Automated clear cell renal carcinoma grade classification with prognostic significance

Katherine Tian, Christopher A. Rubadue, Douglas I. Lin, Mitko Veta, Michael E. Pyle, Humayun Irshad, Yujing J. Heng (Corresponding author)

Research output: Contribution to journalArticleAcademicpeer-review

8 Downloads (Pure)

Abstract

We developed an automated 2-tiered Fuhrman’s grading system for clear cell renal cell carcinoma (ccRCC). Whole slide images (WSI) and clinical data were retrieved for 395 The Cancer Genome Atlas (TCGA) ccRCC cases. Pathologist 1 reviewed and selected regions of interests (ROIs). Nuclear segmentation was performed. Quantitative morphological, intensity, and texture features (n = 72) were extracted. Features associated with grade were identified by constructing a Lasso model using data from cases with concordant 2-tiered Fuhrman’s grades between TCGA and Pathologist 1 (training set n = 235; held-out test set n = 42). Discordant cases (n = 118) were additionally reviewed by Pathologist 2. Cox proportional hazard model evaluated the prognostic efficacy of the predicted grades in an extended test set which was created by combining the test set and discordant cases (n = 160). The Lasso model consisted of 26 features and predicted grade with 84.6% sensitivity and 81.3% specificity in the test set. In the extended test set, predicted grade was significantly associated with overall survival after adjusting for age and gender (Hazard Ratio 2.05; 95% CI 1.21–3.47); manual grades were not prognostic. Future work can adapt our computational system to predict WHO/ISUP grades, and validating this system on other ccRCC cohorts.

Original languageEnglish
Article numbere0222641
Number of pages16
JournalPLoS ONE
Volume14
Issue number10
DOIs
Publication statusPublished - 1 Jan 2019

Fingerprint

kidney cells
Renal Cell Carcinoma
carcinoma
Atlases
Hazards
Genes
Genome
testing
Proportional Hazards Models
Neoplasms
Textures
Cells
neoplasms
genome
Sensitivity and Specificity
cells
texture
Pathologists
gender
alachlor

Cite this

Tian, K., Rubadue, C. A., Lin, D. I., Veta, M., Pyle, M. E., Irshad, H., & Heng, Y. J. (2019). Automated clear cell renal carcinoma grade classification with prognostic significance. PLoS ONE, 14(10), [e0222641]. https://doi.org/10.1371/journal.pone.0222641
Tian, Katherine ; Rubadue, Christopher A. ; Lin, Douglas I. ; Veta, Mitko ; Pyle, Michael E. ; Irshad, Humayun ; Heng, Yujing J. / Automated clear cell renal carcinoma grade classification with prognostic significance. In: PLoS ONE. 2019 ; Vol. 14, No. 10.
@article{635ca2454935431c9c664cccf05b2563,
title = "Automated clear cell renal carcinoma grade classification with prognostic significance",
abstract = "We developed an automated 2-tiered Fuhrman’s grading system for clear cell renal cell carcinoma (ccRCC). Whole slide images (WSI) and clinical data were retrieved for 395 The Cancer Genome Atlas (TCGA) ccRCC cases. Pathologist 1 reviewed and selected regions of interests (ROIs). Nuclear segmentation was performed. Quantitative morphological, intensity, and texture features (n = 72) were extracted. Features associated with grade were identified by constructing a Lasso model using data from cases with concordant 2-tiered Fuhrman’s grades between TCGA and Pathologist 1 (training set n = 235; held-out test set n = 42). Discordant cases (n = 118) were additionally reviewed by Pathologist 2. Cox proportional hazard model evaluated the prognostic efficacy of the predicted grades in an extended test set which was created by combining the test set and discordant cases (n = 160). The Lasso model consisted of 26 features and predicted grade with 84.6{\%} sensitivity and 81.3{\%} specificity in the test set. In the extended test set, predicted grade was significantly associated with overall survival after adjusting for age and gender (Hazard Ratio 2.05; 95{\%} CI 1.21–3.47); manual grades were not prognostic. Future work can adapt our computational system to predict WHO/ISUP grades, and validating this system on other ccRCC cohorts.",
author = "Katherine Tian and Rubadue, {Christopher A.} and Lin, {Douglas I.} and Mitko Veta and Pyle, {Michael E.} and Humayun Irshad and Heng, {Yujing J.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1371/journal.pone.0222641",
language = "English",
volume = "14",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "10",

