Evaluating IPMN and pancreatic carcinoma utilizing quantitative histopathology

Evan S. Glazer, Hao Zhang, Kimberly A. Hill, Charmi Patel, Stephanie T. Kha, Michael L. Yozwiak, Hubert Bartels, Nellie N. Nafissi, Joseph C Watkins, David S Alberts, Robert S Krouse

Research output: Contribution to journalArticle

Abstract

Intraductal papillary mucinous neoplasms (IPMN) are pancreatic lesions with uncertain biologic behavior. This study sought objective, accurate prediction tools, through the use of quantitative histopathological signatures of nuclear images, for classifying lesions as chronic pancreatitis (CP), IPMN, or pancreatic carcinoma (PC). Forty-four pancreatic resection patients were retrospectively identified for this study (12 CP; 16 IPMN; 16 PC). Regularized multinomial regression quantitatively classified each specimen as CP, IPMN, or PC in an automated, blinded fashion. Classification certainty was determined by subtracting the smallest classification probability from the largest probability (of the three groups). The certainty function varied from 1.0 (perfectly classified) to 0.0 (random). From each lesion, 180 ± 22 nuclei were imaged. Overall classification accuracy was 89.6% with six unique nuclear features. No CP cases were misclassified, 1/16 IPMN cases were misclassified, and 4/16 PC cases were misclassified. Certainty function was 0.75 ± 0.16 for correctly classified lesions and 0.47 ± 0.10 for incorrectly classified lesions (P = 0.0005). Uncertainty was identified in four of the five misclassified lesions. Quantitative histopathology provides a robust, novel method to distinguish among CP, IPMN, and PC with a quantitative measure of uncertainty. This may be useful when there is uncertainty in diagnosis.

Original languageEnglish (US)
Pages (from-to)2841-2847
Number of pages7
JournalCancer Medicine
Volume5
Issue number10
DOIs
StatePublished - Oct 1 2016

Fingerprint

Mucinous Adenocarcinoma
Papillary Carcinoma
Chronic Pancreatitis
Uncertainty
Neoplasms
Pancreatic Neoplasms
Pancreatic Carcinoma

Keywords

  • Intraductal papillary mucinous neoplasms
  • karyometry
  • nuclear chromatin pattern
  • pancreatic carcinoma
  • quantitative histopathology

ASJC Scopus subject areas

  • Oncology
  • Radiology Nuclear Medicine and imaging
  • Cancer Research

Cite this

Evaluating IPMN and pancreatic carcinoma utilizing quantitative histopathology. / Glazer, Evan S.; Zhang, Hao; Hill, Kimberly A.; Patel, Charmi; Kha, Stephanie T.; Yozwiak, Michael L.; Bartels, Hubert; Nafissi, Nellie N.; Watkins, Joseph C; Alberts, David S; Krouse, Robert S.

In: Cancer Medicine, Vol. 5, No. 10, 01.10.2016, p. 2841-2847.

Research output: Contribution to journalArticle

Glazer, ES, Zhang, H, Hill, KA, Patel, C, Kha, ST, Yozwiak, ML, Bartels, H, Nafissi, NN, Watkins, JC, Alberts, DS & Krouse, RS 2016, 'Evaluating IPMN and pancreatic carcinoma utilizing quantitative histopathology', Cancer Medicine, vol. 5, no. 10, pp. 2841-2847. https://doi.org/10.1002/cam4.923
Glazer, Evan S. ; Zhang, Hao ; Hill, Kimberly A. ; Patel, Charmi ; Kha, Stephanie T. ; Yozwiak, Michael L. ; Bartels, Hubert ; Nafissi, Nellie N. ; Watkins, Joseph C ; Alberts, David S ; Krouse, Robert S. / Evaluating IPMN and pancreatic carcinoma utilizing quantitative histopathology. In: Cancer Medicine. 2016 ; Vol. 5, No. 10. pp. 2841-2847.
@article{3f1c583864c44e69be1a9063ad1a647c,
title = "Evaluating IPMN and pancreatic carcinoma utilizing quantitative histopathology",
abstract = "Intraductal papillary mucinous neoplasms (IPMN) are pancreatic lesions with uncertain biologic behavior. This study sought objective, accurate prediction tools, through the use of quantitative histopathological signatures of nuclear images, for classifying lesions as chronic pancreatitis (CP), IPMN, or pancreatic carcinoma (PC). Forty-four pancreatic resection patients were retrospectively identified for this study (12 CP; 16 IPMN; 16 PC). Regularized multinomial regression quantitatively classified each specimen as CP, IPMN, or PC in an automated, blinded fashion. Classification certainty was determined by subtracting the smallest classification probability from the largest probability (of the three groups). The certainty function varied from 1.0 (perfectly classified) to 0.0 (random). From each lesion, 180 ± 22 nuclei were imaged. Overall classification accuracy was 89.6{\%} with six unique nuclear features. No CP cases were misclassified, 1/16 IPMN cases were misclassified, and 4/16 PC cases were misclassified. Certainty function was 0.75 ± 0.16 for correctly classified lesions and 0.47 ± 0.10 for incorrectly classified lesions (P = 0.0005). Uncertainty was identified in four of the five misclassified lesions. Quantitative histopathology provides a robust, novel method to distinguish among CP, IPMN, and PC with a quantitative measure of uncertainty. This may be useful when there is uncertainty in diagnosis.",
keywords = "Intraductal papillary mucinous neoplasms, karyometry, nuclear chromatin pattern, pancreatic carcinoma, quantitative histopathology",
author = "Glazer, {Evan S.} and Hao Zhang and Hill, {Kimberly A.} and Charmi Patel and Kha, {Stephanie T.} and Yozwiak, {Michael L.} and Hubert Bartels and Nafissi, {Nellie N.} and Watkins, {Joseph C} and Alberts, {David S} and Krouse, {Robert S}",
year = "2016",
month = "10",
day = "1",
doi = "10.1002/cam4.923",
language = "English (US)",
volume = "5",
pages = "2841--2847",
journal = "Cancer Medicine",
issn = "2045-7634",
publisher = "John Wiley and Sons Ltd",
number = "10",

