Prostate cancer diagnosis using quantitative phase imaging and machine learning algorithms

Tan H. Nguyen, Shamira Sridharan, Virgilia Macias, Andre K. Balla, Minh N. Do, Gabriel Popescu

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

Abstract

We report, for the first time, the use of Quantitative Phase Imaging (QPI) images to perform automatic prostate cancer diagnosis. A machine learning algorithm is implemented to learn textural behaviors of prostate samples imaged under QPI and produce labeled maps of different regions for testing biopsies (e.g. gland, stroma, lumen etc.). From these maps, morphological and textural features are calculated to predict outcomes of the testing samples. Current performance is reported on a dataset of more than 300 cores of various diagnosis results.

Original languageEnglish (US)
Title of host publicationQuantitative Phase Imaging
EditorsYongKeun Park, Gabriel Popescu
PublisherSPIE
ISBN (Electronic)9781628414264
DOIs
StatePublished - Jan 1 2015
Event1st Conference on Quantitative Phase Imaging, QPI 2015 - San Francisco, United States
Duration: Feb 7 2015Feb 10 2015

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume9336
ISSN (Print)1605-7422

Other

Other1st Conference on Quantitative Phase Imaging, QPI 2015
CountryUnited States
CitySan Francisco
Period2/7/152/10/15

Fingerprint

machine learning
Learning algorithms
learning
Learning systems
Prostatic Neoplasms
cancer
Imaging techniques
glands
lumens
Biopsy
Testing
Prostate
Machine Learning
Datasets

Keywords

  • Quantitative Phase Imaging
  • automatic diagnosis
  • prostate cancer
  • texton analysis

ASJC Scopus subject areas

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

Cite this

Nguyen, T. H., Sridharan, S., Macias, V., Balla, A. K., Do, M. N., & Popescu, G. (2015). Prostate cancer diagnosis using quantitative phase imaging and machine learning algorithms. In Y. Park, & G. Popescu (Eds.), Quantitative Phase Imaging [933619] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9336). SPIE. https://doi.org/10.1117/12.2080321

Prostate cancer diagnosis using quantitative phase imaging and machine learning algorithms. / Nguyen, Tan H.; Sridharan, Shamira; Macias, Virgilia; Balla, Andre K.; Do, Minh N.; Popescu, Gabriel.

Quantitative Phase Imaging. ed. / YongKeun Park; Gabriel Popescu. SPIE, 2015. 933619 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 9336).

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

Nguyen, TH, Sridharan, S, Macias, V, Balla, AK, Do, MN & Popescu, G 2015, Prostate cancer diagnosis using quantitative phase imaging and machine learning algorithms. in Y Park & G Popescu (eds), Quantitative Phase Imaging., 933619, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 9336, SPIE, 1st Conference on Quantitative Phase Imaging, QPI 2015, San Francisco, United States, 2/7/15. https://doi.org/10.1117/12.2080321
Nguyen TH, Sridharan S, Macias V, Balla AK, Do MN, Popescu G. Prostate cancer diagnosis using quantitative phase imaging and machine learning algorithms. In Park Y, Popescu G, editors, Quantitative Phase Imaging. SPIE. 2015. 933619. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.2080321
Nguyen, Tan H. ; Sridharan, Shamira ; Macias, Virgilia ; Balla, Andre K. ; Do, Minh N. ; Popescu, Gabriel. / Prostate cancer diagnosis using quantitative phase imaging and machine learning algorithms. Quantitative Phase Imaging. editor / YongKeun Park ; Gabriel Popescu. SPIE, 2015. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
@inproceedings{e062b4725e2c4bfc8ca7b4eeeffb5cfe,
title = "Prostate cancer diagnosis using quantitative phase imaging and machine learning algorithms",
abstract = "We report, for the first time, the use of Quantitative Phase Imaging (QPI) images to perform automatic prostate cancer diagnosis. A machine learning algorithm is implemented to learn textural behaviors of prostate samples imaged under QPI and produce labeled maps of different regions for testing biopsies (e.g. gland, stroma, lumen etc.). From these maps, morphological and textural features are calculated to predict outcomes of the testing samples. Current performance is reported on a dataset of more than 300 cores of various diagnosis results.",
keywords = "Quantitative Phase Imaging, automatic diagnosis, prostate cancer, texton analysis",
author = "Nguyen, {Tan H.} and Shamira Sridharan and Virgilia Macias and Balla, {Andre K.} and Do, {Minh N.} and Gabriel Popescu",
year = "2015",
month = "1",
day = "1",
doi = "10.1117/12.2080321",
language = "English (US)",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",
editor = "YongKeun Park and Gabriel Popescu",
booktitle = "Quantitative Phase Imaging",

}

TY - GEN

T1 - Prostate cancer diagnosis using quantitative phase imaging and machine learning algorithms

AU - Nguyen, Tan H.

AU - Sridharan, Shamira

AU - Macias, Virgilia

AU - Balla, Andre K.

AU - Do, Minh N.

AU - Popescu, Gabriel

PY - 2015/1/1

Y1 - 2015/1/1

N2 - We report, for the first time, the use of Quantitative Phase Imaging (QPI) images to perform automatic prostate cancer diagnosis. A machine learning algorithm is implemented to learn textural behaviors of prostate samples imaged under QPI and produce labeled maps of different regions for testing biopsies (e.g. gland, stroma, lumen etc.). From these maps, morphological and textural features are calculated to predict outcomes of the testing samples. Current performance is reported on a dataset of more than 300 cores of various diagnosis results.

AB - We report, for the first time, the use of Quantitative Phase Imaging (QPI) images to perform automatic prostate cancer diagnosis. A machine learning algorithm is implemented to learn textural behaviors of prostate samples imaged under QPI and produce labeled maps of different regions for testing biopsies (e.g. gland, stroma, lumen etc.). From these maps, morphological and textural features are calculated to predict outcomes of the testing samples. Current performance is reported on a dataset of more than 300 cores of various diagnosis results.

KW - Quantitative Phase Imaging

KW - automatic diagnosis

KW - prostate cancer

KW - texton analysis

UR - http://www.scopus.com/inward/record.url?scp=84931464411&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84931464411&partnerID=8YFLogxK

U2 - 10.1117/12.2080321

DO - 10.1117/12.2080321

M3 - Conference contribution

AN - SCOPUS:84931464411

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

BT - Quantitative Phase Imaging

A2 - Park, YongKeun

A2 - Popescu, Gabriel

PB - SPIE

ER -