Microvascular Structure Segmentation in Human Tissue Using Deep Learning

Singh, Sarvochch Balwant (2023) Microvascular Structure Segmentation in Human Tissue Using Deep Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (5MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The main objective of this research was to investigate the effective ways in which a 2D photo of a healthy human tissue can be segmented to find blood vessel present in them. Two models were selected for the task first being DeeplabV3+ and the second model U-Net.

After conducting a through research it was evident that both the models had potential for image segmentation in the filed of medical. However U-Net showed a Superior performance compared to DeeplabV3+ it had a better dice coefficient score of 0.68 ± 0.1. The study also showed light on the architecture of Deeplabv3+, however being good in the field of medical image segmentation its complex architecture does not work properly when it comes to identify small details present in the image so it may not be accepted across other medical imaging applications.

This study sheds light on how deep learning models can help professionals in filed of medical by improving healthcare imaging, which is very essential for fast and effective diagnosis. The study also shows some limitations such as the models may perform badly given on the dataset/images that they are provided with.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Cosgrave, Noel UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HM Sociology > Information Science > Communication > Medical Informatics
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	23 May 2025 10:22
Last Modified:	23 May 2025 10:22
URI:	https://norma.ncirl.ie/id/eprint/7616

Actions (login required)

View Item