diplomsko delo
Klemen Jan Enova (Author), Matija Marolt (Mentor), Manca Žerovnik (Co-mentor)

Abstract

Celični predelki se lahko razlikujejo po morfologiji. Mitohondriji znotraj evkariontskih celic, na katere se bomo osredotočili v tem delu, so lahko razvejani ali pa se med seboj dotikajo. Končni cilj te diplomske naloge je klasifikacija morfologije mitohondrijev. Ker je iz surovih podatkov o obliki težko pridobiti predstavitev oblike, ki bi dobro opisala njeno morfologijo, smo se obrnili k abstrakciji oblik. Abstrakcija obliko opiše z majhnim številom geometrijskih primitivov. Ocenili smo tri metode abstrakcije oblik s pomočjo globokega učenja. Te se razlikujejo po tipu vhoda, načinu ocenjevanja kvalitete abstrakcije in načinu napovedi števila primitivov. Z modifikacijo najboljše metode smo dosegli dobro kvaliteto abstrakcije. Nato smo opravili klasifikacijo morfologije na podlagi razdalje med vektorji parametrov abstrakcij. Klasifikacija ni bila zadovoljiva. Tudi na razsevnem diagramu, ki smo ga pridobili z vložitvijo razdalj, je bilo razvidno, da razdalje slabo ločujejo mitohondrije z različno morfologijo. Po močnejših metodah strojnega učenja pa nismo mogli poseči zaradi pomanjkanja mitohondrijev z označeno morfologijo.

Keywords

celični predelki;volumetrični podatki;abstrakcija oblik;konvolucijske nevronske mreže;računalništvo in informatika;univerzitetni študij;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [K. J. Enova]
UDC: 004.8: 576.311.347(043.2)
COBISS: 148016643 Link will open in a new window
Views: 35
Downloads: 8
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Deep learning for shape abstraction of cellular compartments
Secondary abstract: Cell compartments can vary in morphology. Mitochondria within eukaryotic cells, the focus of this thesis, can be branched or touch each other. Our objective is the classification of mitochondrial morphology. Since it is difficult to obtain a representation of the raw shape that would describe its morphology well, we turned to shape abstraction. Abstraction describes a shape with a small set of geometric primitives. We evaluated three shape abstraction methods that utilize deep learning. These differ in the type of input, the method of evaluating abstraction quality and in how the number of primitives is predicted. By modifying the best performing method, we achieved good abstraction quality. We then performed morphology classification based on the distance between vectors of abstraction parameters. The classification was not satisfactory. We also showed that these distances poorly separate mitochondria with different morphologies by embedding the distances and plotting the embeddings on a scatter plot. We were unable to perform classification with more powerful machine learning methods due to a lack of mitochondria with labelled morphology.
Secondary keywords: cell compartments;mitochondria;volumetric data;shape abstraction;convolutional neural networks;computer science;computer and information science;diploma;Globoko učenje (strojno učenje);Nevronske mreže (računalništvo);Mitohondriji;Računalništvo;Univerzitetna in visokošolska dela;
Type (COBISS): Bachelor thesis/paper
Study programme: 1000468
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 77 str.
ID: 18275606