Three-dimensional Fluorescence Microscopy Image Synthesis and Analysis Using Machine Learning
Abstract
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.
Degree
Ph.D.
Advisors
Delp, Purdue University.
Subject Area
Artificial intelligence
Off-Campus Purdue Users:
To access this dissertation, please log in to our
proxy server.