A novel Hessian based algorithm for rat kidney glomerulus detection in 3D MRI

Min Zhang, Teresa Wu, Kevin M. Bennett

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

5 Citations (Scopus)

Abstract

The glomeruli of the kidney perform the key role of blood filtration and the number of glomeruli in a kidney is correlated with susceptibility to chronic kidney disease and chronic cardiovascular disease. This motivates the development of new technology using magnetic resonance imaging (MRI) to measure the number of glomeruli and nephrons in vivo. However, there is currently a lack of computationally efficient techniques to perform fast, reliable and accurate counts of glomeruli in MR images due to the issues inherent in MRI, such as acquisition noise, partial volume effects (the mixture of several tissue signals in a voxel) and bias field (spatial intensity inhomogeneity). Such challenges are particularly severe because the glomeruli are very small, (in our case, a MRI image is ∼16 million voxels, each glomerulus is in the size of 8∼20 voxels), and the number of glomeruli is very large. To address this, we have developed an efficient Hessian based Difference of Gaussians (HDoG) detector to identify the glomeruli on 3D rat MR images. The image is first smoothed via DoG followed by the Hessian process to pre-segment and delineate the boundary of the glomerulus candidates. This then provides a basis to extract regional features used in an unsupervised clustering algorithm, completing segmentation by removing the false identifications occurred in the pre-segmentation. The experimental results show that Hessian based DoG has the potential to automatically detect glomeruli,from MRI in 3D, enabling new measurements of renal microstructure and pathology in preclinical and clinical studies.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2015: Image Processing
PublisherSPIE
Volume9413
ISBN (Print)9781628415032
DOIs
StatePublished - 2015
EventMedical Imaging 2015: Image Processing - Orlando, United States
Duration: Feb 24 2015Feb 26 2015

Other

OtherMedical Imaging 2015: Image Processing
CountryUnited States
CityOrlando
Period2/24/152/26/15

Fingerprint

glomerulus
Kidney Glomerulus
kidneys
Magnetic resonance
rats
magnetic resonance
Rats
Magnetic Resonance Imaging
Imaging techniques
Kidney
Nephrons
Pathology
Chronic Renal Insufficiency
Clustering algorithms
Cluster Analysis
Noise
Blood
Chronic Disease
Cardiovascular Diseases
Tissue

Keywords

  • Glomeruli detection
  • Hessian Analysis
  • Scale Space
  • Unsupervised Learning

ASJC Scopus subject areas

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

Cite this

Zhang, M., Wu, T., & Bennett, K. M. (2015). A novel Hessian based algorithm for rat kidney glomerulus detection in 3D MRI. In Medical Imaging 2015: Image Processing (Vol. 9413). [94132N] SPIE. https://doi.org/10.1117/12.2081484

A novel Hessian based algorithm for rat kidney glomerulus detection in 3D MRI. / Zhang, Min; Wu, Teresa; Bennett, Kevin M.

Medical Imaging 2015: Image Processing. Vol. 9413 SPIE, 2015. 94132N.

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

Zhang, M, Wu, T & Bennett, KM 2015, A novel Hessian based algorithm for rat kidney glomerulus detection in 3D MRI. in Medical Imaging 2015: Image Processing. vol. 9413, 94132N, SPIE, Medical Imaging 2015: Image Processing, Orlando, United States, 2/24/15. https://doi.org/10.1117/12.2081484
Zhang M, Wu T, Bennett KM. A novel Hessian based algorithm for rat kidney glomerulus detection in 3D MRI. In Medical Imaging 2015: Image Processing. Vol. 9413. SPIE. 2015. 94132N https://doi.org/10.1117/12.2081484
Zhang, Min ; Wu, Teresa ; Bennett, Kevin M. / A novel Hessian based algorithm for rat kidney glomerulus detection in 3D MRI. Medical Imaging 2015: Image Processing. Vol. 9413 SPIE, 2015.
@inproceedings{ad11bdb90b94430582931bee9fcbf722,
title = "A novel Hessian based algorithm for rat kidney glomerulus detection in 3D MRI",
abstract = "The glomeruli of the kidney perform the key role of blood filtration and the number of glomeruli in a kidney is correlated with susceptibility to chronic kidney disease and chronic cardiovascular disease. This motivates the development of new technology using magnetic resonance imaging (MRI) to measure the number of glomeruli and nephrons in vivo. However, there is currently a lack of computationally efficient techniques to perform fast, reliable and accurate counts of glomeruli in MR images due to the issues inherent in MRI, such as acquisition noise, partial volume effects (the mixture of several tissue signals in a voxel) and bias field (spatial intensity inhomogeneity). Such challenges are particularly severe because the glomeruli are very small, (in our case, a MRI image is ∼16 million voxels, each glomerulus is in the size of 8∼20 voxels), and the number of glomeruli is very large. To address this, we have developed an efficient Hessian based Difference of Gaussians (HDoG) detector to identify the glomeruli on 3D rat MR images. The image is first smoothed via DoG followed by the Hessian process to pre-segment and delineate the boundary of the glomerulus candidates. This then provides a basis to extract regional features used in an unsupervised clustering algorithm, completing segmentation by removing the false identifications occurred in the pre-segmentation. The experimental results show that Hessian based DoG has the potential to automatically detect glomeruli,from MRI in 3D, enabling new measurements of renal microstructure and pathology in preclinical and clinical studies.",
keywords = "Glomeruli detection, Hessian Analysis, Scale Space, Unsupervised Learning",
author = "Min Zhang and Teresa Wu and Bennett, {Kevin M.}",
year = "2015",
doi = "10.1117/12.2081484",
language = "English (US)",
isbn = "9781628415032",
volume = "9413",
booktitle = "Medical Imaging 2015: Image Processing",
publisher = "SPIE",

