A comparison of mid-infrared spectral regions on accuracy of tissue classification

Shachi Mittal, Rohit Bhargava

Research output: Contribution to journalArticle

Abstract

Infrared (IR) spectroscopic imaging, utilizing both the molecular and structural disease signatures, enables extensive profiling of tumors and their microenvironments. Here, we examine the relative merits of using either the fingerprint or the high frequency regions of the IR spectrum for tissue histopathology. We selected a complex model as a test case, evaluating both stromal and epithelial segmentation for various breast pathologies. IR spectral classification in each of these spectral windows is quantitatively assessed by estimating area under the curve (AUC) of the receiver operating characteristic curve (ROC) for pixel level accuracy and images for diagnostic ability. We found only small differences, though some that may be sufficiently important in diagnostic tasks to be clinically significant, between the two regions with the fingerprint region-based classifiers consistently emerging as more accurate. The work provides added evidence and comparison with fingerprint region, complex models, and previously untested tissue type (breast)-that the use of restricted spectral regions can provide high accuracy. Our study indicates that the fingerprint region is ideal for epithelial and stromal models to obtain high pixel level accuracies. Glass slides provide a limited spectral feature set but provides accurate information at the patient level.

Original languageEnglish (US)
Pages (from-to)2635-2642
Number of pages8
JournalAnalyst
Volume144
Issue number8
DOIs
StatePublished - Apr 21 2019

Fingerprint

Dermatoglyphics
Tissue
Infrared radiation
Pixels
Breast
Pathology
Tumor Microenvironment
Tumors
pixel
Classifiers
ROC Curve
Area Under Curve
Glass
Imaging techniques
histopathology
pathology
tumor
segmentation
comparison
tissue

ASJC Scopus subject areas

  • Analytical Chemistry
  • Biochemistry
  • Environmental Chemistry
  • Spectroscopy
  • Electrochemistry

Cite this

A comparison of mid-infrared spectral regions on accuracy of tissue classification. / Mittal, Shachi; Bhargava, Rohit.

In: Analyst, Vol. 144, No. 8, 21.04.2019, p. 2635-2642.

Research output: Contribution to journalArticle

@article{bb278496309740f7bc6602518d12daf4,
title = "A comparison of mid-infrared spectral regions on accuracy of tissue classification",
abstract = "Infrared (IR) spectroscopic imaging, utilizing both the molecular and structural disease signatures, enables extensive profiling of tumors and their microenvironments. Here, we examine the relative merits of using either the fingerprint or the high frequency regions of the IR spectrum for tissue histopathology. We selected a complex model as a test case, evaluating both stromal and epithelial segmentation for various breast pathologies. IR spectral classification in each of these spectral windows is quantitatively assessed by estimating area under the curve (AUC) of the receiver operating characteristic curve (ROC) for pixel level accuracy and images for diagnostic ability. We found only small differences, though some that may be sufficiently important in diagnostic tasks to be clinically significant, between the two regions with the fingerprint region-based classifiers consistently emerging as more accurate. The work provides added evidence and comparison with fingerprint region, complex models, and previously untested tissue type (breast)-that the use of restricted spectral regions can provide high accuracy. Our study indicates that the fingerprint region is ideal for epithelial and stromal models to obtain high pixel level accuracies. Glass slides provide a limited spectral feature set but provides accurate information at the patient level.",
author = "Shachi Mittal and Rohit Bhargava",
year = "2019",
month = "4",
day = "21",
doi = "10.1039/c8an01782d",
language = "English (US)",
volume = "144",
pages = "2635--2642",
journal = "Analyst",
issn = "0003-2654",
publisher = "Royal Society of Chemistry",
number = "8",

}

TY - JOUR

T1 - A comparison of mid-infrared spectral regions on accuracy of tissue classification

AU - Mittal, Shachi

AU - Bhargava, Rohit

PY - 2019/4/21

Y1 - 2019/4/21

N2 - Infrared (IR) spectroscopic imaging, utilizing both the molecular and structural disease signatures, enables extensive profiling of tumors and their microenvironments. Here, we examine the relative merits of using either the fingerprint or the high frequency regions of the IR spectrum for tissue histopathology. We selected a complex model as a test case, evaluating both stromal and epithelial segmentation for various breast pathologies. IR spectral classification in each of these spectral windows is quantitatively assessed by estimating area under the curve (AUC) of the receiver operating characteristic curve (ROC) for pixel level accuracy and images for diagnostic ability. We found only small differences, though some that may be sufficiently important in diagnostic tasks to be clinically significant, between the two regions with the fingerprint region-based classifiers consistently emerging as more accurate. The work provides added evidence and comparison with fingerprint region, complex models, and previously untested tissue type (breast)-that the use of restricted spectral regions can provide high accuracy. Our study indicates that the fingerprint region is ideal for epithelial and stromal models to obtain high pixel level accuracies. Glass slides provide a limited spectral feature set but provides accurate information at the patient level.

AB - Infrared (IR) spectroscopic imaging, utilizing both the molecular and structural disease signatures, enables extensive profiling of tumors and their microenvironments. Here, we examine the relative merits of using either the fingerprint or the high frequency regions of the IR spectrum for tissue histopathology. We selected a complex model as a test case, evaluating both stromal and epithelial segmentation for various breast pathologies. IR spectral classification in each of these spectral windows is quantitatively assessed by estimating area under the curve (AUC) of the receiver operating characteristic curve (ROC) for pixel level accuracy and images for diagnostic ability. We found only small differences, though some that may be sufficiently important in diagnostic tasks to be clinically significant, between the two regions with the fingerprint region-based classifiers consistently emerging as more accurate. The work provides added evidence and comparison with fingerprint region, complex models, and previously untested tissue type (breast)-that the use of restricted spectral regions can provide high accuracy. Our study indicates that the fingerprint region is ideal for epithelial and stromal models to obtain high pixel level accuracies. Glass slides provide a limited spectral feature set but provides accurate information at the patient level.

UR - http://www.scopus.com/inward/record.url?scp=85064162605&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064162605&partnerID=8YFLogxK

U2 - 10.1039/c8an01782d

DO - 10.1039/c8an01782d

M3 - Article

VL - 144

SP - 2635

EP - 2642

JO - Analyst

JF - Analyst

SN - 0003-2654

IS - 8

ER -