Automatic glomerulus extraction in whole slide images towards computer aided diagnosis

Yan Zhao, Edgar F. Black, Luigi Marini, Kenton McHenry, Norma S Kenyon, Rachana Patil, Andre Balla, Amelia Bartholomew

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

6 Citations (Scopus)

Abstract

Renal biopsies form the gold standard of diagnostic and prognostic assessments of renal transplants. With the addition of new quantitative strategies to supplement renal biopsy interpretation such as gene array and metabolomics, the capability to incorporate all quantitative measures for clinical interpretation will require multi-dimensional analyses. Currently, renal biopsies are analyzed manually; the quantitative features of pathology observed on the biopsies are limited to hand counts. Standardized, automated detection of pathology observed in a kidney transplant biopsy will enable the input of these digital images alongside other quantitative measures of new technologies, with potential gains in precision in patient care. We investigate a learning framework to detect pathological changes in biopsy image that addresses two main issues: the inadequate training set and the significant diversity of color and tissue shape on whole slide images. Two case studies, automatic detection of interstitial inflammation and tubular cast, are presented in this work. Afterwards, we propose a fully automated glomerulus extraction framework on micrograph of entire renal tissue, focusing on extracting Bowman's capsule, the supportive structure of glomeruli. Statistical approaches are also introduced to further improve the performance. Human expert annotations of interstitial inflammation and tubular casts in 10 H&E stained renal tissues of nonhuman primates and more than 100 glomeruli are used to demonstrate the superior performance of the proposed algorithm over existing solutions.

Original languageEnglish (US)
Title of host publicationProceedings of the 2016 IEEE 12th International Conference on e-Science, e-Science 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages165-174
Number of pages10
ISBN (Electronic)9781509042722
DOIs
StatePublished - Mar 3 2017
Event12th IEEE International Conference on e-Science, e-Science 2016 - Baltimore, United States
Duration: Oct 23 2016Oct 27 2016

Other

Other12th IEEE International Conference on e-Science, e-Science 2016
CountryUnited States
CityBaltimore
Period10/23/1610/27/16

Fingerprint

interstitial
Computer aided diagnosis
Biopsy
pathology
biopsy
Kidney
kidneys
interpretation
gold standard
patient care
supplement
performance
new technology
kidney transplant
Transplants
diagnostic
Pathology
expert
Tissue
digital image

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Environmental Science (miscellaneous)
  • Medicine (miscellaneous)
  • Social Sciences (miscellaneous)
  • Agricultural and Biological Sciences (miscellaneous)
  • Computer Science Applications

Cite this

Zhao, Y., Black, E. F., Marini, L., McHenry, K., Kenyon, N. S., Patil, R., ... Bartholomew, A. (2017). Automatic glomerulus extraction in whole slide images towards computer aided diagnosis. In Proceedings of the 2016 IEEE 12th International Conference on e-Science, e-Science 2016 (pp. 165-174). [7870897] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/eScience.2016.7870897

Automatic glomerulus extraction in whole slide images towards computer aided diagnosis. / Zhao, Yan; Black, Edgar F.; Marini, Luigi; McHenry, Kenton; Kenyon, Norma S; Patil, Rachana; Balla, Andre; Bartholomew, Amelia.

Proceedings of the 2016 IEEE 12th International Conference on e-Science, e-Science 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 165-174 7870897.