}

Tian, K, Rubadue, CA, Lin, DI, Veta, M, Pyle, ME, Irshad, H & Heng, YJ 2019, 'Automated clear cell renal carcinoma grade classification with prognostic significance', PLoS ONE, vol. 14, no. 10, e0222641. https://doi.org/10.1371/journal.pone.0222641

Automated clear cell renal carcinoma grade classification with prognostic significance. / Tian, Katherine; Rubadue, Christopher A.; Lin, Douglas I.; Veta, Mitko; Pyle, Michael E.; Irshad, Humayun; Heng, Yujing J. (Corresponding author).

In: PLoS ONE, Vol. 14, No. 10, e0222641, 01.01.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Automated clear cell renal carcinoma grade classification with prognostic significance

AU - Tian, Katherine

AU - Rubadue, Christopher A.

AU - Lin, Douglas I.

AU - Veta, Mitko

AU - Pyle, Michael E.

AU - Irshad, Humayun

AU - Heng, Yujing J.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We developed an automated 2-tiered Fuhrman’s grading system for clear cell renal cell carcinoma (ccRCC). Whole slide images (WSI) and clinical data were retrieved for 395 The Cancer Genome Atlas (TCGA) ccRCC cases. Pathologist 1 reviewed and selected regions of interests (ROIs). Nuclear segmentation was performed. Quantitative morphological, intensity, and texture features (n = 72) were extracted. Features associated with grade were identified by constructing a Lasso model using data from cases with concordant 2-tiered Fuhrman’s grades between TCGA and Pathologist 1 (training set n = 235; held-out test set n = 42). Discordant cases (n = 118) were additionally reviewed by Pathologist 2. Cox proportional hazard model evaluated the prognostic efficacy of the predicted grades in an extended test set which was created by combining the test set and discordant cases (n = 160). The Lasso model consisted of 26 features and predicted grade with 84.6% sensitivity and 81.3% specificity in the test set. In the extended test set, predicted grade was significantly associated with overall survival after adjusting for age and gender (Hazard Ratio 2.05; 95% CI 1.21–3.47); manual grades were not prognostic. Future work can adapt our computational system to predict WHO/ISUP grades, and validating this system on other ccRCC cohorts.

AB - We developed an automated 2-tiered Fuhrman’s grading system for clear cell renal cell carcinoma (ccRCC). Whole slide images (WSI) and clinical data were retrieved for 395 The Cancer Genome Atlas (TCGA) ccRCC cases. Pathologist 1 reviewed and selected regions of interests (ROIs). Nuclear segmentation was performed. Quantitative morphological, intensity, and texture features (n = 72) were extracted. Features associated with grade were identified by constructing a Lasso model using data from cases with concordant 2-tiered Fuhrman’s grades between TCGA and Pathologist 1 (training set n = 235; held-out test set n = 42). Discordant cases (n = 118) were additionally reviewed by Pathologist 2. Cox proportional hazard model evaluated the prognostic efficacy of the predicted grades in an extended test set which was created by combining the test set and discordant cases (n = 160). The Lasso model consisted of 26 features and predicted grade with 84.6% sensitivity and 81.3% specificity in the test set. In the extended test set, predicted grade was significantly associated with overall survival after adjusting for age and gender (Hazard Ratio 2.05; 95% CI 1.21–3.47); manual grades were not prognostic. Future work can adapt our computational system to predict WHO/ISUP grades, and validating this system on other ccRCC cohorts.

UR - http://www.scopus.com/inward/record.url?scp=85072841807&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0222641

DO - 10.1371/journal.pone.0222641

M3 - Article

C2 - 31581201

AN - SCOPUS:85072841807

VL - 14

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 10

M1 - e0222641

ER -