Spectral features selection and classification for bimodal optical spectroscopy applied to bladder cancer in vivo diagnosis

Emilie Pery; Walter Blondel; Samy Tindel; Maha Ghribi; Agnès Leroux; François Guillemin

hal-00541125, version 1

Spectral features selection and classification for bimodal optical spectroscopy applied to bladder cancer in vivo diagnosis

Emilie Pery ¹, Walter Blondel ¹, Samy Tindel ², Maha Ghribi ³, Agnès Leroux ⁴, François Guillemin ^1, 4

IEEE Transactions on Biomedical Engineering (2013) Article in Press, Corrected Proof

Abstract: This paper describes an experimental study combining spatially resolved AutoFluorescence (AF) and Diffuse Reflectance (DR) fibred spectroscopies to discriminate in vivo between healthy and pathological tissues in a preclinical model of bladder cancer. Then, a detailed step-by-step analysis scheme is presented for the extraction and the selection of discriminative spectral features (correlation, Linear Discriminant and Logistic Regression Analysis), and for the spectroscopic data final classification algorithms (Regularized Discriminant Analysis and Support Vector Machines). Significant differences between healthy, inflammatory and tumoral tissues were obtained by selecting a reasonable number of discriminant spectral features from AF, DR and Intrinsic Fluorescence spectra, leading to improved sensitivity (87%) and specificity (77%) compared to monomodality (AF or DR alone).

1: Centre de recherche en automatique de Nancy (CRAN)
CNRS : UMR7039 – Université Henri Poincaré - Nancy I – Institut National Polytechnique de Lorraine (INPL)
2: Institut Elie Cartan Nancy (IECN)
CNRS : UMR7502 – INRIA – Université Henri Poincaré - Nancy I – Université Nancy II – Institut National Polytechnique de Lorraine (INPL)
3: Institut de l'information scientifique et technique (INIST)
CNRS : UPS76
4: Centre Alexis Vautrin
CRLCC Alexis Vautrin

hal-00541125, version 1
http://hal.archives-ouvertes.fr/hal-00541125
oai:hal.archives-ouvertes.fr:hal-00541125
From: Didier Wolf <>
Submitted on: Monday, 29 November 2010 20:32:16
Updated on: Saturday, 15 December 2012 13:57:01

See detailed view

Associated documents

DOI: 10.1109/TBME.2010.2103559

Export

Bibtex EndNote TEI RefWorks

%% hal-00541125, version 1
%% http://hal.archives-ouvertes.fr/hal-00541125
@article{pery:hal-00541125,
    hal_id = {hal-00541125},
    url = {http://hal.archives-ouvertes.fr/hal-00541125},
    title = {{Spectral features selection and classification for bimodal optical spectroscopy applied to bladder cancer in vivo diagnosis}},
    author = {Pery, Emilie and Blondel, Walter and Tindel, Samy and Ghribi, Maha and Leroux, Agn{\`e}s and Guillemin, Fran{\c c}ois},
    abstract = {{This paper describes an experimental study combining spatially resolved AutoFluorescence (AF) and Diffuse Reflectance (DR) fibred spectroscopies to discriminate in vivo between healthy and pathological tissues in a preclinical model of bladder cancer. Then, a detailed step-by-step analysis scheme is presented for the extraction and the selection of discriminative spectral features (correlation, Linear Discriminant and Logistic Regression Analysis), and for the spectroscopic data final classification algorithms (Regularized Discriminant Analysis and Support Vector Machines). Significant differences between healthy, inflammatory and tumoral tissues were obtained by selecting a reasonable number of discriminant spectral features from AF, DR and Intrinsic Fluorescence spectra, leading to improved sensitivity (87\%) and specificity (77\%) compared to monomodality (AF or DR alone).}},
    keywords = {Absorption; Bladder; Cancer; Feature extraction; In vivo; Spectroscopy; Tumors; autofluorescence; bladder cancer; diffuse reflectance; feature selection; supervised classification},
    language = {English},
    affiliation = {Centre de recherche en automatique de Nancy - CRAN , Institut Elie Cartan Nancy - IECN , Institut de l'information scientifique et technique - INIST , Centre Alexis Vautrin},
    pages = {Article in Press, Corrected Proof},
    journal = {IEEE Transactions on Biomedical Engineering},
    note = {IPS, SBS IPS, SBS },
    audience = {international },
    doi = {10.1109/TBME.2010.2103559 },
    year = {2013},
}

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="article"><head>Articles in peer-reviewed journal</head>
<biblStruct type="article" xml:id="hal-00541125"><analytic>
<author><persName><forename>Emilie</forename><surname>Pery</surname></persName>
<affiliation>
<orgName type="laboratory">CRAN</orgName>
<orgName type="team">Centre de recherche en automatique de Nancy</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR7039</orgName>
<orgName type="institution">Université Henri Poincaré - Nancy I</orgName>
<orgName type="institution">Institut National Polytechnique de Lorraine (INPL)</orgName>
</affiliation>
</author>
<author><persName><forename>Walter</forename><surname>Blondel</surname></persName>
<affiliation>
<orgName type="laboratory">CRAN</orgName>
<orgName type="team">Centre de recherche en automatique de Nancy</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR7039</orgName>
<orgName type="institution">Université Henri Poincaré - Nancy I</orgName>
<orgName type="institution">Institut National Polytechnique de Lorraine (INPL)</orgName>
</affiliation>
</author>
<author><persName><forename>Samy</forename><surname>Tindel</surname></persName>
<affiliation>
<orgName type="laboratory">IECN</orgName>
<orgName type="team">Institut Elie Cartan Nancy</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR7502</orgName>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Université Henri Poincaré - Nancy I</orgName>
<orgName type="institution">Université Nancy II</orgName>
<orgName type="institution">Institut National Polytechnique de Lorraine (INPL)</orgName>
</affiliation>
</author>
<author><persName><forename>Maha</forename><surname>Ghribi</surname></persName>
<affiliation>
<orgName type="laboratory">INIST</orgName>
<orgName type="team">Institut de l'information scientifique et technique</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UPS76</orgName>
</affiliation>
</author>
<author><persName><forename>Agnès</forename><surname>Leroux</surname></persName>
<affiliation>
<orgName type="team">Centre Alexis Vautrin</orgName>
<country>FR</country>
<orgName type="institution">CRLCC Alexis Vautrin</orgName>
</affiliation>
</author>
<author><persName><forename>François</forename><surname>Guillemin</surname></persName>
<affiliation>
<orgName type="laboratory">CRAN</orgName>
<orgName type="team">Centre de recherche en automatique de Nancy</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR7039</orgName>
<orgName type="institution">Université Henri Poincaré - Nancy I</orgName>
<orgName type="institution">Institut National Polytechnique de Lorraine (INPL)</orgName>
</affiliation>
<affiliation>
<orgName type="team">Centre Alexis Vautrin</orgName>
<country>FR</country>
<orgName type="institution">CRLCC Alexis Vautrin</orgName>
</affiliation>
</author>
<title type="main" level="a">Spectral features selection and classification for bimodal optical spectroscopy applied to bladder cancer in vivo diagnosis</title></analytic><monogr><title level="j" type="main">IEEE Transactions on Biomedical Engineering</title><imprint><biblScope type="publicationDate">2013-00-00</biblScope><biblScope type="pp">Article in Press, Corrected Proof</biblScope></imprint></monogr><idno type="doi">10.1109/TBME.2010.2103559</idno><idno type="HALid">http://hal.archives-ouvertes.fr/hal-00541125</idno></biblStruct>
</listBibl>
</listBibl>