Development of a practical spatial-spectral analysis protocol for breast histopathology using Fourier transform infrared spectroscopic imaging

F. Nell Pounder, Rohith K. Reddy, Rohit Bhargava

Research output: Contribution to journalArticle

Abstract

Breast cancer screening provides sensitive tumor identification, but low specificity implies that a vast majority of biopsies are not ultimately diagnosed as cancer. Automated techniques to evaluate biopsies can prevent errors, reduce pathologist workload and provide objective analysis. Fourier transform infrared (FT-IR) spectroscopic imaging provides both molecular signatures and spatial information that may be applicable for pathology. Here, we utilize both the spectral and spatial information to develop a combined classifier that provides rapid tissue assessment. First, we evaluated the potential of IR imaging to provide a diagnosis using spectral data alone. While highly accurate histologic [epithelium, stroma] recognition could be achieved, the same was not possible for disease [cancer, no-cancer] due to the diversity of spectral signals. Hence, we employed spatial data, developing and evaluating increasingly complex models, to detect cancers. Sub-mm tumors could be very confidently predicted as indicated by the quantitative measurement of accuracy via receiver operating characteristic (ROC) curve analyses. The developed protocol was validated with a small set and statistical performance used to develop a model that predicts study design for a large scale, definitive validation. The results of evaluation on different instruments, at higher noise levels, under a coarser spectral resolution and two sampling modes [transmission and transflection], indicate that the protocol is highly accurate under a variety of conditions. The study paves the way to validating IR imaging for rapid breast tumor detection, its statistical validation and potential directions for optimization of the speed and sampling for clinical deployment.

Original languageEnglish (US)
Pages (from-to)43-68
Number of pages26
JournalFaraday Discussions
Volume187
DOIs
StatePublished - Jan 1 2016

Fingerprint

breast
Spectrum analysis
spectrum analysis
Tumors
Fourier transforms
Biopsy
cancer
Infrared imaging
Infrared radiation
Imaging techniques
tumors
Sampling
Spectral resolution
Pathology
sampling
Screening
Classifiers
epithelium
Tissue
pathology

ASJC Scopus subject areas

  • Physical and Theoretical Chemistry

Cite this

Development of a practical spatial-spectral analysis protocol for breast histopathology using Fourier transform infrared spectroscopic imaging. / Pounder, F. Nell; Reddy, Rohith K.; Bhargava, Rohit.

In: Faraday Discussions, Vol. 187, 01.01.2016, p. 43-68.

Research output: Contribution to journalArticle

@article{326c7387217346409fd4938b9842aab1,
title = "Development of a practical spatial-spectral analysis protocol for breast histopathology using Fourier transform infrared spectroscopic imaging",
abstract = "Breast cancer screening provides sensitive tumor identification, but low specificity implies that a vast majority of biopsies are not ultimately diagnosed as cancer. Automated techniques to evaluate biopsies can prevent errors, reduce pathologist workload and provide objective analysis. Fourier transform infrared (FT-IR) spectroscopic imaging provides both molecular signatures and spatial information that may be applicable for pathology. Here, we utilize both the spectral and spatial information to develop a combined classifier that provides rapid tissue assessment. First, we evaluated the potential of IR imaging to provide a diagnosis using spectral data alone. While highly accurate histologic [epithelium, stroma] recognition could be achieved, the same was not possible for disease [cancer, no-cancer] due to the diversity of spectral signals. Hence, we employed spatial data, developing and evaluating increasingly complex models, to detect cancers. Sub-mm tumors could be very confidently predicted as indicated by the quantitative measurement of accuracy via receiver operating characteristic (ROC) curve analyses. The developed protocol was validated with a small set and statistical performance used to develop a model that predicts study design for a large scale, definitive validation. The results of evaluation on different instruments, at higher noise levels, under a coarser spectral resolution and two sampling modes [transmission and transflection], indicate that the protocol is highly accurate under a variety of conditions. The study paves the way to validating IR imaging for rapid breast tumor detection, its statistical validation and potential directions for optimization of the speed and sampling for clinical deployment.",
author = "Pounder, {F. Nell} and Reddy, {Rohith K.} and Rohit Bhargava",
year = "2016",
month = "1",
day = "1",
doi = "10.1039/c5fd00199d",
language = "English (US)",
volume = "187",
pages = "43--68",
journal = "Faraday Discussions",
issn = "1364-5498",
publisher = "Royal Society of Chemistry",

