Biomedical applications of the information-efficient spectral imaging sensor (ISIS)

Stephen M. Gentry, Richard M Levenson

Research output: Contribution to journalConference article

5 Citations (Scopus)

Abstract

The Information-efficient Spectral Imaging Sensor (ISIS) approach to spectral imaging seeks to bridge the gap between tuned multispectral and fixed hyperspectral imaging sensors. By allowing the definition of completely general spectral filter functions, truly optimal measurements can be made for a given task. These optimal measurements significantly improve signal-to-noise ratio (SNR) and speed, minimize data volume and data rate, while preserving classification accuracy. The following paper investigates the application of the ISIS sensing approach in two sample biomedical applications: prostate and colon cancer screening. It is shown that in these applications, two to three optimal measurements are sufficient to capture the majority of classification information for critical sample constituents. In the prostate cancer example, the optimal measurements: allow 8% relative improvement in classification accuracy of critical cell constituents over a red, green, blue (RGB) sensor. In the colon cancer example, use of optimal measurements boost the classification accuracy of critical cell constituents by 28% relative to the RGB sensor. In both cases, optimal measurements match the performance achieved by the entire hyperspectral data set. The paper concludes that an ISIS style spectral imager can acquire these optimal spectral images directly, allowing improved classification accuracy over an RGB sensor. Compared to a hyperspectral sensor, the ISIS approach can achieve similar classification accuracy using a significantly lower number of spectral samples, thus minimizing overall sample classification time and cost.

Original languageEnglish (US)
Pages (from-to)129-142
Number of pages14
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume3603
StatePublished - Jan 1 1999
Externally publishedYes
EventProceedings of the 1999 Systems and Technologies for Clinical Diagnostics and Drug Discovery II - San Jose, CA, USA
Duration: Jan 24 1999Jan 25 1999

Fingerprint

Spectral Imaging
Biomedical Applications
Imaging techniques
Sensor
sensors
Sensors
cancer
Cancer
Hyperspectral Data
Hyperspectral Imaging
Prostate Cancer
Cell
Imager
acceleration (physics)
cells
Image sensors
preserving
Screening
Signal to noise ratio
signal to noise ratios

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Biomedical applications of the information-efficient spectral imaging sensor (ISIS). / Gentry, Stephen M.; Levenson, Richard M.

In: Proceedings of SPIE - The International Society for Optical Engineering, Vol. 3603, 01.01.1999, p. 129-142.

Research output: Contribution to journalConference article

@article{01c4d71faffd4e51818c884db6002aeb,
title = "Biomedical applications of the information-efficient spectral imaging sensor (ISIS)",
abstract = "The Information-efficient Spectral Imaging Sensor (ISIS) approach to spectral imaging seeks to bridge the gap between tuned multispectral and fixed hyperspectral imaging sensors. By allowing the definition of completely general spectral filter functions, truly optimal measurements can be made for a given task. These optimal measurements significantly improve signal-to-noise ratio (SNR) and speed, minimize data volume and data rate, while preserving classification accuracy. The following paper investigates the application of the ISIS sensing approach in two sample biomedical applications: prostate and colon cancer screening. It is shown that in these applications, two to three optimal measurements are sufficient to capture the majority of classification information for critical sample constituents. In the prostate cancer example, the optimal measurements: allow 8{\%} relative improvement in classification accuracy of critical cell constituents over a red, green, blue (RGB) sensor. In the colon cancer example, use of optimal measurements boost the classification accuracy of critical cell constituents by 28{\%} relative to the RGB sensor. In both cases, optimal measurements match the performance achieved by the entire hyperspectral data set. The paper concludes that an ISIS style spectral imager can acquire these optimal spectral images directly, allowing improved classification accuracy over an RGB sensor. Compared to a hyperspectral sensor, the ISIS approach can achieve similar classification accuracy using a significantly lower number of spectral samples, thus minimizing overall sample classification time and cost.",
author = "Gentry, {Stephen M.} and Levenson, {Richard M}",
year = "1999",
month = "1",
day = "1",
language = "English (US)",
volume = "3603",
pages = "129--142",
journal = "Proceedings of SPIE - The International Society for Optical Engineering",
issn = "0277-786X",
publisher = "SPIE",

}

TY - JOUR

T1 - Biomedical applications of the information-efficient spectral imaging sensor (ISIS)

AU - Gentry, Stephen M.

AU - Levenson, Richard M

PY - 1999/1/1

Y1 - 1999/1/1

N2 - The Information-efficient Spectral Imaging Sensor (ISIS) approach to spectral imaging seeks to bridge the gap between tuned multispectral and fixed hyperspectral imaging sensors. By allowing the definition of completely general spectral filter functions, truly optimal measurements can be made for a given task. These optimal measurements significantly improve signal-to-noise ratio (SNR) and speed, minimize data volume and data rate, while preserving classification accuracy. The following paper investigates the application of the ISIS sensing approach in two sample biomedical applications: prostate and colon cancer screening. It is shown that in these applications, two to three optimal measurements are sufficient to capture the majority of classification information for critical sample constituents. In the prostate cancer example, the optimal measurements: allow 8% relative improvement in classification accuracy of critical cell constituents over a red, green, blue (RGB) sensor. In the colon cancer example, use of optimal measurements boost the classification accuracy of critical cell constituents by 28% relative to the RGB sensor. In both cases, optimal measurements match the performance achieved by the entire hyperspectral data set. The paper concludes that an ISIS style spectral imager can acquire these optimal spectral images directly, allowing improved classification accuracy over an RGB sensor. Compared to a hyperspectral sensor, the ISIS approach can achieve similar classification accuracy using a significantly lower number of spectral samples, thus minimizing overall sample classification time and cost.

AB - The Information-efficient Spectral Imaging Sensor (ISIS) approach to spectral imaging seeks to bridge the gap between tuned multispectral and fixed hyperspectral imaging sensors. By allowing the definition of completely general spectral filter functions, truly optimal measurements can be made for a given task. These optimal measurements significantly improve signal-to-noise ratio (SNR) and speed, minimize data volume and data rate, while preserving classification accuracy. The following paper investigates the application of the ISIS sensing approach in two sample biomedical applications: prostate and colon cancer screening. It is shown that in these applications, two to three optimal measurements are sufficient to capture the majority of classification information for critical sample constituents. In the prostate cancer example, the optimal measurements: allow 8% relative improvement in classification accuracy of critical cell constituents over a red, green, blue (RGB) sensor. In the colon cancer example, use of optimal measurements boost the classification accuracy of critical cell constituents by 28% relative to the RGB sensor. In both cases, optimal measurements match the performance achieved by the entire hyperspectral data set. The paper concludes that an ISIS style spectral imager can acquire these optimal spectral images directly, allowing improved classification accuracy over an RGB sensor. Compared to a hyperspectral sensor, the ISIS approach can achieve similar classification accuracy using a significantly lower number of spectral samples, thus minimizing overall sample classification time and cost.

UR - http://www.scopus.com/inward/record.url?scp=0032652023&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032652023&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0032652023

VL - 3603

SP - 129

EP - 142

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

SN - 0277-786X

ER -