Abstract

Measuring the glomerular number in the entire, intact kidney using non-destructive techniques is of immense importance in studying several renal and systemic diseases. Commonly used approaches either require destruction of the entire kidney or perform extrapolation from measurements obtained from a few isolated sections. A recent magnetic resonance imaging (MRI) method, based on the injection of a contrast agent (cationic ferritin), has been used to effectively identify glomerular regions in the kidney. In this work, we propose a robust, accurate, and low-complexity method for estimating the number of glomeruli from such kidney MRI images. The proposed technique has a training phase and a low-complexity testing phase. In the training phase, organ segmentation is performed on a few expert-marked training images, and glomerular and non-glomerular image patches are extracted. Using non-local sparse coding to compute similarity and dissimilarity graphs between the patches, the subspace in which the glomerular regions can be discriminated from the rest are estimated. For novel test images, the image patches extracted after pre-processing are embedded using the discriminative subspace projections. The testing phase is of low computational complexity since it involves only matrix multiplications, clustering, and simple morphological operations. Preliminary results with MRI data obtained from five kidneys of rats show that the proposed non-invasive, low-complexity approach performs comparably to conventional approaches such as acid maceration and stereology.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2016: Image Processing
PublisherSPIE
Volume9784
ISBN (Electronic)9781510600195
DOIs
StatePublished - 2016
EventMedical Imaging 2016: Image Processing - San Diego, United States
Duration: Mar 1 2016Mar 3 2016

Other

OtherMedical Imaging 2016: Image Processing
CountryUnited States
CitySan Diego
Period3/1/163/3/16

Fingerprint

kidneys
Magnetic resonance
magnetic resonance
Magnetic Resonance Imaging
Kidney
Imaging techniques
education
Testing
Ferritins
Extrapolation
Contrast Media
glomerulus
Kidney Glomerulus
Rats
Computational complexity
preprocessing
Acids
multiplication
organs
rats

Keywords

  • Discriminative embedding
  • Magnetic resonance imaging
  • Non-destructive technique
  • Renal disease
  • Sparse coding

ASJC Scopus subject areas

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

Cite this

Thiagarajan, J. J., Natesan Ramamurthy, K., Kanberoglu, B., Frakes, D., Bennett, K., & Spanias, A. (2016). Measuring glomerular number from kidney MRI images. In Medical Imaging 2016: Image Processing (Vol. 9784). [978412] SPIE. https://doi.org/10.1117/12.2216753

Measuring glomerular number from kidney MRI images. / Thiagarajan, Jayaraman J.; Natesan Ramamurthy, Karthikeyan; Kanberoglu, Berkay; Frakes, David; Bennett, Kevin; Spanias, Andreas.

Medical Imaging 2016: Image Processing. Vol. 9784 SPIE, 2016. 978412.

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

Thiagarajan, JJ, Natesan Ramamurthy, K, Kanberoglu, B, Frakes, D, Bennett, K & Spanias, A 2016, Measuring glomerular number from kidney MRI images. in Medical Imaging 2016: Image Processing. vol. 9784, 978412, SPIE, Medical Imaging 2016: Image Processing, San Diego, United States, 3/1/16. https://doi.org/10.1117/12.2216753
Thiagarajan JJ, Natesan Ramamurthy K, Kanberoglu B, Frakes D, Bennett K, Spanias A. Measuring glomerular number from kidney MRI images. In Medical Imaging 2016: Image Processing. Vol. 9784. SPIE. 2016. 978412 https://doi.org/10.1117/12.2216753
Thiagarajan, Jayaraman J. ; Natesan Ramamurthy, Karthikeyan ; Kanberoglu, Berkay ; Frakes, David ; Bennett, Kevin ; Spanias, Andreas. / Measuring glomerular number from kidney MRI images. Medical Imaging 2016: Image Processing. Vol. 9784 SPIE, 2016.
@inproceedings{37762e93696c4fd9b9f0f1af81fdb0bb,
title = "Measuring glomerular number from kidney MRI images",
abstract = "Measuring the glomerular number in the entire, intact kidney using non-destructive techniques is of immense importance in studying several renal and systemic diseases. Commonly used approaches either require destruction of the entire kidney or perform extrapolation from measurements obtained from a few isolated sections. A recent magnetic resonance imaging (MRI) method, based on the injection of a contrast agent (cationic ferritin), has been used to effectively identify glomerular regions in the kidney. In this work, we propose a robust, accurate, and low-complexity method for estimating the number of glomeruli from such kidney MRI images. The proposed technique has a training phase and a low-complexity testing phase. In the training phase, organ segmentation is performed on a few expert-marked training images, and glomerular and non-glomerular image patches are extracted. Using non-local sparse coding to compute similarity and dissimilarity graphs between the patches, the subspace in which the glomerular regions can be discriminated from the rest are estimated. For novel test images, the image patches extracted after pre-processing are embedded using the discriminative subspace projections. The testing phase is of low computational complexity since it involves only matrix multiplications, clustering, and simple morphological operations. Preliminary results with MRI data obtained from five kidneys of rats show that the proposed non-invasive, low-complexity approach performs comparably to conventional approaches such as acid maceration and stereology.",
keywords = "Discriminative embedding, Magnetic resonance imaging, Non-destructive technique, Renal disease, Sparse coding",
author = "Thiagarajan, {Jayaraman J.} and {Natesan Ramamurthy}, Karthikeyan and Berkay Kanberoglu and David Frakes and Kevin Bennett and Andreas Spanias",
year = "2016",
doi = "10.1117/12.2216753",
language = "English (US)",
volume = "9784",
booktitle = "Medical Imaging 2016: Image Processing",
publisher = "SPIE",
address = "United States",

