University of Notre Dame
Browse

Solutions to Limited Annotation Problems of Deep Learning in Medical Image Segmentation

Download (5.13 MB)
dataset
posted on 2024-05-09, 16:51 authored by Xinrong Hu
Image segmentation holds broad applications in medical image analysis, providing crucial support to doctors in both automatic diagnosis and computer-assisted interventions. The heterogeneity observed across various medical image datasets necessitates the training of task-specific segmentation models. However, effectively supervising the training of deep learning segmentation models typically demands dense label masks, a requirement that becomes challenging due to the constraints posed by privacy and cost issues in collecting large-scale medical datasets. These challenges collectively give rise to the limited annotations problems in medical image segmentation. In this dissertation, we address the challenges posed by annotation deficiencies through a comprehensive exploration of various strategies. Firstly, we employ self-supervised learning to extract information from unlabeled data, presenting a tailored self-supervised method designed specifically for convolutional neural networks and 3D Vision Transformers. Secondly, our attention shifts to domain adaptation problems, leveraging images with similar content but in different modalities. We introduce the use of contrastive loss as a shape constraint in our image translation framework, resulting in both improved performance and enhanced training robustness. Thirdly, we incorporate diffusion models for data augmentation, expanding datasets with generated image-label pairs. Lastly, we explore to extract segmentation masks from image-level annotations alone. We propose a multi-task training framework for ECG abnormal beats localization and a conditional diffusion-based algorithm for tumor detection.

History

Date Created

2024-04-15

Date Modified

2024-05-09

Defense Date

2024-01-26

CIP Code

  • 14.0901

Research Director(s)

Yiyu Shi

Committee Members

Danny Chen Fanny Ye Walter Scheirer

Degree

  • Doctor of Philosophy

Degree Level

  • Doctoral Dissertation

Language

  • English

Library Record

006584542

OCLC Number

1433091732

Publisher

University of Notre Dame

Program Name

  • Computer Science and Engineering

Usage metrics

    Dissertations

    Categories

    No categories selected

    Keywords

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC