Improving white blood cells image segmentation performance under domain shift

Improving white blood cells image segmentation performance under domain shift

Domain shift is a phenomenon in which the distribution of the input space is shifted due to a change in the description of the observed variable or in the observing system. In this paper, the structure of white blood cells is analyzed, U-Net semantic segmentation network is constructed, and image se...

Full description

Saved in:
Bibliographic Details
Main Author: Duan, Bohao
Other Authors: Wen Bihan
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2024
Subjects:
Computer and Information Science
White blood cells
U-Net image semantic segmentation
Domain shift
Online Access:https://hdl.handle.net/10356/176776
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-176776
record_format dspace
spelling sg-ntu-dr.10356-1767762024-05-24T15:42:56Z Improving white blood cells image segmentation performance under domain shift Duan, Bohao Wen Bihan School of Electrical and Electronic Engineering bihan.wen@ntu.edu.sg Computer and Information Science White blood cells U-Net image semantic segmentation Domain shift Domain shift is a phenomenon in which the distribution of the input space is shifted due to a change in the description of the observed variable or in the observing system. In this paper, the structure of white blood cells is analyzed, U-Net semantic segmentation network is constructed, and image segmentation deep learning of white blood cells, especially their nuclei, is carried out on PBC data set. Using the learned weights, the segmentation results are tested on the Test-B data set of Raabin-WBC. Bachelor's degree 2024-05-20T07:42:12Z 2024-05-20T07:42:12Z 2024 Final Year Project (FYP) Duan, B. (2024). Improving white blood cells image segmentation performance under domain shift. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/176776 https://hdl.handle.net/10356/176776 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Computer and Information Science
White blood cells
U-Net image semantic segmentation
Domain shift
spellingShingle Computer and Information Science
White blood cells
U-Net image semantic segmentation
Domain shift
Duan, Bohao
Improving white blood cells image segmentation performance under domain shift
description Domain shift is a phenomenon in which the distribution of the input space is shifted due to a change in the description of the observed variable or in the observing system. In this paper, the structure of white blood cells is analyzed, U-Net semantic segmentation network is constructed, and image segmentation deep learning of white blood cells, especially their nuclei, is carried out on PBC data set. Using the learned weights, the segmentation results are tested on the Test-B data set of Raabin-WBC.
author2 Wen Bihan
author_facet Wen Bihan
Duan, Bohao
format Final Year Project
author Duan, Bohao
author_sort Duan, Bohao
title Improving white blood cells image segmentation performance under domain shift
title_short Improving white blood cells image segmentation performance under domain shift
title_full Improving white blood cells image segmentation performance under domain shift
title_fullStr Improving white blood cells image segmentation performance under domain shift
title_full_unstemmed Improving white blood cells image segmentation performance under domain shift
title_sort improving white blood cells image segmentation performance under domain shift
publisher Nanyang Technological University
publishDate 2024
url https://hdl.handle.net/10356/176776
_version_ 1806059922076467200

Similar Items