Three Dimensional Fluorescence Microscopy Image Synthesis and Segmentation

  title={Three Dimensional Fluorescence Microscopy Image Synthesis and Segmentation},
  author={Chichen Fu and Soonam Lee and David Joon Ho and Shuo Han and Paul Salama and Kenneth W. Dunn and Edward J. Delp},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  • Chichen FuSoonam Lee E. Delp
  • Published 22 January 2018
  • Computer Science
  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Advances in fluorescence microscopy enable acquisition of 3D image volumes with better image quality and deeper penetration into tissue. [] Key Method A set of synthetic volumes and the corresponding groundtruth are generated using spatially constrained cycle-consistent adversarial networks. Segmentation results demonstrate that our proposed method is capable of segmenting nuclei successfully for various data sets.

Figures and Tables from this paper

Center-Extraction-Based Three Dimensional Nuclei Instance Segmentation of Fluorescence Microscopy Images

This paper describes a method for generating synthetic microscopy volumes based on a spatially constrained cycle-consistent adversarial network and outperforms other commonly used segmentation techniques.

Three Dimensional Nuclei Segmentation and Classification of Fluorescence Microscopy Images

  • Shuo HanSoonam Lee E. Delp
  • Biology, Physics
    2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)
  • 2020
An unsupervised volume to volume translation approach adapted from the Recycle-GAN using modified Hausdorff distance loss for synthetically generating nuclei with better shapes is presented.

Sphere estimation network: three-dimensional nuclei detection of fluorescence microscopy images

A 3D convolutional neural network, called Sphere Estimation Network (SphEsNet), is developed, to extract characteristics of nuclei without any postprocessing steps and can simultaneously localize nuclei and estimate their size without additional steps.

Three Dimensional Blind Image Deconvolution for Fluorescence Microscopy using Generative Adversarial Networks

Experimental results indicate that the proposed three dimensional blind image deconvolution method can restore and improve the quality of blurred and noisy deep depth microscopy image visually and quantitatively.

Quality Assessment of Synthetic Fluorescence Microscopy Images for Image Segmentation

This work proposes three quality metrics that quantify the fidelity of the foreground signal, the background noise, and blurring, respectively, of synthesized fluorescence microscopy images of mitochondria synthesized by two representative GANs.

NISNet3D: Three-Dimensional Nuclear Synthesis and Instance Segmentation for Fluorescence Microscopy Images

3D Nuclei Instance Segmentation Network (NISNet3D), a deep learning-based approach in which training is accomplished using synthetic data, profoundly reducing the effort required for network training.

An Ensemble Learning and Slice Fusion Strategy for Three-Dimensional Nuclei Instance Segmentation

An ensemble learning and slice fusion strategy for 3D nuclei instance segmentation that is practical and effective, that does not need any ground truth annotations for training and can inference on any large size volumes.

Nuclei counting in microscopy images with three dimensional generative adversarial networks

Both the counting accuracy and the object-based evaluation show that the proposed technique is successful for counting nuclei in 3D.

Three Dimensional Synthetic Non-Ellipsoidal Nuclei Volume Generation Using Bézier Curves

This paper presents a technique to generate synthetic non-ellipsoidal nuclei microscopy images using Bézier Curves and indicates that the approach achieves improved segmentation on volumes with irregularly shaped nuclei.

DeepSynth: Three-dimensional nuclear segmentation of biological images using neural networks trained with synthetic data

Comparisons with results obtained using commonly-used image processing packages demonstrate that DeepSynth provides the superior results associated with deep-learning techniques without the need for manual annotation.



Nuclei segmentation of fluorescence microscopy images using convolutional neural networks

A nuclei segmentation method using a deep convolutional neural network, data augmentation to generate training images of different shapes and contrasts, a refinement process combining segmentation results of horizontal, frontal, and sagittal planes in a volume, and a watershed technique to count the number of nuclei is described.

Nuclei Segmentation of Fluorescence Microscopy Images Using Three Dimensional Convolutional Neural Networks

This paper describes a fully 3D nuclei segmentation method using three dimensional convolutional neural networks and demonstrates that the method can successfully segment nuclei in 3D.

Segmentation of fluorescence microscopy images using three dimensional active contours with inhomogeneity correction

This paper describes a nuclei segmentation method for fluorescence microscopy based on the use of three dimensional (3D) active contours with inhomogeneity correction that achieves better performance than other reported methods.

Three dimensional segmentation of fluorescence microscopy images using active surfaces

A three dimensional segmentation method utilizing active surfaces to segment microscopy image volumes is described and demonstrated on a three dimensional sequence of images acquired from stationary/stabilized kidney tissue of a rat.

Active Mask Segmentation of Fluorescence Microscope Images

A new active mask algorithm for the segmentation of fluorescence microscope images of punctate patterns that combines the flexibility offered by active-contour methods, speed offered by multiresolution methods, and statistical modeling offered by region-growing methods into a fast and accurate segmentation tool.

Segmentation and quantification of subcellular structures in fluorescence microscopy images using Squassh

A versatile protocol for a method named 'Squassh' (segmentation and quantification of subcellular shapes), which is used for detecting, delineating and quantifyingSubcellular structures in fluorescence microscopy images, implemented in freely available, user-friendly software.

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

This work proposes an approach to 3D image segmentation based on a volumetric, fully convolutional, neural network, trained end-to-end on MRI volumes depicting prostate, and learns to predict segmentation for the whole volume at once.

Adversarial synthesis learning enables segmentation without target modality ground truth

A novel end-to-end synthesis and segmentation network (EssNet) is proposed to achieve the unpaired MRI to CT image synthesis and CT splenomegaly segmentation simultaneously without using manual labels on CT.

U-Net: Convolutional Networks for Biomedical Image Segmentation

It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks.

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts and performs on-the-fly elastic deformations for efficient data augmentation during training.