Reconstructing FT-IR spectroscopic imaging data with a sparse prior

Spencer P. Brady, Minh N. Do, Rohit Bhargava

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

Abstract

Fourier Transform Infrared (FT-IR) spectroscopic imaging is a potentially valuable tool for diagnosing breast and prostate cancer, but its clinical deployment is limited due to long data acquisition times and vast storage requirements. To counter this limitation, we develop a sparse representation for FT-IR absorbance spectra using a learned dictionary. This sparse representation is used as prior knowledge in regularizing the compressed sensing inverse problem. The data size and acquisition time are directly proportional to the length of the measured signal, namely the interferogram. Hence, we model our measurement process as interferogram truncation, which we implement by low pass filtering and downsampling in the spectral domain. With a downsample factor of four, our reconstruction is adequate for tissue classification and provides a Peak Signal-to-noise Ratio (PSNR) of 41.92 dB, while standard interpolation of the same low resolution measurements can only provide a PSNR of 36.93 dB.

Original languageEnglish (US)
Title of host publication2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings
PublisherIEEE Computer Society
Pages829-832
Number of pages4
ISBN (Print)9781424456543
DOIs
StatePublished - Jan 1 2009
Event2009 IEEE International Conference on Image Processing, ICIP 2009 - Cairo, Egypt
Duration: Nov 7 2009Nov 10 2009

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880

Other

Other2009 IEEE International Conference on Image Processing, ICIP 2009
CountryEgypt
CityCairo
Period11/7/0911/10/09

Fingerprint

Signal to noise ratio
Fourier transforms
Infrared radiation
Imaging techniques
Compressed sensing
Glossaries
Inverse problems
Data acquisition
Interpolation
Tissue

Keywords

  • FT-IR
  • K-SVD
  • l-minimization

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Brady, S. P., Do, M. N., & Bhargava, R. (2009). Reconstructing FT-IR spectroscopic imaging data with a sparse prior. In 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings (pp. 829-832). [5414384] (Proceedings - International Conference on Image Processing, ICIP). IEEE Computer Society. https://doi.org/10.1109/ICIP.2009.5414384

Reconstructing FT-IR spectroscopic imaging data with a sparse prior. / Brady, Spencer P.; Do, Minh N.; Bhargava, Rohit.

2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society, 2009. p. 829-832 5414384 (Proceedings - International Conference on Image Processing, ICIP).

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

Brady, SP, Do, MN & Bhargava, R 2009, Reconstructing FT-IR spectroscopic imaging data with a sparse prior. in 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings., 5414384, Proceedings - International Conference on Image Processing, ICIP, IEEE Computer Society, pp. 829-832, 2009 IEEE International Conference on Image Processing, ICIP 2009, Cairo, Egypt, 11/7/09. https://doi.org/10.1109/ICIP.2009.5414384
Brady SP, Do MN, Bhargava R. Reconstructing FT-IR spectroscopic imaging data with a sparse prior. In 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society. 2009. p. 829-832. 5414384. (Proceedings - International Conference on Image Processing, ICIP). https://doi.org/10.1109/ICIP.2009.5414384
Brady, Spencer P. ; Do, Minh N. ; Bhargava, Rohit. / Reconstructing FT-IR spectroscopic imaging data with a sparse prior. 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings. IEEE Computer Society, 2009. pp. 829-832 (Proceedings - International Conference on Image Processing, ICIP).
@inproceedings{332222ae7f0840099e813ddbd02e7571,
title = "Reconstructing FT-IR spectroscopic imaging data with a sparse prior",
abstract = "Fourier Transform Infrared (FT-IR) spectroscopic imaging is a potentially valuable tool for diagnosing breast and prostate cancer, but its clinical deployment is limited due to long data acquisition times and vast storage requirements. To counter this limitation, we develop a sparse representation for FT-IR absorbance spectra using a learned dictionary. This sparse representation is used as prior knowledge in regularizing the compressed sensing inverse problem. The data size and acquisition time are directly proportional to the length of the measured signal, namely the interferogram. Hence, we model our measurement process as interferogram truncation, which we implement by low pass filtering and downsampling in the spectral domain. With a downsample factor of four, our reconstruction is adequate for tissue classification and provides a Peak Signal-to-noise Ratio (PSNR) of 41.92 dB, while standard interpolation of the same low resolution measurements can only provide a PSNR of 36.93 dB.",
keywords = "FT-IR, K-SVD, l-minimization",
author = "Brady, {Spencer P.} and Do, {Minh N.} and Rohit Bhargava",
year = "2009",
month = "1",
day = "1",
doi = "10.1109/ICIP.2009.5414384",
language = "English (US)",
isbn = "9781424456543",
series = "Proceedings - International Conference on Image Processing, ICIP",
publisher = "IEEE Computer Society",
pages = "829--832",
booktitle = "2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings",

}

TY - GEN

T1 - Reconstructing FT-IR spectroscopic imaging data with a sparse prior

AU - Brady, Spencer P.

AU - Do, Minh N.

AU - Bhargava, Rohit

PY - 2009/1/1

Y1 - 2009/1/1

N2 - Fourier Transform Infrared (FT-IR) spectroscopic imaging is a potentially valuable tool for diagnosing breast and prostate cancer, but its clinical deployment is limited due to long data acquisition times and vast storage requirements. To counter this limitation, we develop a sparse representation for FT-IR absorbance spectra using a learned dictionary. This sparse representation is used as prior knowledge in regularizing the compressed sensing inverse problem. The data size and acquisition time are directly proportional to the length of the measured signal, namely the interferogram. Hence, we model our measurement process as interferogram truncation, which we implement by low pass filtering and downsampling in the spectral domain. With a downsample factor of four, our reconstruction is adequate for tissue classification and provides a Peak Signal-to-noise Ratio (PSNR) of 41.92 dB, while standard interpolation of the same low resolution measurements can only provide a PSNR of 36.93 dB.

AB - Fourier Transform Infrared (FT-IR) spectroscopic imaging is a potentially valuable tool for diagnosing breast and prostate cancer, but its clinical deployment is limited due to long data acquisition times and vast storage requirements. To counter this limitation, we develop a sparse representation for FT-IR absorbance spectra using a learned dictionary. This sparse representation is used as prior knowledge in regularizing the compressed sensing inverse problem. The data size and acquisition time are directly proportional to the length of the measured signal, namely the interferogram. Hence, we model our measurement process as interferogram truncation, which we implement by low pass filtering and downsampling in the spectral domain. With a downsample factor of four, our reconstruction is adequate for tissue classification and provides a Peak Signal-to-noise Ratio (PSNR) of 41.92 dB, while standard interpolation of the same low resolution measurements can only provide a PSNR of 36.93 dB.

KW - FT-IR

KW - K-SVD

KW - l-minimization

UR - http://www.scopus.com/inward/record.url?scp=77951950767&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951950767&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2009.5414384

DO - 10.1109/ICIP.2009.5414384

M3 - Conference contribution

AN - SCOPUS:77951950767

SN - 9781424456543

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 829

EP - 832

BT - 2009 IEEE International Conference on Image Processing, ICIP 2009 - Proceedings

PB - IEEE Computer Society

ER -