Edge and curvilinear structures detection on medical images via unsupervised, adaptive and deep learning approaches

Computer-aided-diagnosis (CAD) systems are very useful to help doctors in detecting various human diseases. To build a CAD system, several computer vision algorithms are required, particularly to handle object detection and segmentation tasks automatically. To develop object detection algorithms, ed...

Full description

Saved in:
Bibliographic Details
Main Author: Dharmawan, Dhimas Arief
Other Authors: Ng Boon Poh
Format: Thesis-Doctor of Philosophy
Language:English
Published: Nanyang Technological University 2020
Subjects:
Online Access:https://hdl.handle.net/10356/140289
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-140289
record_format dspace
spelling sg-ntu-dr.10356-1402892023-07-04T17:20:18Z Edge and curvilinear structures detection on medical images via unsupervised, adaptive and deep learning approaches Dharmawan, Dhimas Arief Ng Boon Poh School of Electrical and Electronic Engineering EBPNG@ntu.edu.sg Engineering::Electrical and electronic engineering::Electronic systems::Signal processing Computer-aided-diagnosis (CAD) systems are very useful to help doctors in detecting various human diseases. To build a CAD system, several computer vision algorithms are required, particularly to handle object detection and segmentation tasks automatically. To develop object detection algorithms, edges and curvilinear structures detection tasks are typically required. However, performing these tasks manually is tedious, time-consuming and prone to human errors. In this thesis, we design computer algorithms for edge and curvilinear structures detection, particularly for the application of optical disc boundary and retinal vessel detection from fundus images. The algorithms are developed based on the mathematical function that can closely represent the edge and curvilinear structures behaviours. The algorithms can detect edge and curvilinear structures under an unsupervised framework and they also allow an implementation with a deep learning architecture. This provides meaningful insight for robust edge and curvilinear structures detection algorithms developments on other image modalities. Doctor of Philosophy 2020-05-27T13:15:14Z 2020-05-27T13:15:14Z 2020 Thesis-Doctor of Philosophy Dharmawan, D. A. (2020). Edge and curvilinear structures detection on medical images via unsupervised, adaptive and deep learning approaches. Doctoral thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/140289 10.32657/10356/140289 en This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0). 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 Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
spellingShingle Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
Dharmawan, Dhimas Arief
Edge and curvilinear structures detection on medical images via unsupervised, adaptive and deep learning approaches
description Computer-aided-diagnosis (CAD) systems are very useful to help doctors in detecting various human diseases. To build a CAD system, several computer vision algorithms are required, particularly to handle object detection and segmentation tasks automatically. To develop object detection algorithms, edges and curvilinear structures detection tasks are typically required. However, performing these tasks manually is tedious, time-consuming and prone to human errors. In this thesis, we design computer algorithms for edge and curvilinear structures detection, particularly for the application of optical disc boundary and retinal vessel detection from fundus images. The algorithms are developed based on the mathematical function that can closely represent the edge and curvilinear structures behaviours. The algorithms can detect edge and curvilinear structures under an unsupervised framework and they also allow an implementation with a deep learning architecture. This provides meaningful insight for robust edge and curvilinear structures detection algorithms developments on other image modalities.
author2 Ng Boon Poh
author_facet Ng Boon Poh
Dharmawan, Dhimas Arief
format Thesis-Doctor of Philosophy
author Dharmawan, Dhimas Arief
author_sort Dharmawan, Dhimas Arief
title Edge and curvilinear structures detection on medical images via unsupervised, adaptive and deep learning approaches
title_short Edge and curvilinear structures detection on medical images via unsupervised, adaptive and deep learning approaches
title_full Edge and curvilinear structures detection on medical images via unsupervised, adaptive and deep learning approaches
title_fullStr Edge and curvilinear structures detection on medical images via unsupervised, adaptive and deep learning approaches
title_full_unstemmed Edge and curvilinear structures detection on medical images via unsupervised, adaptive and deep learning approaches
title_sort edge and curvilinear structures detection on medical images via unsupervised, adaptive and deep learning approaches
publisher Nanyang Technological University
publishDate 2020
url https://hdl.handle.net/10356/140289
_version_ 1772827804379906048