An exploratory radiomics analysis on digital breast tomosynthesis in women with mammographically negative dense breasts

Alberto Stefano Tagliafico, Francesca Valdora, Giovanna Mariscotti, Maunela Durando, Jacopo Nori, Daniele La Forgia, Ilan Rosenberg, Francesca Caumo, Nicoletta Gandolfo, Nehmat Houssami, Massimo Calabrese

Research output: Contribution to journalArticle

Abstract

PURPOSE: To compare Digital Breast Tomosynthesis (DBT) for cancers and normal screens in women with dense breasts and negative mammography using a Radiomics approach.

MATERIALS AND METHODS: A substudy (N = 40) of the 'Adjunct Screening With Tomosynthesis or Ultrasound in Women With Mammography-Negative Dense Breasts (ASTOUND)' trial was done based on 20 women who had DBT-detected, histology-proven, breast cancer and 20 controls matched for age and density. Using a Radiomics approach normal and pathological breast parenchyma were evaluated, and correlations among Radiomics features and clinical and prognostic parameters were investigated.

RESULTS: The median age of the patients was 50 years (range 39-70 years). After Radiomics feature number reduction, 3 of 6 (50%) selected features differed between controls and cancers (Skewness (0.002); Entropy (p.004); 90percentile (p.006)). Three Radiomics features (Energy, Entropy and Dissimilarity) significantly correlated to tumor size (r = -0.15,r = 0.49,r = 0.51), but not with prognostic factors. Entropy correlated with Estrogen Receptor status (r = -0,46; p.004).

CONCLUSION: Radiomics features in patients with dense breasts and negative mammography appear to differ between cancerous and normal breast tissue, with evidence of correlation with tumor size and estrogen receptors. This new information warrants further evaluation in larger studies and could contribute to improved understanding of breast cancer through imaging, and may support tailored screening and treatments.

Original languageEnglish
Pages (from-to)92-96
Number of pages5
JournalBreast
Volume40
DOIs
Publication statusPublished - Aug 2018

Fingerprint

Mammography
Breast
Entropy
Breast Neoplasms
Estrogen Receptors
Neoplasms
Histology

Keywords

  • Adult
  • Aged
  • Breast/diagnostic imaging
  • Breast Neoplasms/diagnostic imaging
  • Case-Control Studies
  • Early Detection of Cancer/methods
  • Entropy
  • Female
  • Humans
  • Mammography/methods
  • Middle Aged
  • Prognosis
  • Radiometry/methods
  • Receptors, Estrogen/analysis

Cite this

An exploratory radiomics analysis on digital breast tomosynthesis in women with mammographically negative dense breasts. / Tagliafico, Alberto Stefano; Valdora, Francesca; Mariscotti, Giovanna; Durando, Maunela; Nori, Jacopo; La Forgia, Daniele; Rosenberg, Ilan; Caumo, Francesca; Gandolfo, Nicoletta; Houssami, Nehmat; Calabrese, Massimo.

In: Breast, Vol. 40, 08.2018, p. 92-96.

Research output: Contribution to journalArticle

Tagliafico, Alberto Stefano ; Valdora, Francesca ; Mariscotti, Giovanna ; Durando, Maunela ; Nori, Jacopo ; La Forgia, Daniele ; Rosenberg, Ilan ; Caumo, Francesca ; Gandolfo, Nicoletta ; Houssami, Nehmat ; Calabrese, Massimo. / An exploratory radiomics analysis on digital breast tomosynthesis in women with mammographically negative dense breasts. In: Breast. 2018 ; Vol. 40. pp. 92-96.
@article{34c25a39ebd54df3bef01d06730e42af,
title = "An exploratory radiomics analysis on digital breast tomosynthesis in women with mammographically negative dense breasts",
abstract = "PURPOSE: To compare Digital Breast Tomosynthesis (DBT) for cancers and normal screens in women with dense breasts and negative mammography using a Radiomics approach.MATERIALS AND METHODS: A substudy (N = 40) of the 'Adjunct Screening With Tomosynthesis or Ultrasound in Women With Mammography-Negative Dense Breasts (ASTOUND)' trial was done based on 20 women who had DBT-detected, histology-proven, breast cancer and 20 controls matched for age and density. Using a Radiomics approach normal and pathological breast parenchyma were evaluated, and correlations among Radiomics features and clinical and prognostic parameters were investigated.RESULTS: The median age of the patients was 50 years (range 39-70 years). After Radiomics feature number reduction, 3 of 6 (50{\%}) selected features differed between controls and cancers (Skewness (0.002); Entropy (p.004); 90percentile (p.006)). Three Radiomics features (Energy, Entropy and Dissimilarity) significantly correlated to tumor size (r = -0.15,r = 0.49,r = 0.51), but not with prognostic factors. Entropy correlated with Estrogen Receptor status (r = -0,46; p.004).CONCLUSION: Radiomics features in patients with dense breasts and negative mammography appear to differ between cancerous and normal breast tissue, with evidence of correlation with tumor size and estrogen receptors. This new information warrants further evaluation in larger studies and could contribute to improved understanding of breast cancer through imaging, and may support tailored screening and treatments.",
keywords = "Adult, Aged, Breast/diagnostic imaging, Breast Neoplasms/diagnostic imaging, Case-Control Studies, Early Detection of Cancer/methods, Entropy, Female, Humans, Mammography/methods, Middle Aged, Prognosis, Radiometry/methods, Receptors, Estrogen/analysis",
author = "Tagliafico, {Alberto Stefano} and Francesca Valdora and Giovanna Mariscotti and Maunela Durando and Jacopo Nori and {La Forgia}, Daniele and Ilan Rosenberg and Francesca Caumo and Nicoletta Gandolfo and Nehmat Houssami and Massimo Calabrese",
note = "Copyright {\circledC} 2018 Elsevier Ltd. All rights reserved.",
year = "2018",
month = "8",
doi = "10.1016/j.breast.2018.04.016",
language = "English",
volume = "40",
pages = "92--96",
journal = "Breast",
issn = "0960-9776",
publisher = "Churchill Livingstone",

