Photoacoustic spectroscopy based investigatory approach to discriminate breast cancer from normal

A pilot study

Mallika Priya, Bola Sadashiva Satish Rao, Subhash Chandra, Satadru Ray, Stanley Mathew, Anirbit Datta, Subramanya G. Nayak, Krishna Kishore Mahato

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

2 Citations (Scopus)

Abstract

In spite of many efforts for early detection of breast cancer, there is still lack of technology for immediate implementation. In the present study, the potential photoacoustic spectroscopy was evaluated in discriminating breast cancer from normal, involving blood serum samples seeking early detection. Three photoacoustic spectra in time domain were recorded from each of 20 normal and 20 malignant samples at 281nm pulsed laser excitations and a total of 120 spectra were generated. The time domain spectra were then Fast Fourier Transformed into frequency domain and 116.5625 - 206.875 kHz region was selected for further analysis using a combinational approach of wavelet, PCA and logistic regression. Initially, wavelet analysis was performed on the FFT data and seven features (mean, median, area under the curve, variance, standard deviation, skewness and kurtosis) from each were extracted. PCA was then performed on the feature matrix (7x120) for discriminating malignant samples from the normal by plotting a decision boundary using logistic regression analysis. The unsupervised mode of classification used in the present study yielded specificity and sensitivity values of 100% in each respectively with a ROC - AUC value of 1. The results obtained have clearly demonstrated the capability of photoacoustic spectroscopy in discriminating cancer from the normal, suggesting its possible clinical implications.

Original languageEnglish
Title of host publicationPhotonic Therapeutics and Diagnostics XII
PublisherSPIE
Volume9689
ISBN (Electronic)9781628419245
DOIs
Publication statusPublished - 2016
EventPhotonic Therapeutics and Diagnostics XI - San Francisco, United States
Duration: 07-02-201508-02-2015

Conference

ConferencePhotonic Therapeutics and Diagnostics XI
CountryUnited States
CitySan Francisco
Period07-02-1508-02-15

Fingerprint

Photoacoustic spectroscopy
Passive Cutaneous Anaphylaxis
photoacoustic spectroscopy
breast
Area Under Curve
Logistics
Spectrum Analysis
Logistic Models
cancer
logistics
Breast Neoplasms
Wavelet Analysis
Laser excitation
Photoacoustic effect
regression analysis
Wavelet analysis
Pulsed lasers
Early Detection of Cancer
Regression analysis
Fast Fourier transforms

All Science Journal Classification (ASJC) codes

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

Cite this

Priya, Mallika ; Rao, Bola Sadashiva Satish ; Chandra, Subhash ; Ray, Satadru ; Mathew, Stanley ; Datta, Anirbit ; Nayak, Subramanya G. ; Mahato, Krishna Kishore. / Photoacoustic spectroscopy based investigatory approach to discriminate breast cancer from normal : A pilot study. Photonic Therapeutics and Diagnostics XII. Vol. 9689 SPIE, 2016.
@inproceedings{762d0e50215e49d5bbaba6a9bf052356,
title = "Photoacoustic spectroscopy based investigatory approach to discriminate breast cancer from normal: A pilot study",
abstract = "In spite of many efforts for early detection of breast cancer, there is still lack of technology for immediate implementation. In the present study, the potential photoacoustic spectroscopy was evaluated in discriminating breast cancer from normal, involving blood serum samples seeking early detection. Three photoacoustic spectra in time domain were recorded from each of 20 normal and 20 malignant samples at 281nm pulsed laser excitations and a total of 120 spectra were generated. The time domain spectra were then Fast Fourier Transformed into frequency domain and 116.5625 - 206.875 kHz region was selected for further analysis using a combinational approach of wavelet, PCA and logistic regression. Initially, wavelet analysis was performed on the FFT data and seven features (mean, median, area under the curve, variance, standard deviation, skewness and kurtosis) from each were extracted. PCA was then performed on the feature matrix (7x120) for discriminating malignant samples from the normal by plotting a decision boundary using logistic regression analysis. The unsupervised mode of classification used in the present study yielded specificity and sensitivity values of 100{\%} in each respectively with a ROC - AUC value of 1. The results obtained have clearly demonstrated the capability of photoacoustic spectroscopy in discriminating cancer from the normal, suggesting its possible clinical implications.",
author = "Mallika Priya and Rao, {Bola Sadashiva Satish} and Subhash Chandra and Satadru Ray and Stanley Mathew and Anirbit Datta and Nayak, {Subramanya G.} and Mahato, {Krishna Kishore}",
year = "2016",
doi = "10.1117/12.2210900",
language = "English",
volume = "9689",
booktitle = "Photonic Therapeutics and Diagnostics XII",
publisher = "SPIE",
address = "United States",

