Relationships Between Human-Extracted MRI Tumor Phenotypes of Breast Cancer and Clinical Prognostic Indicators Including Receptor Status and Molecular Subtype

Jose M Net, Gary J. Whitman, Elizabteh Morris, Kathleen R. Brandt, Elizabeth S. Burnside, Maryellen L. Giger, Marie Ganott, Elizabeth J. Sutton, Margarita L. Zuley, Arvind Rao

Research output: Contribution to journalArticle

Abstract

PURPOSE: The purpose of this study was to investigate if human-extracted MRI tumor phenotypes of breast cancer could predict receptor status and tumor molecular subtype using MRIs from The Cancer Genome Atlas project. MATERIALS AND METHODS: Our retrospective interpretation study utilized the analysis of HIPAA-compliant breast MRI data from The Cancer Imaging Archive. One hundred and seven preoperative breast MRIs of biopsy proven invasive breast cancers were analyzed by 3 fellowship-trained breast-imaging radiologists. Each study was scored according to the Breast Imaging Reporting and Data System lexicon for mass and nonmass features. The Spearman rank correlation was used for association analysis of continuous variables; the Kruskal-Wallis test was used for associating continuous outcomes with categorical variables. The Fisher-exact test was used to assess correlations between categorical image-derived features and receptor status. Prediction of estrogen receptor (ER), progesterone receptor, human epidermal growth factor receptor, and molecular subtype were performed using random forest classifiers. RESULTS: ER+ tumors were associated with the absence of rim enhancement (P = 0.019, odds ratio [OR] 5.5), heterogeneous internal enhancement (P = 0.02, OR 6.5), peritumoral edema (P = 0.0001, OR 10.0), and axillary adenopathy (P = 0.04, OR 4.4). ER+ tumors were smaller than ER− tumors (23.7 mm vs 29.2 mm, P = 0.02, OR 8.2). All of these variables except the lack of axillary adenopathy were also associated with progesterone receptor+ status. Luminal A tumors (n = 57) were smaller compared to nonLuminal A (21.8 mm vs 27.5 mm, P = 0.035, OR 7.3) and lacked peritumoral edema (P = 0.001, OR 6.8). Basal like tumors were associated with heterogeneous internal enhancement (P = 0.05, OR 10.1), rim enhancement (P = 0.05, OR6.9), and perituomral edema (P = 0.0001, OR 13.8). CONCLUSIONS: Human extracted MRI tumor phenotypes may be able to differentiate those tumors with a more favorable clinical prognosis from their more aggressive counterparts.

Original languageEnglish (US)
JournalCurrent Problems in Diagnostic Radiology
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Breast Neoplasms
Phenotype
Odds Ratio
Neoplasms
Estrogen Receptors
Breast
Edema
Progesterone Receptors
Health Insurance Portability and Accountability Act
Atlases
Epidermal Growth Factor Receptor
Information Systems
Retrospective Studies
Genome
Biopsy

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Relationships Between Human-Extracted MRI Tumor Phenotypes of Breast Cancer and Clinical Prognostic Indicators Including Receptor Status and Molecular Subtype. / Net, Jose M; Whitman, Gary J.; Morris, Elizabteh; Brandt, Kathleen R.; Burnside, Elizabeth S.; Giger, Maryellen L.; Ganott, Marie; Sutton, Elizabeth J.; Zuley, Margarita L.; Rao, Arvind.

In: Current Problems in Diagnostic Radiology, 01.01.2018.

