Bc. Adam Džadoň

Bachelor's thesis

Deep Learning Methods for Epithelium Segmentation of Breast and Colorectal Tissue

Deep Learning Methods for Epithelium Segmentation of Breast and Colorectal Tissue
Abstract:
Automatizované metódy segmentácie epitelu znižujú množstvo potrebnej práce od profesionálnych patológov a zlepšujú proces diagnostiky rakoviny. Táto práca vytvára a prezentuje niekoľko modelov hlbokého učenia pre segmentáciu epitelu prsného a kolorektálneho tkaniva založených na architektúre U-Net. Vyhodnotenie modelov naznačuje, že modely trénované na kolorektálnych dátach vykazujú sľubné výsledky …more
Abstract:
Automated methods of epithelium segmentation reduce the manual effort of professional pathologists and enhance the cancer diagnosis process. This thesis creates and presents several deep learning models for the epithelium segmentation of breast and colorectal tissue based on U-Net architecture. The evaluation of the models reveals that the models trained on colorectal data exhibit promising results …more
 
 
Language used: English
Date on which the thesis was submitted / produced: 23. 5. 2024

Thesis defence

  • Date of defence: 24. 6. 2024
  • Supervisor: RNDr. Vít Musil, Ph.D.
  • Reader: doc. Mgr. Jan Obdržálek, PhD.

Citation record

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

Masaryk University

Faculty of Informatics

Bachelor programme / field:
Informatics / Informatics