Towards better than human capability in diagnosing prostate cancer using infrared spectroscopic imaging

Xavier Llorá, Rohith Reddy, Brian Matesic, Rohit Bhargava

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

Abstract

Cancer diagnosis is essentially a human task. Almost universally, the process requires the extraction of tissue (biopsy) and examination of its microstructure by a human. To improve diagnoses based on limited and inconsistent morphologic knowledge, a new approach has recently been proposed that uses molecular spectroscopic imaging to utilize microscopic chemical composition for diagnoses. In contrast to visible imaging, the approach results in very large data sets as each pixel contains the entire molecular vibrational spectroscopy data from all chemical species. Here, we propose data handling and analysis strategies to allow computer-based diagnosis of human prostate cancer by applying a novel genetics-based machine learning technique ({\tt NAX). We apply this technique to demonstrate both fast learning and accurate classification that, additionally, scales well with parallelization. Preliminary results demonstrate that this approach can improve current clinical practice in diagnosing prostate cancer.

Original languageEnglish (US)
Title of host publicationProceedings of GECCO 2007
Subtitle of host publicationGenetic and Evolutionary Computation Conference
Pages2098-2105
Number of pages8
DOIs
StatePublished - Aug 27 2007
Event9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007 - London, United Kingdom
Duration: Jul 7 2007Jul 11 2007

Publication series

NameProceedings of GECCO 2007: Genetic and Evolutionary Computation Conference

Other

Other9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007
CountryUnited Kingdom
CityLondon
Period7/7/077/11/07

Fingerprint

Prostate Cancer
Infrared
Imaging
Infrared radiation
Imaging techniques
Genetics-based Machine Learning
Data Handling
Molecular spectroscopy
Large Data Sets
Parallelization
Inconsistent
Vibrational spectroscopy
Demonstrate
Data handling
Biopsy
Spectroscopy
Microstructure
Data analysis
Cancer
Pixel

Keywords

  • Genetics-based machine learning
  • Learning classifier Sys-tems
  • Parallelization
  • Prostate cancer

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Theoretical Computer Science

Cite this

Llorá, X., Reddy, R., Matesic, B., & Bhargava, R. (2007). Towards better than human capability in diagnosing prostate cancer using infrared spectroscopic imaging. In Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference (pp. 2098-2105). (Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference). https://doi.org/10.1145/1276958.1277366

Towards better than human capability in diagnosing prostate cancer using infrared spectroscopic imaging. / Llorá, Xavier; Reddy, Rohith; Matesic, Brian; Bhargava, Rohit.

Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference. 2007. p. 2098-2105 (Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference).

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

Llorá, X, Reddy, R, Matesic, B & Bhargava, R 2007, Towards better than human capability in diagnosing prostate cancer using infrared spectroscopic imaging. in Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference. Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference, pp. 2098-2105, 9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007, London, United Kingdom, 7/7/07. https://doi.org/10.1145/1276958.1277366
Llorá X, Reddy R, Matesic B, Bhargava R. Towards better than human capability in diagnosing prostate cancer using infrared spectroscopic imaging. In Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference. 2007. p. 2098-2105. (Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference). https://doi.org/10.1145/1276958.1277366
Llorá, Xavier ; Reddy, Rohith ; Matesic, Brian ; Bhargava, Rohit. / Towards better than human capability in diagnosing prostate cancer using infrared spectroscopic imaging. Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference. 2007. pp. 2098-2105 (Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference).
@inproceedings{67143048db2a4db582351115d1a21cd1,
title = "Towards better than human capability in diagnosing prostate cancer using infrared spectroscopic imaging",
abstract = "Cancer diagnosis is essentially a human task. Almost universally, the process requires the extraction of tissue (biopsy) and examination of its microstructure by a human. To improve diagnoses based on limited and inconsistent morphologic knowledge, a new approach has recently been proposed that uses molecular spectroscopic imaging to utilize microscopic chemical composition for diagnoses. In contrast to visible imaging, the approach results in very large data sets as each pixel contains the entire molecular vibrational spectroscopy data from all chemical species. Here, we propose data handling and analysis strategies to allow computer-based diagnosis of human prostate cancer by applying a novel genetics-based machine learning technique ({\tt NAX). We apply this technique to demonstrate both fast learning and accurate classification that, additionally, scales well with parallelization. Preliminary results demonstrate that this approach can improve current clinical practice in diagnosing prostate cancer.",
keywords = "Genetics-based machine learning, Learning classifier Sys-tems, Parallelization, Prostate cancer",
author = "Xavier Llor{\'a} and Rohith Reddy and Brian Matesic and Rohit Bhargava",
year = "2007",
month = "8",
day = "27",
doi = "10.1145/1276958.1277366",
language = "English (US)",
isbn = "1595936971",
series = "Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference",
pages = "2098--2105",
booktitle = "Proceedings of GECCO 2007",

}

TY - GEN

T1 - Towards better than human capability in diagnosing prostate cancer using infrared spectroscopic imaging

AU - Llorá, Xavier

AU - Reddy, Rohith

AU - Matesic, Brian

AU - Bhargava, Rohit

PY - 2007/8/27

Y1 - 2007/8/27

N2 - Cancer diagnosis is essentially a human task. Almost universally, the process requires the extraction of tissue (biopsy) and examination of its microstructure by a human. To improve diagnoses based on limited and inconsistent morphologic knowledge, a new approach has recently been proposed that uses molecular spectroscopic imaging to utilize microscopic chemical composition for diagnoses. In contrast to visible imaging, the approach results in very large data sets as each pixel contains the entire molecular vibrational spectroscopy data from all chemical species. Here, we propose data handling and analysis strategies to allow computer-based diagnosis of human prostate cancer by applying a novel genetics-based machine learning technique ({\tt NAX). We apply this technique to demonstrate both fast learning and accurate classification that, additionally, scales well with parallelization. Preliminary results demonstrate that this approach can improve current clinical practice in diagnosing prostate cancer.

AB - Cancer diagnosis is essentially a human task. Almost universally, the process requires the extraction of tissue (biopsy) and examination of its microstructure by a human. To improve diagnoses based on limited and inconsistent morphologic knowledge, a new approach has recently been proposed that uses molecular spectroscopic imaging to utilize microscopic chemical composition for diagnoses. In contrast to visible imaging, the approach results in very large data sets as each pixel contains the entire molecular vibrational spectroscopy data from all chemical species. Here, we propose data handling and analysis strategies to allow computer-based diagnosis of human prostate cancer by applying a novel genetics-based machine learning technique ({\tt NAX). We apply this technique to demonstrate both fast learning and accurate classification that, additionally, scales well with parallelization. Preliminary results demonstrate that this approach can improve current clinical practice in diagnosing prostate cancer.

KW - Genetics-based machine learning

KW - Learning classifier Sys-tems

KW - Parallelization

KW - Prostate cancer

UR - http://www.scopus.com/inward/record.url?scp=34548100580&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548100580&partnerID=8YFLogxK

U2 - 10.1145/1276958.1277366

DO - 10.1145/1276958.1277366

M3 - Conference contribution

AN - SCOPUS:34548100580

SN - 1595936971

SN - 9781595936974

T3 - Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference

SP - 2098

EP - 2105

BT - Proceedings of GECCO 2007

ER -