Computational analysis of the structural progression of human glomeruli in diabetic nephropathy

Brandon G. Ginley, John E. Tomaszewski, Kuang-Yu Jen, Agnes Fogo, Sanjay Jain, Pinaki Sarder

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

1 Citation (Scopus)

Abstract

The glomerulus is the primary compartment of blood filtration in the kidney. It is a sphere of bundled, fenestrated capillaries that selectively allows solute loss. Structural damages to glomerular micro-compartments lead to physiological failures which influence filtration efficacy. The sole way to confirm glomerular structural damage in renal pathology is by examining histopathological or immunofluorescence stained needle biopsies under a light microscope. However, this method is extremely tedious and time consuming, and requires manual scoring on the number and volume of structures. Computational image analysis is the perfect tool to ease this burden. The major obstacle to development of digital histopathological quantification protocols for renal pathology is the extreme heterogeneity present within kidney tissue. Here we present an automated computational pipeline to 1) segment glomerular compartment boundaries and 2) quantify features of compartments, in healthy and diseased renal tissue. The segmentation involves a two stage process, one step for rough segmentation generation and another for refinement. Using a Naïve Bayesian classifier on the resulting feature set, this method was able to distinguish pathological stage IIa from III with 0.89/0.93 sensitivity/specificity and stage IIb from III with 0.7/0.8 sensitivity/specificity, on n = 514 glomeruli taken from n = 13 human biopsies with diagnosed diabetic nephropathy, and n = 5 human renal tissues with no histological abnormalities. Our method will simplify computational partitioning of glomerular micro-compartments and subsequent quantification. We aim for our methods to ease manual labor associated with clinical diagnosis of renal disease.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2018
Subtitle of host publicationDigital Pathology
PublisherSPIE
Volume10581
ISBN (Electronic)9781510616516
DOIs
StatePublished - Jan 1 2018
Externally publishedYes
EventMedical Imaging 2018: Digital Pathology - Houston, United States
Duration: Feb 11 2018Feb 12 2018

Other

OtherMedical Imaging 2018: Digital Pathology
CountryUnited States
CityHouston
Period2/11/182/12/18

Fingerprint

glomerulus
Diabetic Nephropathies
compartments
progressions
Biopsy
Pathology
Tissue
Kidney
pathology
kidneys
Needles
Image analysis
damage
Microscopes
Blood
Classifiers
Pipelines
Personnel
scoring
labor

Keywords

  • Automated computation
  • Diabetic nephropathy
  • Digital quantification
  • Feature extraction
  • Glomerulus
  • Histology
  • Kidney
  • Naïve Bayes
  • Segmentation

ASJC Scopus subject areas

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

Cite this

Ginley, B. G., Tomaszewski, J. E., Jen, K-Y., Fogo, A., Jain, S., & Sarder, P. (2018). Computational analysis of the structural progression of human glomeruli in diabetic nephropathy. In Medical Imaging 2018: Digital Pathology (Vol. 10581). [105810A] SPIE. https://doi.org/10.1117/12.2295249

Computational analysis of the structural progression of human glomeruli in diabetic nephropathy. / Ginley, Brandon G.; Tomaszewski, John E.; Jen, Kuang-Yu; Fogo, Agnes; Jain, Sanjay; Sarder, Pinaki.

Medical Imaging 2018: Digital Pathology. Vol. 10581 SPIE, 2018. 105810A.

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

Ginley, BG, Tomaszewski, JE, Jen, K-Y, Fogo, A, Jain, S & Sarder, P 2018, Computational analysis of the structural progression of human glomeruli in diabetic nephropathy. in Medical Imaging 2018: Digital Pathology. vol. 10581, 105810A, SPIE, Medical Imaging 2018: Digital Pathology, Houston, United States, 2/11/18. https://doi.org/10.1117/12.2295249
Ginley BG, Tomaszewski JE, Jen K-Y, Fogo A, Jain S, Sarder P. Computational analysis of the structural progression of human glomeruli in diabetic nephropathy. In Medical Imaging 2018: Digital Pathology. Vol. 10581. SPIE. 2018. 105810A https://doi.org/10.1117/12.2295249
Ginley, Brandon G. ; Tomaszewski, John E. ; Jen, Kuang-Yu ; Fogo, Agnes ; Jain, Sanjay ; Sarder, Pinaki. / Computational analysis of the structural progression of human glomeruli in diabetic nephropathy. Medical Imaging 2018: Digital Pathology. Vol. 10581 SPIE, 2018.
@inproceedings{a4b809bd27ba4cd1b8cf463d6de0d2be,
title = "Computational analysis of the structural progression of human glomeruli in diabetic nephropathy",
abstract = "The glomerulus is the primary compartment of blood filtration in the kidney. It is a sphere of bundled, fenestrated capillaries that selectively allows solute loss. Structural damages to glomerular micro-compartments lead to physiological failures which influence filtration efficacy. The sole way to confirm glomerular structural damage in renal pathology is by examining histopathological or immunofluorescence stained needle biopsies under a light microscope. However, this method is extremely tedious and time consuming, and requires manual scoring on the number and volume of structures. Computational image analysis is the perfect tool to ease this burden. The major obstacle to development of digital histopathological quantification protocols for renal pathology is the extreme heterogeneity present within kidney tissue. Here we present an automated computational pipeline to 1) segment glomerular compartment boundaries and 2) quantify features of compartments, in healthy and diseased renal tissue. The segmentation involves a two stage process, one step for rough segmentation generation and another for refinement. Using a Na{\"i}ve Bayesian classifier on the resulting feature set, this method was able to distinguish pathological stage IIa from III with 0.89/0.93 sensitivity/specificity and stage IIb from III with 0.7/0.8 sensitivity/specificity, on n = 514 glomeruli taken from n = 13 human biopsies with diagnosed diabetic nephropathy, and n = 5 human renal tissues with no histological abnormalities. Our method will simplify computational partitioning of glomerular micro-compartments and subsequent quantification. We aim for our methods to ease manual labor associated with clinical diagnosis of renal disease.",
keywords = "Automated computation, Diabetic nephropathy, Digital quantification, Feature extraction, Glomerulus, Histology, Kidney, Na{\"i}ve Bayes, Segmentation",
author = "Ginley, {Brandon G.} and Tomaszewski, {John E.} and Kuang-Yu Jen and Agnes Fogo and Sanjay Jain and Pinaki Sarder",
year = "2018",
month = "1",
day = "1",
doi = "10.1117/12.2295249",
language = "English (US)",
volume = "10581",
booktitle = "Medical Imaging 2018",
publisher = "SPIE",

