Computer-assisted measurement of primary tumor area is prognostic of recurrence-free survival in stage IB melanoma patients

Brooke E. Rosenbaum, Christine N. Schafer, Sung Won Han, Iman Osman, Hua Zhong, Nooshin Brinster

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Current staging guidelines are insufficient to predict which patients with thin primary melanoma are at high risk of recurrence. Computer-assisted image analysis may allow for more practical and objective histopathological analysis of primary tumors than traditional light microscopy. We studied a prospective cohort of stage IB melanoma patients treated at NYU Langone Medical Center from 2002 to 2014. Primary tumor width, manual area, digital area, and conformation were evaluated in a patient subset via computer-assisted image analysis. The associations between histologic variables and survival were evaluated using Cox proportional hazards model. Logistic regressions were used to build a classifier with clinicopathological characteristics to predict recurrence status. Of the 655 patients with stage IB melanoma studied, a subset of 149 patient tumors (63 recurred, 86 did not recur) underwent computer-assisted histopathological analysis. Increasing tumor width (hazard ratios (HR): 1.17, P=0.01) and digital area (HR: 1.08, P<0.01) were significantly associated with worse recurrence-free survival, whereas non-contiguous conformation (HR: 0.57, P=0.05) was significantly associated with better recurrence-free survival. The novel histopathological classifier composed of digital area, conformation, and baseline variables effectively distinguished recurrent cases from non-recurrent cases (AUC: 0.733, 95% confidence interval (CI): 0.647-0.818), compared to the baseline classifier alone (AUC: 0.635, 95% CI: 0.545-0.724). Primary tumor cross-sectional area, width, and conformation measured via computer-assisted analysis may help identify high-risk patients with stage IB melanoma.

Original languageEnglish
Pages (from-to)1402-1410
Number of pages9
JournalModern Pathology
Volume30
Issue number10
DOIs
Publication statusPublished - 2017 Oct 1

Fingerprint

Melanoma
Recurrence
Survival
Neoplasms
Computer-Assisted Image Processing
Area Under Curve
Confidence Intervals
Proportional Hazards Models
Microscopy
Logistic Models
Guidelines
Light

ASJC Scopus subject areas

  • Pathology and Forensic Medicine

Cite this

Computer-assisted measurement of primary tumor area is prognostic of recurrence-free survival in stage IB melanoma patients. / Rosenbaum, Brooke E.; Schafer, Christine N.; Han, Sung Won; Osman, Iman; Zhong, Hua; Brinster, Nooshin.

In: Modern Pathology, Vol. 30, No. 10, 01.10.2017, p. 1402-1410.

Research output: Contribution to journalArticle

Rosenbaum, Brooke E. ; Schafer, Christine N. ; Han, Sung Won ; Osman, Iman ; Zhong, Hua ; Brinster, Nooshin. / Computer-assisted measurement of primary tumor area is prognostic of recurrence-free survival in stage IB melanoma patients. In: Modern Pathology. 2017 ; Vol. 30, No. 10. pp. 1402-1410.
@article{395f9ecbacd54e789df67414febbb4d6,
title = "Computer-assisted measurement of primary tumor area is prognostic of recurrence-free survival in stage IB melanoma patients",
abstract = "Current staging guidelines are insufficient to predict which patients with thin primary melanoma are at high risk of recurrence. Computer-assisted image analysis may allow for more practical and objective histopathological analysis of primary tumors than traditional light microscopy. We studied a prospective cohort of stage IB melanoma patients treated at NYU Langone Medical Center from 2002 to 2014. Primary tumor width, manual area, digital area, and conformation were evaluated in a patient subset via computer-assisted image analysis. The associations between histologic variables and survival were evaluated using Cox proportional hazards model. Logistic regressions were used to build a classifier with clinicopathological characteristics to predict recurrence status. Of the 655 patients with stage IB melanoma studied, a subset of 149 patient tumors (63 recurred, 86 did not recur) underwent computer-assisted histopathological analysis. Increasing tumor width (hazard ratios (HR): 1.17, P=0.01) and digital area (HR: 1.08, P<0.01) were significantly associated with worse recurrence-free survival, whereas non-contiguous conformation (HR: 0.57, P=0.05) was significantly associated with better recurrence-free survival. The novel histopathological classifier composed of digital area, conformation, and baseline variables effectively distinguished recurrent cases from non-recurrent cases (AUC: 0.733, 95{\%} confidence interval (CI): 0.647-0.818), compared to the baseline classifier alone (AUC: 0.635, 95{\%} CI: 0.545-0.724). Primary tumor cross-sectional area, width, and conformation measured via computer-assisted analysis may help identify high-risk patients with stage IB melanoma.",
author = "Rosenbaum, {Brooke E.} and Schafer, {Christine N.} and Han, {Sung Won} and Iman Osman and Hua Zhong and Nooshin Brinster",
year = "2017",
month = "10",
day = "1",
doi = "10.1038/modpathol.2017.64",
language = "English",
volume = "30",
pages = "1402--1410",
journal = "Modern Pathology",
issn = "0893-3952",
publisher = "Nature Publishing Group",
number = "10",

