A national centre of pharmaceutical drug research

Wieslander, Håkan

Application, Optimisation and Evaluation of Deep Learning for Biomedical Imaging

Uploaded full-text To DiVA

Lindberg, Frida A.

The Biological Importance of the Amino Acid Transporter SLC38A10: Characterization of a Knockout Mouse

Uploaded full-text To DiVA

Wieslander, Håkan

Application, Optimisation and Evaluation of Deep Learning for Biomedical Imaging

Uploaded full-text To DiVA

Lindberg, Frida A.

The Biological Importance of the Amino Acid Transporter SLC38A10: Characterization of a Knockout Mouse

Uploaded full-text To DiVA

Wieslander, Håkan

Application, Optimisation and Evaluation of Deep Learning for Biomedical Imaging

Abstract

Microscopy imaging is a powerful technique when studying biology at a cellular and sub-cellular level. When combined with digital image analysis it creates an invaluable tool for investigating complex biological processes and phenomena. However, imaging at the cell and sub-cellular level tends to generate large amounts of data which can be difficult to analyse, navigate and store. Despite these difficulties, large data volumes mean more information content which is beneficial for computational methods like machine learning, especially deep learning. The union of microscopy imaging and deep learning thus provides numerous opportunities for advancing our scientific understanding and uncovering interesting and useful biological insights.

The work in this thesis explores various means for optimising information extraction from microscopy data utilising image analysis with deep learning. The focus is on three different imaging modalities: bright-field; fluorescence; and transmission electron microscopy. Within these modalities different learning-based image analysis and processing techniques are explored, ranging from image classification and detection to image restoration and translation. 

The main contributions are: (i) a computational method for diagnosing oral and cervical cancer based on smear samples and bright-field microscopy; (ii) a hierarchical analysis of whole-slide tissue images from fluorescence microscopy and introducing a confidence based measure for pixel classifications; (iii) an image restoration model for motion-degraded images from transmission electron microscopy with an evaluation of model overfitting on underlying textures; and (iv) an image-to-image translation (virtual staining) of cell images from bright-field to fluorescence microscopy, optimised for biological feature relevance. 

A common theme underlying all the investigations in this thesis is that the evaluation of the methods used is in relation to the biological question at hand.

Uploaded full-text To DiVA

Lindberg, Frida A.

The Biological Importance of the Amino Acid Transporter SLC38A10: Characterization of a Knockout Mouse

Abstract

The biggest group of transporters, the solute carriers (SLCs), has more than 400 members, and about 30% of these are still orphan. In order to decipher their biological function and possible role in disease, there is a need for characterization of these. Around 25% of SLCs are estimated to have amino acids as substrates, including transporters belonging to the SLC38 family. The SLC38 members are sometimes referred to their alternative name: sodium-coupled neutral amino acid transporters (SNATs). One of these transporters, SNAT10 (or SLC38A10), has been characterized as a bidirectional transporter of glutamate, glutamine, alanine and aspartate, as well as having an efflux of serine, and is ubiquitously expressed in the body. However, its biological importance is not yet understood. The aim with this thesis was to characterize a mouse model deficient in SNAT10 protein in order to find the biological importance of this transporter. In paper I, this is done by using a series of behavioral tests, including the open field test, elevated plus maze, rotarod and Y-maze, among others. The SNAT10 knockout mouse was found to have an increased risk-taking behavior, but no motor or spatial working memory impairments. Furthermore, the knockout mouse was found to have a decreased body weight. In paper II, an additional behavioral characterization was performed by using the multivariate concentric square field™ (MCSF) test. The MCSF test is an arena with different zones associated to different behavioral traits, which generates a behavioral profile depending on where the mouse spends its time. The result from this test implies that the SNAT10 deficient mouse has a lower explorative behavior than its wild type littermates. In paper III, gene expression was studied in whole brain and some genes related to cell cycle regulation and p53 expression were found to be differentially expressed in the knockout brain. Additional gene expression was studied in kidney, liver, lung and muscle, but no changes were found. Plasma levels of histidine and threonine were altered in males, but no altered amino acid levels were found in knockout females, suggesting a possible sex-specific effect. These studies together imply that SNAT10 might be involved in processes related to risk-taking and explorative behavior in the open field and MCSF tests. SNAT10 deficiency also affected amino acid levels in plasma, indicating a disrupted amino acid homeostasis.

Uploaded full-text To DiVA

Wieslander, Håkan

Application, Optimisation and Evaluation of Deep Learning for Biomedical Imaging

Uploaded full-text To DiVA

Lindberg, Frida A.

The Biological Importance of the Amino Acid Transporter SLC38A10: Characterization of a Knockout Mouse

Uploaded full-text To DiVA