}

TY - JOUR

T1 - Evaluating IPMN and pancreatic carcinoma utilizing quantitative histopathology

AU - Glazer, Evan S.

AU - Zhang, Hao

AU - Hill, Kimberly A.

AU - Patel, Charmi

AU - Kha, Stephanie T.

AU - Yozwiak, Michael L.

AU - Bartels, Hubert

AU - Nafissi, Nellie N.

AU - Watkins, Joseph C

AU - Alberts, David S

AU - Krouse, Robert S

PY - 2016/10/1

Y1 - 2016/10/1

N2 - Intraductal papillary mucinous neoplasms (IPMN) are pancreatic lesions with uncertain biologic behavior. This study sought objective, accurate prediction tools, through the use of quantitative histopathological signatures of nuclear images, for classifying lesions as chronic pancreatitis (CP), IPMN, or pancreatic carcinoma (PC). Forty-four pancreatic resection patients were retrospectively identified for this study (12 CP; 16 IPMN; 16 PC). Regularized multinomial regression quantitatively classified each specimen as CP, IPMN, or PC in an automated, blinded fashion. Classification certainty was determined by subtracting the smallest classification probability from the largest probability (of the three groups). The certainty function varied from 1.0 (perfectly classified) to 0.0 (random). From each lesion, 180 ± 22 nuclei were imaged. Overall classification accuracy was 89.6% with six unique nuclear features. No CP cases were misclassified, 1/16 IPMN cases were misclassified, and 4/16 PC cases were misclassified. Certainty function was 0.75 ± 0.16 for correctly classified lesions and 0.47 ± 0.10 for incorrectly classified lesions (P = 0.0005). Uncertainty was identified in four of the five misclassified lesions. Quantitative histopathology provides a robust, novel method to distinguish among CP, IPMN, and PC with a quantitative measure of uncertainty. This may be useful when there is uncertainty in diagnosis.

AB - Intraductal papillary mucinous neoplasms (IPMN) are pancreatic lesions with uncertain biologic behavior. This study sought objective, accurate prediction tools, through the use of quantitative histopathological signatures of nuclear images, for classifying lesions as chronic pancreatitis (CP), IPMN, or pancreatic carcinoma (PC). Forty-four pancreatic resection patients were retrospectively identified for this study (12 CP; 16 IPMN; 16 PC). Regularized multinomial regression quantitatively classified each specimen as CP, IPMN, or PC in an automated, blinded fashion. Classification certainty was determined by subtracting the smallest classification probability from the largest probability (of the three groups). The certainty function varied from 1.0 (perfectly classified) to 0.0 (random). From each lesion, 180 ± 22 nuclei were imaged. Overall classification accuracy was 89.6% with six unique nuclear features. No CP cases were misclassified, 1/16 IPMN cases were misclassified, and 4/16 PC cases were misclassified. Certainty function was 0.75 ± 0.16 for correctly classified lesions and 0.47 ± 0.10 for incorrectly classified lesions (P = 0.0005). Uncertainty was identified in four of the five misclassified lesions. Quantitative histopathology provides a robust, novel method to distinguish among CP, IPMN, and PC with a quantitative measure of uncertainty. This may be useful when there is uncertainty in diagnosis.

KW - Intraductal papillary mucinous neoplasms

KW - karyometry

KW - nuclear chromatin pattern

KW - pancreatic carcinoma

KW - quantitative histopathology

UR - http://www.scopus.com/inward/record.url?scp=84988848363&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988848363&partnerID=8YFLogxK

U2 - 10.1002/cam4.923

DO - 10.1002/cam4.923

M3 - Article

C2 - 27666740

AN - SCOPUS:84988848363

VL - 5

SP - 2841

EP - 2847

JO - Cancer Medicine

JF - Cancer Medicine

SN - 2045-7634

IS - 10

ER -