}

TY - JOUR

T1 - Development of a practical spatial-spectral analysis protocol for breast histopathology using Fourier transform infrared spectroscopic imaging

AU - Pounder, F. Nell

AU - Reddy, Rohith K.

AU - Bhargava, Rohit

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Breast cancer screening provides sensitive tumor identification, but low specificity implies that a vast majority of biopsies are not ultimately diagnosed as cancer. Automated techniques to evaluate biopsies can prevent errors, reduce pathologist workload and provide objective analysis. Fourier transform infrared (FT-IR) spectroscopic imaging provides both molecular signatures and spatial information that may be applicable for pathology. Here, we utilize both the spectral and spatial information to develop a combined classifier that provides rapid tissue assessment. First, we evaluated the potential of IR imaging to provide a diagnosis using spectral data alone. While highly accurate histologic [epithelium, stroma] recognition could be achieved, the same was not possible for disease [cancer, no-cancer] due to the diversity of spectral signals. Hence, we employed spatial data, developing and evaluating increasingly complex models, to detect cancers. Sub-mm tumors could be very confidently predicted as indicated by the quantitative measurement of accuracy via receiver operating characteristic (ROC) curve analyses. The developed protocol was validated with a small set and statistical performance used to develop a model that predicts study design for a large scale, definitive validation. The results of evaluation on different instruments, at higher noise levels, under a coarser spectral resolution and two sampling modes [transmission and transflection], indicate that the protocol is highly accurate under a variety of conditions. The study paves the way to validating IR imaging for rapid breast tumor detection, its statistical validation and potential directions for optimization of the speed and sampling for clinical deployment.

AB - Breast cancer screening provides sensitive tumor identification, but low specificity implies that a vast majority of biopsies are not ultimately diagnosed as cancer. Automated techniques to evaluate biopsies can prevent errors, reduce pathologist workload and provide objective analysis. Fourier transform infrared (FT-IR) spectroscopic imaging provides both molecular signatures and spatial information that may be applicable for pathology. Here, we utilize both the spectral and spatial information to develop a combined classifier that provides rapid tissue assessment. First, we evaluated the potential of IR imaging to provide a diagnosis using spectral data alone. While highly accurate histologic [epithelium, stroma] recognition could be achieved, the same was not possible for disease [cancer, no-cancer] due to the diversity of spectral signals. Hence, we employed spatial data, developing and evaluating increasingly complex models, to detect cancers. Sub-mm tumors could be very confidently predicted as indicated by the quantitative measurement of accuracy via receiver operating characteristic (ROC) curve analyses. The developed protocol was validated with a small set and statistical performance used to develop a model that predicts study design for a large scale, definitive validation. The results of evaluation on different instruments, at higher noise levels, under a coarser spectral resolution and two sampling modes [transmission and transflection], indicate that the protocol is highly accurate under a variety of conditions. The study paves the way to validating IR imaging for rapid breast tumor detection, its statistical validation and potential directions for optimization of the speed and sampling for clinical deployment.

UR - http://www.scopus.com/inward/record.url?scp=84976902806&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976902806&partnerID=8YFLogxK

U2 - 10.1039/c5fd00199d

DO - 10.1039/c5fd00199d

M3 - Article

C2 - 27095431

AN - SCOPUS:84976902806

VL - 187

SP - 43

EP - 68

JO - Faraday Discussions

JF - Faraday Discussions

SN - 1364-5498

ER -