklade jag en plattform för att hantera, analysera och visualisera information från bildsekvenser insamlade genom automatiserad
mikroskopi. Jag använde maskininlärning på filmer av tusentals celler för att identifiera cellers olika vandringsbeteenden och studera vad som utmärkte
celler med dessa beteenden.
De analyser jag utförde hittade olika vandringsbeteenden som relaterar till cellernas utseende. Modellerna som utvecklades i det här projektet kan i
framtiden användas för att utföra riktade studier av dessa celler. (Less)
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9066894
- author
- Kumra Ahnlide, Johannes LU
- supervisor
- organization
- course
- BMEM01 20212
- year
- 2021
- type
- H2 - Master's Degree (Two Years)
- subject
- keywords
- cell migration, machine learning, fluorescence microscopy, quantitative microscopy, cell tracking, classification, clustering
- language
- English
- additional info
- 2021-18
- id
- 9066894
- date added to LUP
- 2021-11-11 15:55:20
- date last changed
- 2021-11-11 15:55:20
@misc{9066894,
abstract = {{Automated fluorescence microscopy is an emerging technique that enables researchers to generate large amounts of data which in turn allows for large scale quantitative studies. In previous small scale quantitative studies, migration modes found by qualitatively observing migrating lung cancer cells have been described. Since such a method starts from qualitative observations it might not generalize to other modes of migration or cells. Furthermore it is not obvious that this approach captures the full complexity of the system. In order to perform a fully quantitative study of cancer cell migration modes large data sets are needed which requires a method that allows us to detect cells of interest in low magnification. This way, larger samples can be scanned in an achievable time frame and high magnification data collected only on relevant cells. The aim of this thesis project was therefore to create a pipeline that extracts features from large data sets of low magnification live fluorescence imaging data and uses machine learning to cluster the cells into subpopulations that could be of interest for further study. Additionally, it would be of interest to see if such a method could recover the migration modes found in the previously mentioned small scale quantitative studies.
To run the pipeline a server and a database for storing metadata and analysis results were set up. I developed scripts for automated
analyses such as cell tracking and extraction of morphology data. For the purpose of interaction with the data, a web server serving both a
graphical and a programmatic interface was created.
The created infrastructure was successfully used for post-acquisition
analysis. The clustering methods that I have evaluated tend to cluster dead cells. Further analysis of the other clusters and more data acquired by real-time classification is required for a generalized automatic method.}},
author = {{Kumra Ahnlide, Johannes}},
language = {{eng}},
note = {{Student Paper}},
title = {{Generalized automatic classification of cancer cell migratory patterns}},
year = {{2021}},
}