}

TY - GEN

T1 - A novel Hessian based algorithm for rat kidney glomerulus detection in 3D MRI

AU - Zhang, Min

AU - Wu, Teresa

AU - Bennett, Kevin M.

PY - 2015

Y1 - 2015

N2 - The glomeruli of the kidney perform the key role of blood filtration and the number of glomeruli in a kidney is correlated with susceptibility to chronic kidney disease and chronic cardiovascular disease. This motivates the development of new technology using magnetic resonance imaging (MRI) to measure the number of glomeruli and nephrons in vivo. However, there is currently a lack of computationally efficient techniques to perform fast, reliable and accurate counts of glomeruli in MR images due to the issues inherent in MRI, such as acquisition noise, partial volume effects (the mixture of several tissue signals in a voxel) and bias field (spatial intensity inhomogeneity). Such challenges are particularly severe because the glomeruli are very small, (in our case, a MRI image is ∼16 million voxels, each glomerulus is in the size of 8∼20 voxels), and the number of glomeruli is very large. To address this, we have developed an efficient Hessian based Difference of Gaussians (HDoG) detector to identify the glomeruli on 3D rat MR images. The image is first smoothed via DoG followed by the Hessian process to pre-segment and delineate the boundary of the glomerulus candidates. This then provides a basis to extract regional features used in an unsupervised clustering algorithm, completing segmentation by removing the false identifications occurred in the pre-segmentation. The experimental results show that Hessian based DoG has the potential to automatically detect glomeruli,from MRI in 3D, enabling new measurements of renal microstructure and pathology in preclinical and clinical studies.

AB - The glomeruli of the kidney perform the key role of blood filtration and the number of glomeruli in a kidney is correlated with susceptibility to chronic kidney disease and chronic cardiovascular disease. This motivates the development of new technology using magnetic resonance imaging (MRI) to measure the number of glomeruli and nephrons in vivo. However, there is currently a lack of computationally efficient techniques to perform fast, reliable and accurate counts of glomeruli in MR images due to the issues inherent in MRI, such as acquisition noise, partial volume effects (the mixture of several tissue signals in a voxel) and bias field (spatial intensity inhomogeneity). Such challenges are particularly severe because the glomeruli are very small, (in our case, a MRI image is ∼16 million voxels, each glomerulus is in the size of 8∼20 voxels), and the number of glomeruli is very large. To address this, we have developed an efficient Hessian based Difference of Gaussians (HDoG) detector to identify the glomeruli on 3D rat MR images. The image is first smoothed via DoG followed by the Hessian process to pre-segment and delineate the boundary of the glomerulus candidates. This then provides a basis to extract regional features used in an unsupervised clustering algorithm, completing segmentation by removing the false identifications occurred in the pre-segmentation. The experimental results show that Hessian based DoG has the potential to automatically detect glomeruli,from MRI in 3D, enabling new measurements of renal microstructure and pathology in preclinical and clinical studies.

KW - Glomeruli detection

KW - Hessian Analysis

KW - Scale Space

KW - Unsupervised Learning

UR - http://www.scopus.com/inward/record.url?scp=84943414190&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84943414190&partnerID=8YFLogxK

U2 - 10.1117/12.2081484

DO - 10.1117/12.2081484

M3 - Conference contribution

AN - SCOPUS:84943414190

SN - 9781628415032

VL - 9413

BT - Medical Imaging 2015: Image Processing

PB - SPIE

ER -