Non-invasive optical estimate of tissue composition to differentiate malignant from benign breast lesions

A pilot study

Paola Taroni, Anna Maria Paganoni, Francesca Ieva, Antonio Pifferi, Giovanna Quarto, Francesca Abbate, Enrico Cassano, Rinaldo Cubeddu

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Several techniques are being investigated as a complement to screening mammography, to reduce its false-positive rate, but results are still insufficient to draw conclusions. This initial study explores time domain diffuse optical imaging as an adjunct method to classify non-invasively malignant vs benign breast lesions. We estimated differences in tissue composition (oxy-and deoxyhemoglobin, lipid, water, collagen) and absorption properties between lesion and average healthy tissue in the same breast applying a perturbative approach to optical images collected at 7 red-near infrared wavelengths (635-1060 nm) from subjects bearing breast lesions. The Discrete AdaBoost procedure, a machine-learning algorithm, was then exploited to classify lesions based on optically derived information (either tissue composition or absorption) and risk factors obtained from patient's anamnesis (age, body mass index, familiarity, parity, use of oral contraceptives, and use of Tamoxifen). Collagen content, in particular, turned out to be the most important parameter for discrimination. Based on the initial results of this study the proposed method deserves further investigation.

Original languageEnglish
Article number40683
JournalScientific Reports
Volume7
DOIs
Publication statusPublished - Jan 16 2017

Fingerprint

Breast
Collagen
Optical Imaging
Mammography
Tamoxifen
Oral Contraceptives
Parity
Body Mass Index
Lipids
Water
deoxyhemoglobin
Discrimination (Psychology)
Machine Learning
Recognition (Psychology)

ASJC Scopus subject areas

  • General

Cite this

Non-invasive optical estimate of tissue composition to differentiate malignant from benign breast lesions : A pilot study. / Taroni, Paola; Paganoni, Anna Maria; Ieva, Francesca; Pifferi, Antonio; Quarto, Giovanna; Abbate, Francesca; Cassano, Enrico; Cubeddu, Rinaldo.

In: Scientific Reports, Vol. 7, 40683, 16.01.2017.

Research output: Contribution to journalArticle

Taroni, Paola ; Paganoni, Anna Maria ; Ieva, Francesca ; Pifferi, Antonio ; Quarto, Giovanna ; Abbate, Francesca ; Cassano, Enrico ; Cubeddu, Rinaldo. / Non-invasive optical estimate of tissue composition to differentiate malignant from benign breast lesions : A pilot study. In: Scientific Reports. 2017 ; Vol. 7.
@article{f0874ed67188475d91918e100120e290,
title = "Non-invasive optical estimate of tissue composition to differentiate malignant from benign breast lesions: A pilot study",
abstract = "Several techniques are being investigated as a complement to screening mammography, to reduce its false-positive rate, but results are still insufficient to draw conclusions. This initial study explores time domain diffuse optical imaging as an adjunct method to classify non-invasively malignant vs benign breast lesions. We estimated differences in tissue composition (oxy-and deoxyhemoglobin, lipid, water, collagen) and absorption properties between lesion and average healthy tissue in the same breast applying a perturbative approach to optical images collected at 7 red-near infrared wavelengths (635-1060 nm) from subjects bearing breast lesions. The Discrete AdaBoost procedure, a machine-learning algorithm, was then exploited to classify lesions based on optically derived information (either tissue composition or absorption) and risk factors obtained from patient's anamnesis (age, body mass index, familiarity, parity, use of oral contraceptives, and use of Tamoxifen). Collagen content, in particular, turned out to be the most important parameter for discrimination. Based on the initial results of this study the proposed method deserves further investigation.",
author = "Paola Taroni and Paganoni, {Anna Maria} and Francesca Ieva and Antonio Pifferi and Giovanna Quarto and Francesca Abbate and Enrico Cassano and Rinaldo Cubeddu",
year = "2017",
month = "1",
day = "16",
doi = "10.1038/srep40683",
language = "English",
volume = "7",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Non-invasive optical estimate of tissue composition to differentiate malignant from benign breast lesions

T2 - A pilot study

AU - Taroni, Paola

AU - Paganoni, Anna Maria

AU - Ieva, Francesca

AU - Pifferi, Antonio

AU - Quarto, Giovanna

AU - Abbate, Francesca

AU - Cassano, Enrico

AU - Cubeddu, Rinaldo

PY - 2017/1/16

Y1 - 2017/1/16

N2 - Several techniques are being investigated as a complement to screening mammography, to reduce its false-positive rate, but results are still insufficient to draw conclusions. This initial study explores time domain diffuse optical imaging as an adjunct method to classify non-invasively malignant vs benign breast lesions. We estimated differences in tissue composition (oxy-and deoxyhemoglobin, lipid, water, collagen) and absorption properties between lesion and average healthy tissue in the same breast applying a perturbative approach to optical images collected at 7 red-near infrared wavelengths (635-1060 nm) from subjects bearing breast lesions. The Discrete AdaBoost procedure, a machine-learning algorithm, was then exploited to classify lesions based on optically derived information (either tissue composition or absorption) and risk factors obtained from patient's anamnesis (age, body mass index, familiarity, parity, use of oral contraceptives, and use of Tamoxifen). Collagen content, in particular, turned out to be the most important parameter for discrimination. Based on the initial results of this study the proposed method deserves further investigation.

AB - Several techniques are being investigated as a complement to screening mammography, to reduce its false-positive rate, but results are still insufficient to draw conclusions. This initial study explores time domain diffuse optical imaging as an adjunct method to classify non-invasively malignant vs benign breast lesions. We estimated differences in tissue composition (oxy-and deoxyhemoglobin, lipid, water, collagen) and absorption properties between lesion and average healthy tissue in the same breast applying a perturbative approach to optical images collected at 7 red-near infrared wavelengths (635-1060 nm) from subjects bearing breast lesions. The Discrete AdaBoost procedure, a machine-learning algorithm, was then exploited to classify lesions based on optically derived information (either tissue composition or absorption) and risk factors obtained from patient's anamnesis (age, body mass index, familiarity, parity, use of oral contraceptives, and use of Tamoxifen). Collagen content, in particular, turned out to be the most important parameter for discrimination. Based on the initial results of this study the proposed method deserves further investigation.

UR - http://www.scopus.com/inward/record.url?scp=85009861392&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009861392&partnerID=8YFLogxK

U2 - 10.1038/srep40683

DO - 10.1038/srep40683

M3 - Article

VL - 7

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 40683

ER -