}

TY - GEN

T1 - Computational analysis of the structural progression of human glomeruli in diabetic nephropathy

AU - Ginley, Brandon G.

AU - Tomaszewski, John E.

AU - Jen, Kuang-Yu

AU - Fogo, Agnes

AU - Jain, Sanjay

AU - Sarder, Pinaki

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The glomerulus is the primary compartment of blood filtration in the kidney. It is a sphere of bundled, fenestrated capillaries that selectively allows solute loss. Structural damages to glomerular micro-compartments lead to physiological failures which influence filtration efficacy. The sole way to confirm glomerular structural damage in renal pathology is by examining histopathological or immunofluorescence stained needle biopsies under a light microscope. However, this method is extremely tedious and time consuming, and requires manual scoring on the number and volume of structures. Computational image analysis is the perfect tool to ease this burden. The major obstacle to development of digital histopathological quantification protocols for renal pathology is the extreme heterogeneity present within kidney tissue. Here we present an automated computational pipeline to 1) segment glomerular compartment boundaries and 2) quantify features of compartments, in healthy and diseased renal tissue. The segmentation involves a two stage process, one step for rough segmentation generation and another for refinement. Using a Naïve Bayesian classifier on the resulting feature set, this method was able to distinguish pathological stage IIa from III with 0.89/0.93 sensitivity/specificity and stage IIb from III with 0.7/0.8 sensitivity/specificity, on n = 514 glomeruli taken from n = 13 human biopsies with diagnosed diabetic nephropathy, and n = 5 human renal tissues with no histological abnormalities. Our method will simplify computational partitioning of glomerular micro-compartments and subsequent quantification. We aim for our methods to ease manual labor associated with clinical diagnosis of renal disease.

AB - The glomerulus is the primary compartment of blood filtration in the kidney. It is a sphere of bundled, fenestrated capillaries that selectively allows solute loss. Structural damages to glomerular micro-compartments lead to physiological failures which influence filtration efficacy. The sole way to confirm glomerular structural damage in renal pathology is by examining histopathological or immunofluorescence stained needle biopsies under a light microscope. However, this method is extremely tedious and time consuming, and requires manual scoring on the number and volume of structures. Computational image analysis is the perfect tool to ease this burden. The major obstacle to development of digital histopathological quantification protocols for renal pathology is the extreme heterogeneity present within kidney tissue. Here we present an automated computational pipeline to 1) segment glomerular compartment boundaries and 2) quantify features of compartments, in healthy and diseased renal tissue. The segmentation involves a two stage process, one step for rough segmentation generation and another for refinement. Using a Naïve Bayesian classifier on the resulting feature set, this method was able to distinguish pathological stage IIa from III with 0.89/0.93 sensitivity/specificity and stage IIb from III with 0.7/0.8 sensitivity/specificity, on n = 514 glomeruli taken from n = 13 human biopsies with diagnosed diabetic nephropathy, and n = 5 human renal tissues with no histological abnormalities. Our method will simplify computational partitioning of glomerular micro-compartments and subsequent quantification. We aim for our methods to ease manual labor associated with clinical diagnosis of renal disease.

KW - Automated computation

KW - Diabetic nephropathy

KW - Digital quantification

KW - Feature extraction

KW - Glomerulus

KW - Histology

KW - Kidney

KW - Naïve Bayes

KW - Segmentation

UR - http://www.scopus.com/inward/record.url?scp=85049215782&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049215782&partnerID=8YFLogxK

U2 - 10.1117/12.2295249

DO - 10.1117/12.2295249

M3 - Conference contribution

AN - SCOPUS:85049215782

VL - 10581

BT - Medical Imaging 2018

PB - SPIE

ER -