Login | Register

Medical Image Segmentation by Deep Convolutional Neural Networks


Medical Image Segmentation by Deep Convolutional Neural Networks

Kang, Qingbo (2019) Medical Image Segmentation by Deep Convolutional Neural Networks. Masters thesis, Concordia University.

[thumbnail of Kang_MASc_F2019.pdf]
Text (application/pdf)
Kang_MASc_F2019.pdf - Accepted Version
Available under License Spectrum Terms of Access.


Medical image segmentation is a fundamental and critical step for medical image analysis. Due to the complexity and diversity of medical images, the segmentation of medical images continues to be a challenging problem. Recently, deep learning techniques, especially Convolution Neural Networks (CNNs) have received extensive research and achieve great success in many vision tasks. Specifically, with the advent of Fully Convolutional Networks (FCNs), automatic medical image segmentation based on FCNs is a promising research field. This thesis focuses on two medical image segmentation tasks: lung segmentation in chest X-ray images and nuclei segmentation in histopathological images.
For the lung segmentation task, we investigate several FCNs that have been successful in semantic and medical image segmentation. We evaluate the performance of these different FCNs on three publicly available chest X-ray image datasets.
For the nuclei segmentation task, since the challenges of this task are difficulty in segmenting the small, overlapping and touching nuclei, and limited ability of generalization to nuclei in different organs and tissue types, we propose a novel nuclei segmentation approach based on a two-stage learning framework and Deep Layer Aggregation (DLA). We convert the original binary segmentation task into a two-step task by adding nuclei-boundary prediction (3-classes) as an intermediate step. To solve our two-step task, we design a two-stage learning framework by stacking two U-Nets. The first stage estimates nuclei and their coarse boundaries while the second stage outputs the final fine-grained segmentation map. Furthermore, we also extend the U-Nets with DLA by iteratively merging features across different levels. We evaluate our proposed method on two public diverse nuclei datasets. The experimental results show that our proposed approach outperforms many standard segmentation architectures and recently proposed nuclei segmentation methods, and can be easily generalized across different cell types in various organs.

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Computer Science and Software Engineering
Item Type:Thesis (Masters)
Authors:Kang, Qingbo
Institution:Concordia University
Degree Name:M.A. Sc.
Program:Software Engineering
Date:9 August 2019
Thesis Supervisor(s):Fevens, Thomas
ID Code:985550
Deposited By: Qingbo Kang
Deposited On:06 Feb 2020 02:40
Last Modified:06 Feb 2020 02:40
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Research related to the current document (at the CORE website)
- Research related to the current document (at the CORE website)
Back to top Back to top