}

TY - JOUR

T1 - Computer-assisted measurement of primary tumor area is prognostic of recurrence-free survival in stage IB melanoma patients

AU - Rosenbaum, Brooke E.

AU - Schafer, Christine N.

AU - Han, Sung Won

AU - Osman, Iman

AU - Zhong, Hua

AU - Brinster, Nooshin

PY - 2017/10/1

Y1 - 2017/10/1

N2 - Current staging guidelines are insufficient to predict which patients with thin primary melanoma are at high risk of recurrence. Computer-assisted image analysis may allow for more practical and objective histopathological analysis of primary tumors than traditional light microscopy. We studied a prospective cohort of stage IB melanoma patients treated at NYU Langone Medical Center from 2002 to 2014. Primary tumor width, manual area, digital area, and conformation were evaluated in a patient subset via computer-assisted image analysis. The associations between histologic variables and survival were evaluated using Cox proportional hazards model. Logistic regressions were used to build a classifier with clinicopathological characteristics to predict recurrence status. Of the 655 patients with stage IB melanoma studied, a subset of 149 patient tumors (63 recurred, 86 did not recur) underwent computer-assisted histopathological analysis. Increasing tumor width (hazard ratios (HR): 1.17, P=0.01) and digital area (HR: 1.08, P<0.01) were significantly associated with worse recurrence-free survival, whereas non-contiguous conformation (HR: 0.57, P=0.05) was significantly associated with better recurrence-free survival. The novel histopathological classifier composed of digital area, conformation, and baseline variables effectively distinguished recurrent cases from non-recurrent cases (AUC: 0.733, 95% confidence interval (CI): 0.647-0.818), compared to the baseline classifier alone (AUC: 0.635, 95% CI: 0.545-0.724). Primary tumor cross-sectional area, width, and conformation measured via computer-assisted analysis may help identify high-risk patients with stage IB melanoma.

AB - Current staging guidelines are insufficient to predict which patients with thin primary melanoma are at high risk of recurrence. Computer-assisted image analysis may allow for more practical and objective histopathological analysis of primary tumors than traditional light microscopy. We studied a prospective cohort of stage IB melanoma patients treated at NYU Langone Medical Center from 2002 to 2014. Primary tumor width, manual area, digital area, and conformation were evaluated in a patient subset via computer-assisted image analysis. The associations between histologic variables and survival were evaluated using Cox proportional hazards model. Logistic regressions were used to build a classifier with clinicopathological characteristics to predict recurrence status. Of the 655 patients with stage IB melanoma studied, a subset of 149 patient tumors (63 recurred, 86 did not recur) underwent computer-assisted histopathological analysis. Increasing tumor width (hazard ratios (HR): 1.17, P=0.01) and digital area (HR: 1.08, P<0.01) were significantly associated with worse recurrence-free survival, whereas non-contiguous conformation (HR: 0.57, P=0.05) was significantly associated with better recurrence-free survival. The novel histopathological classifier composed of digital area, conformation, and baseline variables effectively distinguished recurrent cases from non-recurrent cases (AUC: 0.733, 95% confidence interval (CI): 0.647-0.818), compared to the baseline classifier alone (AUC: 0.635, 95% CI: 0.545-0.724). Primary tumor cross-sectional area, width, and conformation measured via computer-assisted analysis may help identify high-risk patients with stage IB melanoma.

UR - http://www.scopus.com/inward/record.url?scp=85030648080&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030648080&partnerID=8YFLogxK

U2 - 10.1038/modpathol.2017.64

DO - 10.1038/modpathol.2017.64

M3 - Article

C2 - 28731044

AN - SCOPUS:85030648080

VL - 30

SP - 1402

EP - 1410

JO - Modern Pathology

JF - Modern Pathology

SN - 0893-3952

IS - 10

ER -