Detection of malignancy in cytology specimens using spectral-spatial analysis

Cesar Angeletti, Neal R. Harvey, Vitali Khomitch, Andrew H. Fischer, Richard M Levenson, David L. Rimm

Research output: Contribution to journalArticle

24 Citations (Scopus)

Abstract

Despite low sensitivity (around 60%), cytomorphologic examination of urine specimens represents the standard procedure in the diagnosis and follow-up of bladder cancer. Although color is information-rich, morphologic diagnoses are rendered almost exclusively on the basis of spatial information. We hypothesized that quantitative assessment of color (more precisely, of spectral properties) using liquid crystal-based spectral fractionation, combined with genetic algorithm-based spatial analysis, can improve the accuracy of traditional cytologic examination. Images of various cytological specimens were collected every 10 nm from 400 to 700 nm to create an image stack. The resulting data sets were analyzed using the Los Alamos-developed GENetic Imagery Exploitation (GENIE) package, a hybrid genetic algorithm that segments (classifies) images using automatically 'learned' spatio-spectral features. In an evolutionary fashion, GENIE generates a series of algorithms or 'chromosomes', keeping the one with best fitness with respect to a user-defined training set. First, we tested the system to determine if it could recognize malignant cells using artificial cytology specimens constructed to completely avoid the requirement for human interpretation. GENIE was able to differentiate malignant from benign cells and to estimate their relative proportions in controlled mixtures. We then tested the system on routine cytology specimens. When targeted to detect malignant urothelial cells in cytology specimens, GENIE showed a combined sensitivity and specificity of 85 and 95%, in samples drawn from two separate institutions over a span of 4 years. When trained on cases initially diagnosed as 'atypical' but with unequivocal follow-up by biopsy, surgical specimen or cytology, GENIE showed efficiency superior to the cytopathologist with respect to predicting the follow-up result in a cohort of 85 cases. We believe that, in future, this type of methodology could be used as an ancillary test in cytopathology, in a manner analogous to immunostaining, in those situations when a definitive diagnosis cannot be rendered based solely on the morphology.

Original languageEnglish (US)
Pages (from-to)1555-1564
Number of pages10
JournalLaboratory Investigation
Volume85
Issue number12
DOIs
StatePublished - Dec 2005
Externally publishedYes

Fingerprint

Spatial Analysis
Imagery (Psychotherapy)
Cell Biology
Neoplasms
Color
Artificial Cells
Liquid Crystals
Urinary Bladder Neoplasms
Chromosomes
Urine
Biopsy
Sensitivity and Specificity

Keywords

  • Atypical
  • Bladder
  • Cytopathology
  • Genetic algorithm
  • Urine

ASJC Scopus subject areas

  • Pathology and Forensic Medicine

Cite this

Detection of malignancy in cytology specimens using spectral-spatial analysis. / Angeletti, Cesar; Harvey, Neal R.; Khomitch, Vitali; Fischer, Andrew H.; Levenson, Richard M; Rimm, David L.

In: Laboratory Investigation, Vol. 85, No. 12, 12.2005, p. 1555-1564.

Research output: Contribution to journalArticle

Angeletti, C, Harvey, NR, Khomitch, V, Fischer, AH, Levenson, RM & Rimm, DL 2005, 'Detection of malignancy in cytology specimens using spectral-spatial analysis', Laboratory Investigation, vol. 85, no. 12, pp. 1555-1564. https://doi.org/10.1038/labinvest.3700357
Angeletti, Cesar ; Harvey, Neal R. ; Khomitch, Vitali ; Fischer, Andrew H. ; Levenson, Richard M ; Rimm, David L. / Detection of malignancy in cytology specimens using spectral-spatial analysis. In: Laboratory Investigation. 2005 ; Vol. 85, No. 12. pp. 1555-1564.
@article{d90b43c0d59748b69f84a50c521bce84,
title = "Detection of malignancy in cytology specimens using spectral-spatial analysis",
abstract = "Despite low sensitivity (around 60{\%}), cytomorphologic examination of urine specimens represents the standard procedure in the diagnosis and follow-up of bladder cancer. Although color is information-rich, morphologic diagnoses are rendered almost exclusively on the basis of spatial information. We hypothesized that quantitative assessment of color (more precisely, of spectral properties) using liquid crystal-based spectral fractionation, combined with genetic algorithm-based spatial analysis, can improve the accuracy of traditional cytologic examination. Images of various cytological specimens were collected every 10 nm from 400 to 700 nm to create an image stack. The resulting data sets were analyzed using the Los Alamos-developed GENetic Imagery Exploitation (GENIE) package, a hybrid genetic algorithm that segments (classifies) images using automatically 'learned' spatio-spectral features. In an evolutionary fashion, GENIE generates a series of algorithms or 'chromosomes', keeping the one with best fitness with respect to a user-defined training set. First, we tested the system to determine if it could recognize malignant cells using artificial cytology specimens constructed to completely avoid the requirement for human interpretation. GENIE was able to differentiate malignant from benign cells and to estimate their relative proportions in controlled mixtures. We then tested the system on routine cytology specimens. When targeted to detect malignant urothelial cells in cytology specimens, GENIE showed a combined sensitivity and specificity of 85 and 95{\%}, in samples drawn from two separate institutions over a span of 4 years. When trained on cases initially diagnosed as 'atypical' but with unequivocal follow-up by biopsy, surgical specimen or cytology, GENIE showed efficiency superior to the cytopathologist with respect to predicting the follow-up result in a cohort of 85 cases. We believe that, in future, this type of methodology could be used as an ancillary test in cytopathology, in a manner analogous to immunostaining, in those situations when a definitive diagnosis cannot be rendered based solely on the morphology.",
keywords = "Atypical, Bladder, Cytopathology, Genetic algorithm, Urine",
author = "Cesar Angeletti and Harvey, {Neal R.} and Vitali Khomitch and Fischer, {Andrew H.} and Levenson, {Richard M} and Rimm, {David L.}",
year = "2005",
month = "12",
doi = "10.1038/labinvest.3700357",
language = "English (US)",
volume = "85",
pages = "1555--1564",
journal = "Laboratory Investigation",
issn = "0023-6837",
publisher = "Nature Publishing Group",
number = "12",

