Validating the cancer diagnosis potential of mid-infrared spectroscopic imaging

F. Nell Pounder, Rohith K. Reddy, Michael J. Walsh, Rohit Bhargava

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Histologic diagnosis is the gold standard for evaluating the presence and severity of most cancers. Unfortunately, the manual nature of histologic recognition leads to low throughput and errors. Here, we report on the evaluation of an automated means to accurate histologic recognition using mid-infrared spectroscopic imaging. The method does not need dyes or probes and dispenses with human input but relies on computational approaches to provide decisions. Hence, the results must be rigorously validated. We present here a validation of two-class models for pixel-level histologic segmentation and pathologic classification by spatial polling for breast carcinoma. We also discuss optimization of spectral resolution and instrumentation for clinical translation.

Original languageEnglish (US)
Title of host publicationOptical Diagnostics and Sensing IX
DOIs
StatePublished - Jun 15 2009
EventOptical Diagnostics and Sensing IX - San Jose, CA, United States
Duration: Jan 26 2009Jan 27 2009

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7186
ISSN (Print)1605-7422

Other

OtherOptical Diagnostics and Sensing IX
CountryUnited States
CitySan Jose, CA
Period1/26/091/27/09

Fingerprint

Spectral resolution
Coloring Agents
Dyes
Pixels
cancer
Throughput
Breast Neoplasms
Infrared radiation
Imaging techniques
breast
spectral resolution
Neoplasms
dyes
pixels
optimization
evaluation
probes

Keywords

  • Breast
  • Cancer
  • chemical imaging
  • Diagnosis
  • Fourier transform infrared spectroscopy
  • FT-IR
  • Imaging
  • Mid-IR, FPA
  • Spatial polling
  • Spectral resolution

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Pounder, F. N., Reddy, R. K., Walsh, M. J., & Bhargava, R. (2009). Validating the cancer diagnosis potential of mid-infrared spectroscopic imaging. In Optical Diagnostics and Sensing IX [71860f] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 7186). https://doi.org/10.1117/12.810122

Validating the cancer diagnosis potential of mid-infrared spectroscopic imaging. / Pounder, F. Nell; Reddy, Rohith K.; Walsh, Michael J.; Bhargava, Rohit.

Optical Diagnostics and Sensing IX. 2009. 71860f (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 7186).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Pounder, FN, Reddy, RK, Walsh, MJ & Bhargava, R 2009, Validating the cancer diagnosis potential of mid-infrared spectroscopic imaging. in Optical Diagnostics and Sensing IX., 71860f, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 7186, Optical Diagnostics and Sensing IX, San Jose, CA, United States, 1/26/09. https://doi.org/10.1117/12.810122
Pounder FN, Reddy RK, Walsh MJ, Bhargava R. Validating the cancer diagnosis potential of mid-infrared spectroscopic imaging. In Optical Diagnostics and Sensing IX. 2009. 71860f. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.810122
Pounder, F. Nell ; Reddy, Rohith K. ; Walsh, Michael J. ; Bhargava, Rohit. / Validating the cancer diagnosis potential of mid-infrared spectroscopic imaging. Optical Diagnostics and Sensing IX. 2009. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
@inproceedings{9ce725fac7cf4ec297f99b8d0461e90c,
title = "Validating the cancer diagnosis potential of mid-infrared spectroscopic imaging",
abstract = "Histologic diagnosis is the gold standard for evaluating the presence and severity of most cancers. Unfortunately, the manual nature of histologic recognition leads to low throughput and errors. Here, we report on the evaluation of an automated means to accurate histologic recognition using mid-infrared spectroscopic imaging. The method does not need dyes or probes and dispenses with human input but relies on computational approaches to provide decisions. Hence, the results must be rigorously validated. We present here a validation of two-class models for pixel-level histologic segmentation and pathologic classification by spatial polling for breast carcinoma. We also discuss optimization of spectral resolution and instrumentation for clinical translation.",
keywords = "Breast, Cancer, chemical imaging, Diagnosis, Fourier transform infrared spectroscopy, FT-IR, Imaging, Mid-IR, FPA, Spatial polling, Spectral resolution",
author = "Pounder, {F. Nell} and Reddy, {Rohith K.} and Walsh, {Michael J.} and Rohit Bhargava",
year = "2009",
month = "6",
day = "15",
doi = "10.1117/12.810122",
language = "English (US)",
isbn = "9780819474322",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
booktitle = "Optical Diagnostics and Sensing IX",

}

TY - GEN

T1 - Validating the cancer diagnosis potential of mid-infrared spectroscopic imaging

AU - Pounder, F. Nell

AU - Reddy, Rohith K.

AU - Walsh, Michael J.

AU - Bhargava, Rohit

PY - 2009/6/15

Y1 - 2009/6/15

N2 - Histologic diagnosis is the gold standard for evaluating the presence and severity of most cancers. Unfortunately, the manual nature of histologic recognition leads to low throughput and errors. Here, we report on the evaluation of an automated means to accurate histologic recognition using mid-infrared spectroscopic imaging. The method does not need dyes or probes and dispenses with human input but relies on computational approaches to provide decisions. Hence, the results must be rigorously validated. We present here a validation of two-class models for pixel-level histologic segmentation and pathologic classification by spatial polling for breast carcinoma. We also discuss optimization of spectral resolution and instrumentation for clinical translation.

AB - Histologic diagnosis is the gold standard for evaluating the presence and severity of most cancers. Unfortunately, the manual nature of histologic recognition leads to low throughput and errors. Here, we report on the evaluation of an automated means to accurate histologic recognition using mid-infrared spectroscopic imaging. The method does not need dyes or probes and dispenses with human input but relies on computational approaches to provide decisions. Hence, the results must be rigorously validated. We present here a validation of two-class models for pixel-level histologic segmentation and pathologic classification by spatial polling for breast carcinoma. We also discuss optimization of spectral resolution and instrumentation for clinical translation.

KW - Breast

KW - Cancer

KW - chemical imaging

KW - Diagnosis

KW - Fourier transform infrared spectroscopy

KW - FT-IR

KW - Imaging

KW - Mid-IR, FPA

KW - Spatial polling

KW - Spectral resolution

UR - http://www.scopus.com/inward/record.url?scp=66749157267&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=66749157267&partnerID=8YFLogxK

U2 - 10.1117/12.810122

DO - 10.1117/12.810122

M3 - Conference contribution

AN - SCOPUS:66749157267

SN - 9780819474322

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Optical Diagnostics and Sensing IX

ER -