Zpět na vyhledávání

Andrej Kubanda

Bachelor's thesis

AI Image Analysis Pipeline Implementation for Digital Pathology

AI Image Analysis Pipeline Implementation for Digital Pathology
Abstract:
Moderná patológia smeruje k umelou inteligenciou asistovanému spôsobu práce, čo priťahuje mnohých výskumníkov, vrátane tímu na Fakulte informatiky. Avšak, nástroje na analýzu obrazu, vyvinuté týmto výskumným tímom, nie sú zjednotené a obsahujú problémy, typické pre prototypy a experimentálne implementácie. Práca preto predstavuje modulárny dizajn nástroja strojového učenia a dodáva aj jeho implementáciu …more
Abstract:
Modern pathology is moving towards an artificial intelligence-assisted workflow, which attracts many researchers, including a team at the Faculty of Informatics. However, the image analysis tools developed by the research team are not unified and suffer from issues typical for prototypes and experimental implementations. Thus, the thesis presents a modular machine learning pipeline design and delivers …more
 

Keywords

machine learning modularity configurability reproducibility convolutional neural networks machine learning pipeline Python TensorFlow Keras digital pathology whole slide images
 
Language used: English
Date on which the thesis was submitted / produced: 25. 5. 2021
Identifier: https://is.muni.cz/th/zw4kx/

Thesis defence

  • Date of defence: 28. 6. 2021
  • Supervisor: Mgr. Matej Gallo
  • Reader: RNDr. Jaroslav Čechák

Citation record

Cite this text

Full text of thesis

Contents of on-line thesis archive
Published in Theses:
  • světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatiky
Složka Reference to the local database directory of the institution