Automated detection of breast cancer in resected specimens with fluorescence lifetime imaging

Jennifer E. Phipps, Dimitris Gorpas, Jakob Unger, Morgan Darrow, Richard J Bold, Laura Marcu

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Re-excision rates for breast cancer lumpectomy procedures are currently nearly 25% due to surgeons relying on inaccurate or incomplete methods of evaluating specimen margins. The objective of this study was to determine if cancer could be automatically detected in breast specimens from mastectomy and lumpectomy procedures by a classification algorithm that incorporated parameters derived from fluorescence lifetime imaging (FLIm). This study generated a database of co-registered histologic sections and FLIm data from breast cancer specimens (N = 20) and a support vector machine (SVM) classification algorithm able to automatically detect cancerous, fibrous, and adipose breast tissue. Classification accuracies were greater than 97% for automated detection of cancerous, fibrous, and adipose tissue from breast cancer specimens. The classification worked equally well for specimens scanned by hand or with a mechanical stage, demonstrating that the system could be used during surgery or on excised specimens. The ability of this technique to simply discriminate between cancerous and normal breast tissue, in particular to distinguish fibrous breast tissue from tumor, which is notoriously challenging for optical techniques, leads to the conclusion that FLIm has great potential to assess breast cancer margins. Identification of positive margins before waiting for complete histologic analysis could significantly reduce breast cancer re-excision rates.

Original languageEnglish (US)
Article number015003
JournalPhysics in Medicine and Biology
Volume63
Issue number1
DOIs
StatePublished - Jan 1 2018

Fingerprint

Optical Imaging
Breast Neoplasms
Breast
Segmental Mastectomy
Adipose Tissue
Mastectomy
Hand
Databases
Neoplasms

Keywords

  • breast cancer
  • fluorescence lifetime imaging
  • support vector machines

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging

Cite this

Automated detection of breast cancer in resected specimens with fluorescence lifetime imaging. / Phipps, Jennifer E.; Gorpas, Dimitris; Unger, Jakob; Darrow, Morgan; Bold, Richard J; Marcu, Laura.

In: Physics in Medicine and Biology, Vol. 63, No. 1, 015003, 01.01.2018.

Research output: Contribution to journalArticle

@article{641df088ef924431879c77fc0f24389a,
title = "Automated detection of breast cancer in resected specimens with fluorescence lifetime imaging",
abstract = "Re-excision rates for breast cancer lumpectomy procedures are currently nearly 25{\%} due to surgeons relying on inaccurate or incomplete methods of evaluating specimen margins. The objective of this study was to determine if cancer could be automatically detected in breast specimens from mastectomy and lumpectomy procedures by a classification algorithm that incorporated parameters derived from fluorescence lifetime imaging (FLIm). This study generated a database of co-registered histologic sections and FLIm data from breast cancer specimens (N = 20) and a support vector machine (SVM) classification algorithm able to automatically detect cancerous, fibrous, and adipose breast tissue. Classification accuracies were greater than 97{\%} for automated detection of cancerous, fibrous, and adipose tissue from breast cancer specimens. The classification worked equally well for specimens scanned by hand or with a mechanical stage, demonstrating that the system could be used during surgery or on excised specimens. The ability of this technique to simply discriminate between cancerous and normal breast tissue, in particular to distinguish fibrous breast tissue from tumor, which is notoriously challenging for optical techniques, leads to the conclusion that FLIm has great potential to assess breast cancer margins. Identification of positive margins before waiting for complete histologic analysis could significantly reduce breast cancer re-excision rates.",
keywords = "breast cancer, fluorescence lifetime imaging, support vector machines",
author = "Phipps, {Jennifer E.} and Dimitris Gorpas and Jakob Unger and Morgan Darrow and Bold, {Richard J} and Laura Marcu",
year = "2018",
month = "1",
day = "1",
doi = "10.1088/1361-6560/aa983a",
language = "English (US)",
volume = "63",
journal = "Physics in Medicine and Biology",
issn = "0031-9155",
publisher = "IOP Publishing Ltd.",
number = "1",

}

TY - JOUR

T1 - Automated detection of breast cancer in resected specimens with fluorescence lifetime imaging

AU - Phipps, Jennifer E.

AU - Gorpas, Dimitris

AU - Unger, Jakob

AU - Darrow, Morgan

AU - Bold, Richard J

AU - Marcu, Laura

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Re-excision rates for breast cancer lumpectomy procedures are currently nearly 25% due to surgeons relying on inaccurate or incomplete methods of evaluating specimen margins. The objective of this study was to determine if cancer could be automatically detected in breast specimens from mastectomy and lumpectomy procedures by a classification algorithm that incorporated parameters derived from fluorescence lifetime imaging (FLIm). This study generated a database of co-registered histologic sections and FLIm data from breast cancer specimens (N = 20) and a support vector machine (SVM) classification algorithm able to automatically detect cancerous, fibrous, and adipose breast tissue. Classification accuracies were greater than 97% for automated detection of cancerous, fibrous, and adipose tissue from breast cancer specimens. The classification worked equally well for specimens scanned by hand or with a mechanical stage, demonstrating that the system could be used during surgery or on excised specimens. The ability of this technique to simply discriminate between cancerous and normal breast tissue, in particular to distinguish fibrous breast tissue from tumor, which is notoriously challenging for optical techniques, leads to the conclusion that FLIm has great potential to assess breast cancer margins. Identification of positive margins before waiting for complete histologic analysis could significantly reduce breast cancer re-excision rates.

AB - Re-excision rates for breast cancer lumpectomy procedures are currently nearly 25% due to surgeons relying on inaccurate or incomplete methods of evaluating specimen margins. The objective of this study was to determine if cancer could be automatically detected in breast specimens from mastectomy and lumpectomy procedures by a classification algorithm that incorporated parameters derived from fluorescence lifetime imaging (FLIm). This study generated a database of co-registered histologic sections and FLIm data from breast cancer specimens (N = 20) and a support vector machine (SVM) classification algorithm able to automatically detect cancerous, fibrous, and adipose breast tissue. Classification accuracies were greater than 97% for automated detection of cancerous, fibrous, and adipose tissue from breast cancer specimens. The classification worked equally well for specimens scanned by hand or with a mechanical stage, demonstrating that the system could be used during surgery or on excised specimens. The ability of this technique to simply discriminate between cancerous and normal breast tissue, in particular to distinguish fibrous breast tissue from tumor, which is notoriously challenging for optical techniques, leads to the conclusion that FLIm has great potential to assess breast cancer margins. Identification of positive margins before waiting for complete histologic analysis could significantly reduce breast cancer re-excision rates.

KW - breast cancer

KW - fluorescence lifetime imaging

KW - support vector machines

UR - http://www.scopus.com/inward/record.url?scp=85040312663&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040312663&partnerID=8YFLogxK

U2 - 10.1088/1361-6560/aa983a

DO - 10.1088/1361-6560/aa983a

M3 - Article

C2 - 29099721

AN - SCOPUS:85040312663

VL - 63

JO - Physics in Medicine and Biology

JF - Physics in Medicine and Biology

SN - 0031-9155

IS - 1

M1 - 015003

ER -