Boundary segmentation for fluorescence microscopy using steerable filters

David Joon Ho, Paul Salama, Kenneth Dunn, Edward J. Delp

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Fluorescence microscopy is used to image multiple subcellular structures in living cells which are not readily observed using conventional optical microscopy. Moreover, two-photon microscopy is widely used to image structures deeper in tissue. Recent advancement in fluorescence microscopy has enabled the generation of large data sets of images at different depths, times, and spectral channels. Thus, automatic object segmentation is necessary since manual segmentation would be inefficient and biased. However, automatic segmentation is still a challenging problem as regions of interest may not have well defined boundaries as well as non-uniform pixel intensities. This paper describes a method for segmenting tubular structures in fluorescence microscopy images of rat kidney and liver samples using adaptive histogram equalization, foreground/background segmentation, steerable filters to capture directional tendencies, and connected-component analysis. The results from several data sets demonstrate that our method can segment tubular boundaries successfully. Moreover, our method has better performance when compared to other popular image segmentation methods when using ground truth data obtained via manual segmentation.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2017
Subtitle of host publicationImage Processing
PublisherSPIE
Volume10133
ISBN (Electronic)9781510607118
DOIs
StatePublished - 2017
EventMedical Imaging 2017: Image Processing - Orlando, United States
Duration: Feb 12 2017Feb 14 2017

Other

OtherMedical Imaging 2017: Image Processing
CountryUnited States
CityOrlando
Period2/12/172/14/17

Fingerprint

Fluorescence microscopy
Fluorescence Microscopy
microscopy
filters
fluorescence
Microscopy
Image segmentation
Liver
Optical microscopy
Rats
Microscopic examination
Photons
Pixels
Cells
ground truth
Tissue
kidneys
liver
histograms
rats

Keywords

  • Fluorescence microscopy
  • Image segmentation
  • Steerable filters
  • Tubule boundary

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Ho, D. J., Salama, P., Dunn, K., & Delp, E. J. (2017). Boundary segmentation for fluorescence microscopy using steerable filters. In Medical Imaging 2017: Image Processing (Vol. 10133). [101330E] SPIE. https://doi.org/10.1117/12.2254627

Boundary segmentation for fluorescence microscopy using steerable filters. / Ho, David Joon; Salama, Paul; Dunn, Kenneth; Delp, Edward J.

Medical Imaging 2017: Image Processing. Vol. 10133 SPIE, 2017. 101330E.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ho, DJ, Salama, P, Dunn, K & Delp, EJ 2017, Boundary segmentation for fluorescence microscopy using steerable filters. in Medical Imaging 2017: Image Processing. vol. 10133, 101330E, SPIE, Medical Imaging 2017: Image Processing, Orlando, United States, 2/12/17. https://doi.org/10.1117/12.2254627
Ho DJ, Salama P, Dunn K, Delp EJ. Boundary segmentation for fluorescence microscopy using steerable filters. In Medical Imaging 2017: Image Processing. Vol. 10133. SPIE. 2017. 101330E https://doi.org/10.1117/12.2254627
Ho, David Joon ; Salama, Paul ; Dunn, Kenneth ; Delp, Edward J. / Boundary segmentation for fluorescence microscopy using steerable filters. Medical Imaging 2017: Image Processing. Vol. 10133 SPIE, 2017.
@inproceedings{ab64432507a84a908202539e0114bd27,
title = "Boundary segmentation for fluorescence microscopy using steerable filters",
abstract = "Fluorescence microscopy is used to image multiple subcellular structures in living cells which are not readily observed using conventional optical microscopy. Moreover, two-photon microscopy is widely used to image structures deeper in tissue. Recent advancement in fluorescence microscopy has enabled the generation of large data sets of images at different depths, times, and spectral channels. Thus, automatic object segmentation is necessary since manual segmentation would be inefficient and biased. However, automatic segmentation is still a challenging problem as regions of interest may not have well defined boundaries as well as non-uniform pixel intensities. This paper describes a method for segmenting tubular structures in fluorescence microscopy images of rat kidney and liver samples using adaptive histogram equalization, foreground/background segmentation, steerable filters to capture directional tendencies, and connected-component analysis. The results from several data sets demonstrate that our method can segment tubular boundaries successfully. Moreover, our method has better performance when compared to other popular image segmentation methods when using ground truth data obtained via manual segmentation.",
keywords = "Fluorescence microscopy, Image segmentation, Steerable filters, Tubule boundary",
author = "Ho, {David Joon} and Paul Salama and Kenneth Dunn and Delp, {Edward J.}",
year = "2017",
doi = "10.1117/12.2254627",
language = "English (US)",
volume = "10133",
booktitle = "Medical Imaging 2017",
publisher = "SPIE",

}

TY - GEN

T1 - Boundary segmentation for fluorescence microscopy using steerable filters

AU - Ho, David Joon

AU - Salama, Paul

AU - Dunn, Kenneth

AU - Delp, Edward J.

PY - 2017

Y1 - 2017

N2 - Fluorescence microscopy is used to image multiple subcellular structures in living cells which are not readily observed using conventional optical microscopy. Moreover, two-photon microscopy is widely used to image structures deeper in tissue. Recent advancement in fluorescence microscopy has enabled the generation of large data sets of images at different depths, times, and spectral channels. Thus, automatic object segmentation is necessary since manual segmentation would be inefficient and biased. However, automatic segmentation is still a challenging problem as regions of interest may not have well defined boundaries as well as non-uniform pixel intensities. This paper describes a method for segmenting tubular structures in fluorescence microscopy images of rat kidney and liver samples using adaptive histogram equalization, foreground/background segmentation, steerable filters to capture directional tendencies, and connected-component analysis. The results from several data sets demonstrate that our method can segment tubular boundaries successfully. Moreover, our method has better performance when compared to other popular image segmentation methods when using ground truth data obtained via manual segmentation.

AB - Fluorescence microscopy is used to image multiple subcellular structures in living cells which are not readily observed using conventional optical microscopy. Moreover, two-photon microscopy is widely used to image structures deeper in tissue. Recent advancement in fluorescence microscopy has enabled the generation of large data sets of images at different depths, times, and spectral channels. Thus, automatic object segmentation is necessary since manual segmentation would be inefficient and biased. However, automatic segmentation is still a challenging problem as regions of interest may not have well defined boundaries as well as non-uniform pixel intensities. This paper describes a method for segmenting tubular structures in fluorescence microscopy images of rat kidney and liver samples using adaptive histogram equalization, foreground/background segmentation, steerable filters to capture directional tendencies, and connected-component analysis. The results from several data sets demonstrate that our method can segment tubular boundaries successfully. Moreover, our method has better performance when compared to other popular image segmentation methods when using ground truth data obtained via manual segmentation.

KW - Fluorescence microscopy

KW - Image segmentation

KW - Steerable filters

KW - Tubule boundary

UR - http://www.scopus.com/inward/record.url?scp=85020276504&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020276504&partnerID=8YFLogxK

U2 - 10.1117/12.2254627

DO - 10.1117/12.2254627

M3 - Conference contribution

AN - SCOPUS:85020276504

VL - 10133

BT - Medical Imaging 2017

PB - SPIE

ER -