}

TY - JOUR

T1 - Detection of malignancy in cytology specimens using spectral-spatial analysis

AU - Angeletti, Cesar

AU - Harvey, Neal R.

AU - Khomitch, Vitali

AU - Fischer, Andrew H.

AU - Levenson, Richard M

AU - Rimm, David L.

PY - 2005/12

Y1 - 2005/12

N2 - Despite low sensitivity (around 60%), cytomorphologic examination of urine specimens represents the standard procedure in the diagnosis and follow-up of bladder cancer. Although color is information-rich, morphologic diagnoses are rendered almost exclusively on the basis of spatial information. We hypothesized that quantitative assessment of color (more precisely, of spectral properties) using liquid crystal-based spectral fractionation, combined with genetic algorithm-based spatial analysis, can improve the accuracy of traditional cytologic examination. Images of various cytological specimens were collected every 10 nm from 400 to 700 nm to create an image stack. The resulting data sets were analyzed using the Los Alamos-developed GENetic Imagery Exploitation (GENIE) package, a hybrid genetic algorithm that segments (classifies) images using automatically 'learned' spatio-spectral features. In an evolutionary fashion, GENIE generates a series of algorithms or 'chromosomes', keeping the one with best fitness with respect to a user-defined training set. First, we tested the system to determine if it could recognize malignant cells using artificial cytology specimens constructed to completely avoid the requirement for human interpretation. GENIE was able to differentiate malignant from benign cells and to estimate their relative proportions in controlled mixtures. We then tested the system on routine cytology specimens. When targeted to detect malignant urothelial cells in cytology specimens, GENIE showed a combined sensitivity and specificity of 85 and 95%, in samples drawn from two separate institutions over a span of 4 years. When trained on cases initially diagnosed as 'atypical' but with unequivocal follow-up by biopsy, surgical specimen or cytology, GENIE showed efficiency superior to the cytopathologist with respect to predicting the follow-up result in a cohort of 85 cases. We believe that, in future, this type of methodology could be used as an ancillary test in cytopathology, in a manner analogous to immunostaining, in those situations when a definitive diagnosis cannot be rendered based solely on the morphology.

AB - Despite low sensitivity (around 60%), cytomorphologic examination of urine specimens represents the standard procedure in the diagnosis and follow-up of bladder cancer. Although color is information-rich, morphologic diagnoses are rendered almost exclusively on the basis of spatial information. We hypothesized that quantitative assessment of color (more precisely, of spectral properties) using liquid crystal-based spectral fractionation, combined with genetic algorithm-based spatial analysis, can improve the accuracy of traditional cytologic examination. Images of various cytological specimens were collected every 10 nm from 400 to 700 nm to create an image stack. The resulting data sets were analyzed using the Los Alamos-developed GENetic Imagery Exploitation (GENIE) package, a hybrid genetic algorithm that segments (classifies) images using automatically 'learned' spatio-spectral features. In an evolutionary fashion, GENIE generates a series of algorithms or 'chromosomes', keeping the one with best fitness with respect to a user-defined training set. First, we tested the system to determine if it could recognize malignant cells using artificial cytology specimens constructed to completely avoid the requirement for human interpretation. GENIE was able to differentiate malignant from benign cells and to estimate their relative proportions in controlled mixtures. We then tested the system on routine cytology specimens. When targeted to detect malignant urothelial cells in cytology specimens, GENIE showed a combined sensitivity and specificity of 85 and 95%, in samples drawn from two separate institutions over a span of 4 years. When trained on cases initially diagnosed as 'atypical' but with unequivocal follow-up by biopsy, surgical specimen or cytology, GENIE showed efficiency superior to the cytopathologist with respect to predicting the follow-up result in a cohort of 85 cases. We believe that, in future, this type of methodology could be used as an ancillary test in cytopathology, in a manner analogous to immunostaining, in those situations when a definitive diagnosis cannot be rendered based solely on the morphology.

KW - Atypical

KW - Bladder

KW - Cytopathology

KW - Genetic algorithm

KW - Urine

UR - http://www.scopus.com/inward/record.url?scp=27944504371&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27944504371&partnerID=8YFLogxK

U2 - 10.1038/labinvest.3700357

DO - 10.1038/labinvest.3700357

M3 - Article

C2 - 16200074

AN - SCOPUS:27944504371

VL - 85

SP - 1555

EP - 1564

JO - Laboratory Investigation

JF - Laboratory Investigation

SN - 0023-6837

IS - 12

ER -