}

Priya, M, Rao, BSS, Chandra, S, Ray, S, Mathew, S, Datta, A, Nayak, SG & Mahato, KK 2016, Photoacoustic spectroscopy based investigatory approach to discriminate breast cancer from normal: A pilot study. in Photonic Therapeutics and Diagnostics XII. vol. 9689, 968943, SPIE, Photonic Therapeutics and Diagnostics XI, San Francisco, United States, 07-02-15. https://doi.org/10.1117/12.2210900

Photoacoustic spectroscopy based investigatory approach to discriminate breast cancer from normal : A pilot study. / Priya, Mallika; Rao, Bola Sadashiva Satish; Chandra, Subhash; Ray, Satadru; Mathew, Stanley; Datta, Anirbit; Nayak, Subramanya G.; Mahato, Krishna Kishore.

Photonic Therapeutics and Diagnostics XII. Vol. 9689 SPIE, 2016. 968943.

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

TY - GEN

T1 - Photoacoustic spectroscopy based investigatory approach to discriminate breast cancer from normal

T2 - A pilot study

AU - Priya, Mallika

AU - Rao, Bola Sadashiva Satish

AU - Chandra, Subhash

AU - Ray, Satadru

AU - Mathew, Stanley

AU - Datta, Anirbit

AU - Nayak, Subramanya G.

AU - Mahato, Krishna Kishore

PY - 2016

Y1 - 2016

N2 - In spite of many efforts for early detection of breast cancer, there is still lack of technology for immediate implementation. In the present study, the potential photoacoustic spectroscopy was evaluated in discriminating breast cancer from normal, involving blood serum samples seeking early detection. Three photoacoustic spectra in time domain were recorded from each of 20 normal and 20 malignant samples at 281nm pulsed laser excitations and a total of 120 spectra were generated. The time domain spectra were then Fast Fourier Transformed into frequency domain and 116.5625 - 206.875 kHz region was selected for further analysis using a combinational approach of wavelet, PCA and logistic regression. Initially, wavelet analysis was performed on the FFT data and seven features (mean, median, area under the curve, variance, standard deviation, skewness and kurtosis) from each were extracted. PCA was then performed on the feature matrix (7x120) for discriminating malignant samples from the normal by plotting a decision boundary using logistic regression analysis. The unsupervised mode of classification used in the present study yielded specificity and sensitivity values of 100% in each respectively with a ROC - AUC value of 1. The results obtained have clearly demonstrated the capability of photoacoustic spectroscopy in discriminating cancer from the normal, suggesting its possible clinical implications.

AB - In spite of many efforts for early detection of breast cancer, there is still lack of technology for immediate implementation. In the present study, the potential photoacoustic spectroscopy was evaluated in discriminating breast cancer from normal, involving blood serum samples seeking early detection. Three photoacoustic spectra in time domain were recorded from each of 20 normal and 20 malignant samples at 281nm pulsed laser excitations and a total of 120 spectra were generated. The time domain spectra were then Fast Fourier Transformed into frequency domain and 116.5625 - 206.875 kHz region was selected for further analysis using a combinational approach of wavelet, PCA and logistic regression. Initially, wavelet analysis was performed on the FFT data and seven features (mean, median, area under the curve, variance, standard deviation, skewness and kurtosis) from each were extracted. PCA was then performed on the feature matrix (7x120) for discriminating malignant samples from the normal by plotting a decision boundary using logistic regression analysis. The unsupervised mode of classification used in the present study yielded specificity and sensitivity values of 100% in each respectively with a ROC - AUC value of 1. The results obtained have clearly demonstrated the capability of photoacoustic spectroscopy in discriminating cancer from the normal, suggesting its possible clinical implications.

UR - http://www.scopus.com/inward/record.url?scp=84973392605&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973392605&partnerID=8YFLogxK

U2 - 10.1117/12.2210900

DO - 10.1117/12.2210900

M3 - Conference contribution

VL - 9689

BT - Photonic Therapeutics and Diagnostics XII

PB - SPIE

ER -