diplomsko delo
Eva Boneš (Author), Matija Marolt (Mentor), Samo Hudoklin (Co-mentor)

Abstract

Golgijev aparat (GA) je organel, ki ga najdemo v evkariontskih celicah. Zaradi njegove strukture in do nedavnega pomanjkanja ustreznih pristopov je še vedno precej slabo raziskan. Pri nadaljnjem raziskovanju bi med drugim pomagala tudi informacija o njegovi 3D organizaciji in razporeditvi v celici. Ker je ročno segmentiranje velikega števila GA-jev časovno zelo zahtevno in je njegova kvaliteta odvisna od sposobnosti označevalca, je v diplomski nalogi predstavljen pristop k avtomatski segmentaciji GA-jev v volumetričnih podatkih elektronske mikroskopije. Predlagan je cevovod, ki sestoji iz nevronske mreže, naučene na grobih segmentacijah, aktivnih kontur za natančnejšo segmentacijo in odstranjevanja napačnih označb. Kolikor nam je znano, je to prvi pristop za avtomatsko segmentacijo kompleksnih GA-jev v volumetričnih podatkih. Uporaba grobo označenega zlatega standarda je prihranila 80% časa, potrebnega za ročno označevanje vhodnih podatkov. Metoda je bila ovrednotena na volumetrični učni množici, kjer je pokazala obetavne rezultate - pravilno je bila označena večina GA-jev in sicer z 89% občutljivostjo in 99% specifičnostjo.

Keywords

Golgijev aparat;avtomatska segmentacija;konvolucijske nevronske mreže;aktivne konture;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: [L. Prijatelj]
UDC: 004.8(043.2)
COBISS: 29618179 Link will open in a new window
Views: 833
Downloads: 172
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: Automatic segmentation of the Golgi apparatus in electron microscopy volumetric data
Secondary abstract: The Golgi apparatus (GA) is an organelle found in eukaryotic cells. Due to its complex organization and until recently lack of appropriate approaches GA is still rather poorly researched. Knowledge of its 3D organization and distribution inside complex cells would aid to further understand the role of GA. However, manual segmentation of large volumes is very time consuming and its quality depends on the ability of the human annotator. In the thesis, an approach for automatic segmentation of GAs in electron microscopy volumetric data is proposed. The proposed pipeline consists of a neural network trained on roughly annotated data, active contours for a more precise segmentation, and filtering of false segmentations. To our knowledge, this is the first approach that segments complex GAs in volumetric data automatically. The use of roughly annotated ground truth saved 80% of the time needed for manual annotation of the input data. The method was evaluated on a volumetric dataset and it showed promising results - it was able to annotate a wast majority of GAs with 89% sensitivity and 99% specificity.
Secondary keywords: Golgi apparatus;automatic segmentation;convolutional neural networks;active contours;computer and information science;diploma;
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: 53 str.
ID: 12031351