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

Zhao, Y, Black, EF, Marini, L, McHenry, K, Kenyon, NS, Patil, R, Balla, A & Bartholomew, A 2017, Automatic glomerulus extraction in whole slide images towards computer aided diagnosis. in Proceedings of the 2016 IEEE 12th International Conference on e-Science, e-Science 2016., 7870897, Institute of Electrical and Electronics Engineers Inc., pp. 165-174, 12th IEEE International Conference on e-Science, e-Science 2016, Baltimore, United States, 10/23/16. https://doi.org/10.1109/eScience.2016.7870897
Zhao Y, Black EF, Marini L, McHenry K, Kenyon NS, Patil R et al. Automatic glomerulus extraction in whole slide images towards computer aided diagnosis. In Proceedings of the 2016 IEEE 12th International Conference on e-Science, e-Science 2016. Institute of Electrical and Electronics Engineers Inc. 2017. p. 165-174. 7870897 https://doi.org/10.1109/eScience.2016.7870897
Zhao, Yan ; Black, Edgar F. ; Marini, Luigi ; McHenry, Kenton ; Kenyon, Norma S ; Patil, Rachana ; Balla, Andre ; Bartholomew, Amelia. / Automatic glomerulus extraction in whole slide images towards computer aided diagnosis. Proceedings of the 2016 IEEE 12th International Conference on e-Science, e-Science 2016. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 165-174
@inproceedings{456baea7fe254072a079cd208e9686aa,
title = "Automatic glomerulus extraction in whole slide images towards computer aided diagnosis",
abstract = "Renal biopsies form the gold standard of diagnostic and prognostic assessments of renal transplants. With the addition of new quantitative strategies to supplement renal biopsy interpretation such as gene array and metabolomics, the capability to incorporate all quantitative measures for clinical interpretation will require multi-dimensional analyses. Currently, renal biopsies are analyzed manually; the quantitative features of pathology observed on the biopsies are limited to hand counts. Standardized, automated detection of pathology observed in a kidney transplant biopsy will enable the input of these digital images alongside other quantitative measures of new technologies, with potential gains in precision in patient care. We investigate a learning framework to detect pathological changes in biopsy image that addresses two main issues: the inadequate training set and the significant diversity of color and tissue shape on whole slide images. Two case studies, automatic detection of interstitial inflammation and tubular cast, are presented in this work. Afterwards, we propose a fully automated glomerulus extraction framework on micrograph of entire renal tissue, focusing on extracting Bowman's capsule, the supportive structure of glomeruli. Statistical approaches are also introduced to further improve the performance. Human expert annotations of interstitial inflammation and tubular casts in 10 H&E stained renal tissues of nonhuman primates and more than 100 glomeruli are used to demonstrate the superior performance of the proposed algorithm over existing solutions.",
author = "Yan Zhao and Black, {Edgar F.} and Luigi Marini and Kenton McHenry and Kenyon, {Norma S} and Rachana Patil and Andre Balla and Amelia Bartholomew",
year = "2017",
month = "3",
day = "3",
doi = "10.1109/eScience.2016.7870897",
language = "English (US)",
pages = "165--174",
booktitle = "Proceedings of the 2016 IEEE 12th International Conference on e-Science, e-Science 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Automatic glomerulus extraction in whole slide images towards computer aided diagnosis

AU - Zhao, Yan

AU - Black, Edgar F.

AU - Marini, Luigi

AU - McHenry, Kenton

AU - Kenyon, Norma S

AU - Patil, Rachana

AU - Balla, Andre

AU - Bartholomew, Amelia

PY - 2017/3/3

Y1 - 2017/3/3

N2 - Renal biopsies form the gold standard of diagnostic and prognostic assessments of renal transplants. With the addition of new quantitative strategies to supplement renal biopsy interpretation such as gene array and metabolomics, the capability to incorporate all quantitative measures for clinical interpretation will require multi-dimensional analyses. Currently, renal biopsies are analyzed manually; the quantitative features of pathology observed on the biopsies are limited to hand counts. Standardized, automated detection of pathology observed in a kidney transplant biopsy will enable the input of these digital images alongside other quantitative measures of new technologies, with potential gains in precision in patient care. We investigate a learning framework to detect pathological changes in biopsy image that addresses two main issues: the inadequate training set and the significant diversity of color and tissue shape on whole slide images. Two case studies, automatic detection of interstitial inflammation and tubular cast, are presented in this work. Afterwards, we propose a fully automated glomerulus extraction framework on micrograph of entire renal tissue, focusing on extracting Bowman's capsule, the supportive structure of glomeruli. Statistical approaches are also introduced to further improve the performance. Human expert annotations of interstitial inflammation and tubular casts in 10 H&E stained renal tissues of nonhuman primates and more than 100 glomeruli are used to demonstrate the superior performance of the proposed algorithm over existing solutions.

AB - Renal biopsies form the gold standard of diagnostic and prognostic assessments of renal transplants. With the addition of new quantitative strategies to supplement renal biopsy interpretation such as gene array and metabolomics, the capability to incorporate all quantitative measures for clinical interpretation will require multi-dimensional analyses. Currently, renal biopsies are analyzed manually; the quantitative features of pathology observed on the biopsies are limited to hand counts. Standardized, automated detection of pathology observed in a kidney transplant biopsy will enable the input of these digital images alongside other quantitative measures of new technologies, with potential gains in precision in patient care. We investigate a learning framework to detect pathological changes in biopsy image that addresses two main issues: the inadequate training set and the significant diversity of color and tissue shape on whole slide images. Two case studies, automatic detection of interstitial inflammation and tubular cast, are presented in this work. Afterwards, we propose a fully automated glomerulus extraction framework on micrograph of entire renal tissue, focusing on extracting Bowman's capsule, the supportive structure of glomeruli. Statistical approaches are also introduced to further improve the performance. Human expert annotations of interstitial inflammation and tubular casts in 10 H&E stained renal tissues of nonhuman primates and more than 100 glomeruli are used to demonstrate the superior performance of the proposed algorithm over existing solutions.

UR - http://www.scopus.com/inward/record.url?scp=85016756559&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016756559&partnerID=8YFLogxK

U2 - 10.1109/eScience.2016.7870897

DO - 10.1109/eScience.2016.7870897

M3 - Conference contribution

AN - SCOPUS:85016756559

SP - 165

EP - 174

BT - Proceedings of the 2016 IEEE 12th International Conference on e-Science, e-Science 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -