Computer-based image analysis of liver steatosis with large-scale microscopy imagery and correlation with magnetic resonance imaging lipid analysis

Jun Kong, Michael J. Lee, Pelin Bagci, Puneet Sharma, Diego R Martin, N. Volkan Adsay, Joel H. Saltz, Alton B. Farris

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

12 Citations (Scopus)

Abstract

Most pathology analyses and measurements are prevalently carried out by trained reviewers in both clinical and research settings. Therefore, the resulting outputs are inexorably biased by interpreters and degraded with poor reproducibility. In this paper, we propose a computerized image analysis paradigm enabling quantitative characterizations of steatosis areas in microscopy images of pediatric liver biopsies. With the same set of patients, we also acquired the lipid measurements from magnetic resonance imaging data analysis for correlation investigation. Our preliminary results suggest a high correlation between the steatosis areas quantized with microscopy images and the lipid percentages calculated from radiology imaging data. Additionally, we compared the performance of the proposed analysis method with those of three certified pathologists and a popular commercial algorithm. The results suggest the superiority of our method to both human reviewers and the commercial method in terms of the steatosis-lipid correlation strength. This demonstrates that the developed method is promising for generating quantitative and reliable analysis results to better support further liver disease study.

Original languageEnglish (US)
Title of host publicationProceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011
Pages333-338
Number of pages6
DOIs
StatePublished - 2011
Externally publishedYes
Event2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011 - Atlanta, GA, United States
Duration: Nov 12 2011Nov 15 2011

Other

Other2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011
CountryUnited States
CityAtlanta, GA
Period11/12/1111/15/11

Fingerprint

Imagery (Psychotherapy)
Fatty Liver
Magnetic resonance
Liver
Image analysis
Lipids
Microscopy
Microscopic examination
Magnetic Resonance Imaging
Imaging techniques
Pediatrics
Radiology
Biopsy
Pathology
Liver Diseases
Research

Keywords

  • Data correlation
  • Large-scale microscopy image analysis
  • Liver steatosis quantification
  • Parallel computation
  • Tissue representation

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Kong, J., Lee, M. J., Bagci, P., Sharma, P., Martin, D. R., Adsay, N. V., ... Farris, A. B. (2011). Computer-based image analysis of liver steatosis with large-scale microscopy imagery and correlation with magnetic resonance imaging lipid analysis. In Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011 (pp. 333-338). [6120462] https://doi.org/10.1109/BIBM.2011.37

Computer-based image analysis of liver steatosis with large-scale microscopy imagery and correlation with magnetic resonance imaging lipid analysis. / Kong, Jun; Lee, Michael J.; Bagci, Pelin; Sharma, Puneet; Martin, Diego R; Adsay, N. Volkan; Saltz, Joel H.; Farris, Alton B.

Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. p. 333-338 6120462.

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

Kong, J, Lee, MJ, Bagci, P, Sharma, P, Martin, DR, Adsay, NV, Saltz, JH & Farris, AB 2011, Computer-based image analysis of liver steatosis with large-scale microscopy imagery and correlation with magnetic resonance imaging lipid analysis. in Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011., 6120462, pp. 333-338, 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011, Atlanta, GA, United States, 11/12/11. https://doi.org/10.1109/BIBM.2011.37
Kong J, Lee MJ, Bagci P, Sharma P, Martin DR, Adsay NV et al. Computer-based image analysis of liver steatosis with large-scale microscopy imagery and correlation with magnetic resonance imaging lipid analysis. In Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. p. 333-338. 6120462 https://doi.org/10.1109/BIBM.2011.37
Kong, Jun ; Lee, Michael J. ; Bagci, Pelin ; Sharma, Puneet ; Martin, Diego R ; Adsay, N. Volkan ; Saltz, Joel H. ; Farris, Alton B. / Computer-based image analysis of liver steatosis with large-scale microscopy imagery and correlation with magnetic resonance imaging lipid analysis. Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011. 2011. pp. 333-338
@inproceedings{1f2c51e5cd744b8eae58ab29cbe189ae,
title = "Computer-based image analysis of liver steatosis with large-scale microscopy imagery and correlation with magnetic resonance imaging lipid analysis",
abstract = "Most pathology analyses and measurements are prevalently carried out by trained reviewers in both clinical and research settings. Therefore, the resulting outputs are inexorably biased by interpreters and degraded with poor reproducibility. In this paper, we propose a computerized image analysis paradigm enabling quantitative characterizations of steatosis areas in microscopy images of pediatric liver biopsies. With the same set of patients, we also acquired the lipid measurements from magnetic resonance imaging data analysis for correlation investigation. Our preliminary results suggest a high correlation between the steatosis areas quantized with microscopy images and the lipid percentages calculated from radiology imaging data. Additionally, we compared the performance of the proposed analysis method with those of three certified pathologists and a popular commercial algorithm. The results suggest the superiority of our method to both human reviewers and the commercial method in terms of the steatosis-lipid correlation strength. This demonstrates that the developed method is promising for generating quantitative and reliable analysis results to better support further liver disease study.",
keywords = "Data correlation, Large-scale microscopy image analysis, Liver steatosis quantification, Parallel computation, Tissue representation",
author = "Jun Kong and Lee, {Michael J.} and Pelin Bagci and Puneet Sharma and Martin, {Diego R} and Adsay, {N. Volkan} and Saltz, {Joel H.} and Farris, {Alton B.}",
year = "2011",
doi = "10.1109/BIBM.2011.37",
language = "English (US)",
isbn = "9780769545745",
pages = "333--338",
booktitle = "Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011",

}

TY - GEN

T1 - Computer-based image analysis of liver steatosis with large-scale microscopy imagery and correlation with magnetic resonance imaging lipid analysis

AU - Kong, Jun

AU - Lee, Michael J.

AU - Bagci, Pelin

AU - Sharma, Puneet

AU - Martin, Diego R

AU - Adsay, N. Volkan

AU - Saltz, Joel H.

AU - Farris, Alton B.

PY - 2011

Y1 - 2011

N2 - Most pathology analyses and measurements are prevalently carried out by trained reviewers in both clinical and research settings. Therefore, the resulting outputs are inexorably biased by interpreters and degraded with poor reproducibility. In this paper, we propose a computerized image analysis paradigm enabling quantitative characterizations of steatosis areas in microscopy images of pediatric liver biopsies. With the same set of patients, we also acquired the lipid measurements from magnetic resonance imaging data analysis for correlation investigation. Our preliminary results suggest a high correlation between the steatosis areas quantized with microscopy images and the lipid percentages calculated from radiology imaging data. Additionally, we compared the performance of the proposed analysis method with those of three certified pathologists and a popular commercial algorithm. The results suggest the superiority of our method to both human reviewers and the commercial method in terms of the steatosis-lipid correlation strength. This demonstrates that the developed method is promising for generating quantitative and reliable analysis results to better support further liver disease study.

AB - Most pathology analyses and measurements are prevalently carried out by trained reviewers in both clinical and research settings. Therefore, the resulting outputs are inexorably biased by interpreters and degraded with poor reproducibility. In this paper, we propose a computerized image analysis paradigm enabling quantitative characterizations of steatosis areas in microscopy images of pediatric liver biopsies. With the same set of patients, we also acquired the lipid measurements from magnetic resonance imaging data analysis for correlation investigation. Our preliminary results suggest a high correlation between the steatosis areas quantized with microscopy images and the lipid percentages calculated from radiology imaging data. Additionally, we compared the performance of the proposed analysis method with those of three certified pathologists and a popular commercial algorithm. The results suggest the superiority of our method to both human reviewers and the commercial method in terms of the steatosis-lipid correlation strength. This demonstrates that the developed method is promising for generating quantitative and reliable analysis results to better support further liver disease study.

KW - Data correlation

KW - Large-scale microscopy image analysis

KW - Liver steatosis quantification

KW - Parallel computation

KW - Tissue representation

UR - http://www.scopus.com/inward/record.url?scp=84862960386&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862960386&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2011.37

DO - 10.1109/BIBM.2011.37

M3 - Conference contribution

SN - 9780769545745

SP - 333

EP - 338

BT - Proceedings - 2011 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2011

ER -