Data-Efficient and Robust Deep Learning Based Approaches for Biomedical Image Segmentation and Related Problems

Doctoral Dissertation


Image segmentation is a fundamental problem in computer vision and has been studied for decades. It is also an essential preliminary step for quantitative biomedical image analysis and computer-aided diagnoses and studies. Recently, deep learning (DL) based methods have witnessed huge success on various image analysis tasks in terms of accuracy and generality. However, it is not straightforward to apply known semantic segmentation algorithms directly to biomedical images due to different imaging techniques and special application scenarios (e.g., volumetric images, multi-modal data, small amounts of annotated data, domain knowledge from experts). In this dissertation, I develop new deep learning methods to save annotation efforts, improve model efficacy, and generalize well to different biomedical image segmentation tasks.

First, I introduce advanced model architectures and training algorithms to make use of abundant 3D information from volumetric images (e.g., MR and CT images) for delineating detailed structures. The heterogeneous feature aggregation network utilizes anisotropic 3D convolutional kernels to explicitly extract and fuse contextual information from orthogonal geometric views. I also devise a new ensemble learning framework to unify the merits of both 2D and 3D DL models and boost segmentation performance significantly. Second, I introduce the representative annotation method to only select the most effective areas/samples for annotation, thus saving manual efforts. Our method decouples the selection process from the segmentation process and makes a one-shot suggestion. It can achieve comparable performance to full annotation and active learning based methods. Third, noticing that using sparse annotation leads to huge performance degradation, I introduce two semi-supervised methods to leverage unlabeled images and utilize automatically generated labels (i.e., pseudo labels) in model training. Specifically, I propose combining representative annotation and ensemble learning to bridge the performance gap compared with full annotation methods. I also propose a method to estimate the uncertainty of pseudo labels and use them to guide iterative self-training. Fourth, I present a new self-supervised learning framework to extract generic knowledge directly from unlabeled data and demonstrate its high robustness and efficiency on diverse downstream segmentation tasks.


Attribute NameValues
Author Hao Zheng
Contributor Danny Z. Chen, Research Director
Contributor Chaoli Wang, Research Director
Contributor Yiyu Shi, Committee Member
Contributor Walter Scheirer, Committee Member
Contributor Meng Jiang, Committee Member
Contributor Joan T. Richtsmeier, Committee Member
Degree Level Doctoral Dissertation
Degree Discipline Computer Science and Engineering
Degree Name Doctor of Philosophy
Banner Code

Submission Date 2022-01-06
  • Biomedical Image Analysis

  • Image Segmentation

  • Deep Learning

  • English

Record Visibility Public
Content License
  • All rights reserved

Departments and Units
Catalog Record

Digital Object Identifier


This DOI is the best way to cite this doctoral dissertation.


Please Note: You may encounter a delay before a download begins. Large or infrequently accessed files can take several minutes to retrieve from our archival storage system.