}

TY - GEN

T1 - Measuring glomerular number from kidney MRI images

AU - Thiagarajan, Jayaraman J.

AU - Natesan Ramamurthy, Karthikeyan

AU - Kanberoglu, Berkay

AU - Frakes, David

AU - Bennett, Kevin

AU - Spanias, Andreas

PY - 2016

Y1 - 2016

N2 - Measuring the glomerular number in the entire, intact kidney using non-destructive techniques is of immense importance in studying several renal and systemic diseases. Commonly used approaches either require destruction of the entire kidney or perform extrapolation from measurements obtained from a few isolated sections. A recent magnetic resonance imaging (MRI) method, based on the injection of a contrast agent (cationic ferritin), has been used to effectively identify glomerular regions in the kidney. In this work, we propose a robust, accurate, and low-complexity method for estimating the number of glomeruli from such kidney MRI images. The proposed technique has a training phase and a low-complexity testing phase. In the training phase, organ segmentation is performed on a few expert-marked training images, and glomerular and non-glomerular image patches are extracted. Using non-local sparse coding to compute similarity and dissimilarity graphs between the patches, the subspace in which the glomerular regions can be discriminated from the rest are estimated. For novel test images, the image patches extracted after pre-processing are embedded using the discriminative subspace projections. The testing phase is of low computational complexity since it involves only matrix multiplications, clustering, and simple morphological operations. Preliminary results with MRI data obtained from five kidneys of rats show that the proposed non-invasive, low-complexity approach performs comparably to conventional approaches such as acid maceration and stereology.

AB - Measuring the glomerular number in the entire, intact kidney using non-destructive techniques is of immense importance in studying several renal and systemic diseases. Commonly used approaches either require destruction of the entire kidney or perform extrapolation from measurements obtained from a few isolated sections. A recent magnetic resonance imaging (MRI) method, based on the injection of a contrast agent (cationic ferritin), has been used to effectively identify glomerular regions in the kidney. In this work, we propose a robust, accurate, and low-complexity method for estimating the number of glomeruli from such kidney MRI images. The proposed technique has a training phase and a low-complexity testing phase. In the training phase, organ segmentation is performed on a few expert-marked training images, and glomerular and non-glomerular image patches are extracted. Using non-local sparse coding to compute similarity and dissimilarity graphs between the patches, the subspace in which the glomerular regions can be discriminated from the rest are estimated. For novel test images, the image patches extracted after pre-processing are embedded using the discriminative subspace projections. The testing phase is of low computational complexity since it involves only matrix multiplications, clustering, and simple morphological operations. Preliminary results with MRI data obtained from five kidneys of rats show that the proposed non-invasive, low-complexity approach performs comparably to conventional approaches such as acid maceration and stereology.

KW - Discriminative embedding

KW - Magnetic resonance imaging

KW - Non-destructive technique

KW - Renal disease

KW - Sparse coding

UR - http://www.scopus.com/inward/record.url?scp=84981748012&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84981748012&partnerID=8YFLogxK

U2 - 10.1117/12.2216753

DO - 10.1117/12.2216753

M3 - Conference contribution

VL - 9784

BT - Medical Imaging 2016: Image Processing

PB - SPIE

ER -