}

TY - JOUR

T1 - An exploratory radiomics analysis on digital breast tomosynthesis in women with mammographically negative dense breasts

AU - Tagliafico, Alberto Stefano

AU - Valdora, Francesca

AU - Mariscotti, Giovanna

AU - Durando, Maunela

AU - Nori, Jacopo

AU - La Forgia, Daniele

AU - Rosenberg, Ilan

AU - Caumo, Francesca

AU - Gandolfo, Nicoletta

AU - Houssami, Nehmat

AU - Calabrese, Massimo

N1 - Copyright © 2018 Elsevier Ltd. All rights reserved.

PY - 2018/8

Y1 - 2018/8

N2 - PURPOSE: To compare Digital Breast Tomosynthesis (DBT) for cancers and normal screens in women with dense breasts and negative mammography using a Radiomics approach.MATERIALS AND METHODS: A substudy (N = 40) of the 'Adjunct Screening With Tomosynthesis or Ultrasound in Women With Mammography-Negative Dense Breasts (ASTOUND)' trial was done based on 20 women who had DBT-detected, histology-proven, breast cancer and 20 controls matched for age and density. Using a Radiomics approach normal and pathological breast parenchyma were evaluated, and correlations among Radiomics features and clinical and prognostic parameters were investigated.RESULTS: The median age of the patients was 50 years (range 39-70 years). After Radiomics feature number reduction, 3 of 6 (50%) selected features differed between controls and cancers (Skewness (0.002); Entropy (p.004); 90percentile (p.006)). Three Radiomics features (Energy, Entropy and Dissimilarity) significantly correlated to tumor size (r = -0.15,r = 0.49,r = 0.51), but not with prognostic factors. Entropy correlated with Estrogen Receptor status (r = -0,46; p.004).CONCLUSION: Radiomics features in patients with dense breasts and negative mammography appear to differ between cancerous and normal breast tissue, with evidence of correlation with tumor size and estrogen receptors. This new information warrants further evaluation in larger studies and could contribute to improved understanding of breast cancer through imaging, and may support tailored screening and treatments.

AB - PURPOSE: To compare Digital Breast Tomosynthesis (DBT) for cancers and normal screens in women with dense breasts and negative mammography using a Radiomics approach.MATERIALS AND METHODS: A substudy (N = 40) of the 'Adjunct Screening With Tomosynthesis or Ultrasound in Women With Mammography-Negative Dense Breasts (ASTOUND)' trial was done based on 20 women who had DBT-detected, histology-proven, breast cancer and 20 controls matched for age and density. Using a Radiomics approach normal and pathological breast parenchyma were evaluated, and correlations among Radiomics features and clinical and prognostic parameters were investigated.RESULTS: The median age of the patients was 50 years (range 39-70 years). After Radiomics feature number reduction, 3 of 6 (50%) selected features differed between controls and cancers (Skewness (0.002); Entropy (p.004); 90percentile (p.006)). Three Radiomics features (Energy, Entropy and Dissimilarity) significantly correlated to tumor size (r = -0.15,r = 0.49,r = 0.51), but not with prognostic factors. Entropy correlated with Estrogen Receptor status (r = -0,46; p.004).CONCLUSION: Radiomics features in patients with dense breasts and negative mammography appear to differ between cancerous and normal breast tissue, with evidence of correlation with tumor size and estrogen receptors. This new information warrants further evaluation in larger studies and could contribute to improved understanding of breast cancer through imaging, and may support tailored screening and treatments.

KW - Adult

KW - Aged

KW - Breast/diagnostic imaging

KW - Breast Neoplasms/diagnostic imaging

KW - Case-Control Studies

KW - Early Detection of Cancer/methods

KW - Entropy

KW - Female

KW - Humans

KW - Mammography/methods

KW - Middle Aged

KW - Prognosis

KW - Radiometry/methods

KW - Receptors, Estrogen/analysis

U2 - 10.1016/j.breast.2018.04.016

DO - 10.1016/j.breast.2018.04.016

M3 - Article

VL - 40

SP - 92

EP - 96

JO - Breast

JF - Breast

SN - 0960-9776

ER -