Research output: Contribution to journalArticle

Net, Jose M ; Whitman, Gary J. ; Morris, Elizabteh ; Brandt, Kathleen R. ; Burnside, Elizabeth S. ; Giger, Maryellen L. ; Ganott, Marie ; Sutton, Elizabeth J. ; Zuley, Margarita L. ; Rao, Arvind. / Relationships Between Human-Extracted MRI Tumor Phenotypes of Breast Cancer and Clinical Prognostic Indicators Including Receptor Status and Molecular Subtype. In: Current Problems in Diagnostic Radiology. 2018.
@article{df4933a80aae44689c4fed7fa5d1b941,
title = "Relationships Between Human-Extracted MRI Tumor Phenotypes of Breast Cancer and Clinical Prognostic Indicators Including Receptor Status and Molecular Subtype",
abstract = "PURPOSE: The purpose of this study was to investigate if human-extracted MRI tumor phenotypes of breast cancer could predict receptor status and tumor molecular subtype using MRIs from The Cancer Genome Atlas project. MATERIALS AND METHODS: Our retrospective interpretation study utilized the analysis of HIPAA-compliant breast MRI data from The Cancer Imaging Archive. One hundred and seven preoperative breast MRIs of biopsy proven invasive breast cancers were analyzed by 3 fellowship-trained breast-imaging radiologists. Each study was scored according to the Breast Imaging Reporting and Data System lexicon for mass and nonmass features. The Spearman rank correlation was used for association analysis of continuous variables; the Kruskal-Wallis test was used for associating continuous outcomes with categorical variables. The Fisher-exact test was used to assess correlations between categorical image-derived features and receptor status. Prediction of estrogen receptor (ER), progesterone receptor, human epidermal growth factor receptor, and molecular subtype were performed using random forest classifiers. RESULTS: ER+ tumors were associated with the absence of rim enhancement (P = 0.019, odds ratio [OR] 5.5), heterogeneous internal enhancement (P = 0.02, OR 6.5), peritumoral edema (P = 0.0001, OR 10.0), and axillary adenopathy (P = 0.04, OR 4.4). ER+ tumors were smaller than ER− tumors (23.7 mm vs 29.2 mm, P = 0.02, OR 8.2). All of these variables except the lack of axillary adenopathy were also associated with progesterone receptor+ status. Luminal A tumors (n = 57) were smaller compared to nonLuminal A (21.8 mm vs 27.5 mm, P = 0.035, OR 7.3) and lacked peritumoral edema (P = 0.001, OR 6.8). Basal like tumors were associated with heterogeneous internal enhancement (P = 0.05, OR 10.1), rim enhancement (P = 0.05, OR6.9), and perituomral edema (P = 0.0001, OR 13.8). CONCLUSIONS: Human extracted MRI tumor phenotypes may be able to differentiate those tumors with a more favorable clinical prognosis from their more aggressive counterparts.",
author = "Net, {Jose M} and Whitman, {Gary J.} and Elizabteh Morris and Brandt, {Kathleen R.} and Burnside, {Elizabeth S.} and Giger, {Maryellen L.} and Marie Ganott and Sutton, {Elizabeth J.} and Zuley, {Margarita L.} and Arvind Rao",
year = "2018",
month = "1",
day = "1",
doi = "10.1067/j.cpradiol.2018.08.003",
language = "English (US)",
journal = "Current Problems in Diagnostic Radiology",
issn = "0363-0188",
publisher = "Mosby Inc.",

}

TY - JOUR

T1 - Relationships Between Human-Extracted MRI Tumor Phenotypes of Breast Cancer and Clinical Prognostic Indicators Including Receptor Status and Molecular Subtype

AU - Net, Jose M

AU - Whitman, Gary J.

AU - Morris, Elizabteh

AU - Brandt, Kathleen R.

AU - Burnside, Elizabeth S.

AU - Giger, Maryellen L.

AU - Ganott, Marie

AU - Sutton, Elizabeth J.

AU - Zuley, Margarita L.

AU - Rao, Arvind

PY - 2018/1/1

Y1 - 2018/1/1

N2 - PURPOSE: The purpose of this study was to investigate if human-extracted MRI tumor phenotypes of breast cancer could predict receptor status and tumor molecular subtype using MRIs from The Cancer Genome Atlas project. MATERIALS AND METHODS: Our retrospective interpretation study utilized the analysis of HIPAA-compliant breast MRI data from The Cancer Imaging Archive. One hundred and seven preoperative breast MRIs of biopsy proven invasive breast cancers were analyzed by 3 fellowship-trained breast-imaging radiologists. Each study was scored according to the Breast Imaging Reporting and Data System lexicon for mass and nonmass features. The Spearman rank correlation was used for association analysis of continuous variables; the Kruskal-Wallis test was used for associating continuous outcomes with categorical variables. The Fisher-exact test was used to assess correlations between categorical image-derived features and receptor status. Prediction of estrogen receptor (ER), progesterone receptor, human epidermal growth factor receptor, and molecular subtype were performed using random forest classifiers. RESULTS: ER+ tumors were associated with the absence of rim enhancement (P = 0.019, odds ratio [OR] 5.5), heterogeneous internal enhancement (P = 0.02, OR 6.5), peritumoral edema (P = 0.0001, OR 10.0), and axillary adenopathy (P = 0.04, OR 4.4). ER+ tumors were smaller than ER− tumors (23.7 mm vs 29.2 mm, P = 0.02, OR 8.2). All of these variables except the lack of axillary adenopathy were also associated with progesterone receptor+ status. Luminal A tumors (n = 57) were smaller compared to nonLuminal A (21.8 mm vs 27.5 mm, P = 0.035, OR 7.3) and lacked peritumoral edema (P = 0.001, OR 6.8). Basal like tumors were associated with heterogeneous internal enhancement (P = 0.05, OR 10.1), rim enhancement (P = 0.05, OR6.9), and perituomral edema (P = 0.0001, OR 13.8). CONCLUSIONS: Human extracted MRI tumor phenotypes may be able to differentiate those tumors with a more favorable clinical prognosis from their more aggressive counterparts.

AB - PURPOSE: The purpose of this study was to investigate if human-extracted MRI tumor phenotypes of breast cancer could predict receptor status and tumor molecular subtype using MRIs from The Cancer Genome Atlas project. MATERIALS AND METHODS: Our retrospective interpretation study utilized the analysis of HIPAA-compliant breast MRI data from The Cancer Imaging Archive. One hundred and seven preoperative breast MRIs of biopsy proven invasive breast cancers were analyzed by 3 fellowship-trained breast-imaging radiologists. Each study was scored according to the Breast Imaging Reporting and Data System lexicon for mass and nonmass features. The Spearman rank correlation was used for association analysis of continuous variables; the Kruskal-Wallis test was used for associating continuous outcomes with categorical variables. The Fisher-exact test was used to assess correlations between categorical image-derived features and receptor status. Prediction of estrogen receptor (ER), progesterone receptor, human epidermal growth factor receptor, and molecular subtype were performed using random forest classifiers. RESULTS: ER+ tumors were associated with the absence of rim enhancement (P = 0.019, odds ratio [OR] 5.5), heterogeneous internal enhancement (P = 0.02, OR 6.5), peritumoral edema (P = 0.0001, OR 10.0), and axillary adenopathy (P = 0.04, OR 4.4). ER+ tumors were smaller than ER− tumors (23.7 mm vs 29.2 mm, P = 0.02, OR 8.2). All of these variables except the lack of axillary adenopathy were also associated with progesterone receptor+ status. Luminal A tumors (n = 57) were smaller compared to nonLuminal A (21.8 mm vs 27.5 mm, P = 0.035, OR 7.3) and lacked peritumoral edema (P = 0.001, OR 6.8). Basal like tumors were associated with heterogeneous internal enhancement (P = 0.05, OR 10.1), rim enhancement (P = 0.05, OR6.9), and perituomral edema (P = 0.0001, OR 13.8). CONCLUSIONS: Human extracted MRI tumor phenotypes may be able to differentiate those tumors with a more favorable clinical prognosis from their more aggressive counterparts.

UR - http://www.scopus.com/inward/record.url?scp=85054158857&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054158857&partnerID=8YFLogxK

U2 - 10.1067/j.cpradiol.2018.08.003

DO - 10.1067/j.cpradiol.2018.08.003

M3 - Article

AN - SCOPUS:85054158857

JO - Current Problems in Diagnostic Radiology

JF - Current Problems in Diagnostic Radiology

SN - 0363-0188

ER -