Purdue University Graduate School
Browse
thesis-liming.pdf (19.62 MB)

Three-Dimensional Fluorescence Microscopy Image Synthesis and Analysis Using Machine Learning

Download (19.62 MB)
thesis
posted on 2023-02-07, 13:42 authored by Liming WuLiming Wu

Recent advances in fluorescence  microscopy enable deeper cellular imaging in living tissues with near-infrared excitation light. 

High quality fluorescence microscopy images provide useful information for analyzing biological structures and diagnosing diseases.

Nuclei detection and segmentation are two fundamental steps for quantitative analysis of microscopy images.

However, existing machine learning-based approaches are hampered by three main challenges: (1) Hand annotated ground truth is difficult to obtain especially for 3D volumes, (2) Most of the object detection methods work only on 2D images and are difficult to extend to 3D volumes, (3) Segmentation-based approaches typically cannot distinguish different object instances without proper post-processing steps.

In this thesis, we propose various new methods for microscopy image analysis including nuclei synthesis, detection, and segmentation. 

Due to the limitation of manually annotated ground truth masks, we first describe how we generate 2D/3D synthetic microscopy images using SpCycleGAN and use them as a data augmentation technique for our detection and segmentation networks.

For nuclei detection, we describe our RCNN-SliceNet for nuclei counting and centroid detection using slice-and-cluster strategy. 

Then we introduce our 3D CentroidNet for nuclei centroid estimation using vector flow voting mechanism which does not require any post-processing steps.

For nuclei segmentation, we first describe our EMR-CNN for nuclei instance segmentation using ensemble learning and slice fusion strategy.

Then we present the 3D Nuclei Instance Segmentation Network (NISNet3D) for nuclei instance segmentation using gradient vector field array.

Extensive experiments have been conducted on a variety of challenging microscopy volumes to demonstrate that our approach can accurately detect and segment the cell nuclei and outperforms other compared methods.

Finally, we describe the Distributed and Networked Analysis of Volumetric Image Data (DINAVID) system we developed for biologists to remotely analyze large microscopy volumes using machine learning. 

Funding

NIH/NIDDK P30 DK079312

History

Degree Type

  • Doctor of Philosophy

Department

  • Electrical and Computer Engineering

Campus location

  • West Lafayette

Advisor/Supervisor/Committee Chair

Edward J. Delp

Additional Committee Member 2

Paul Salama

Additional Committee Member 3

Fengqing Maggie Zhu

Additional Committee Member 4

Mary L. Comer

Usage metrics

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC