Quantification of human brain metabolites from in Vivo 1 H NMR magnitude spectra using automated artificial neural network analysis

Yrjö Hiltunen, Jouni Kaartinen, Juhani Pulkkinen, Anna-Maija Häkkinen, Nina Lundbom, Risto Kauppinen

    Research output: Contribution to journalArticleScientificpeer-review

    21 Citations (Scopus)

    Abstract

    Long echo time (TE =270 ms) in vivo proton NMR spectra resembling human brain metabolite patterns were simulated for lineshape fitting (LF) and quantitative artificial neural network (ANN) analyses. A set of experimental in vivo 1 H NMR spectra were first analyzed by the LF method to match the signal-to-noise ratios and linewidths of simulated spectra to those in the experi-mental data. The performance of constructed ANNs was compared for the peak area determinations of choline-containing compounds (Cho), total creatine (Cr), and N-acetyl aspartate (NAA) signals using both manually phase-corrected and magnitude spectra as in-puts. The peak area data from ANN and LF analyses for simulated spectra yielded high correlation coefficients demonstrating that the peak areas quantified with ANNgave similar results as LF analysis. Thus, a fully automated ANN method based on magnitude spectra has demonstrated potential for quantification of in vivo metabolites from long echo time spectroscopic imaging.
    Original languageEnglish
    Pages (from-to)1-5
    JournalJournal of Magnetic Resonance
    Volume154
    Issue number1
    DOIs
    Publication statusPublished - 2002
    MoE publication typeA1 Journal article-refereed

    Fingerprint

    Electric network analysis
    Metabolites
    Brain
    Nuclear magnetic resonance
    Neural networks
    Creatine
    Choline
    Linewidth
    Protons
    Signal to noise ratio
    Imaging techniques

    Keywords

    • artificial neural network
    • 1H nuclear magnetic resonance spectroscopy
    • NMR spectroscopy
    • brain metabolites
    • metabolites
    • quantification
    • simulated spectra

    Cite this

    Hiltunen, Yrjö ; Kaartinen, Jouni ; Pulkkinen, Juhani ; Häkkinen, Anna-Maija ; Lundbom, Nina ; Kauppinen, Risto. / Quantification of human brain metabolites from in Vivo 1 H NMR magnitude spectra using automated artificial neural network analysis. In: Journal of Magnetic Resonance. 2002 ; Vol. 154, No. 1. pp. 1-5.
    @article{54dccbce65294633a881b462c894c098,
    title = "Quantification of human brain metabolites from in Vivo 1 H NMR magnitude spectra using automated artificial neural network analysis",
    abstract = "Long echo time (TE =270 ms) in vivo proton NMR spectra resembling human brain metabolite patterns were simulated for lineshape fitting (LF) and quantitative artificial neural network (ANN) analyses. A set of experimental in vivo 1 H NMR spectra were first analyzed by the LF method to match the signal-to-noise ratios and linewidths of simulated spectra to those in the experi-mental data. The performance of constructed ANNs was compared for the peak area determinations of choline-containing compounds (Cho), total creatine (Cr), and N-acetyl aspartate (NAA) signals using both manually phase-corrected and magnitude spectra as in-puts. The peak area data from ANN and LF analyses for simulated spectra yielded high correlation coefficients demonstrating that the peak areas quantified with ANNgave similar results as LF analysis. Thus, a fully automated ANN method based on magnitude spectra has demonstrated potential for quantification of in vivo metabolites from long echo time spectroscopic imaging.",
    keywords = "artificial neural network, 1H nuclear magnetic resonance spectroscopy, NMR spectroscopy, brain metabolites, metabolites, quantification, simulated spectra",
    author = "Yrj{\"o} Hiltunen and Jouni Kaartinen and Juhani Pulkkinen and Anna-Maija H{\"a}kkinen and Nina Lundbom and Risto Kauppinen",
    year = "2002",
    doi = "10.1006/jmre.2001.2457",
    language = "English",
    volume = "154",
    pages = "1--5",
    journal = "Journal of Magnetic Resonance",
    issn = "1090-7807",
    publisher = "Elsevier",
    number = "1",

    }

    Quantification of human brain metabolites from in Vivo 1 H NMR magnitude spectra using automated artificial neural network analysis. / Hiltunen, Yrjö; Kaartinen, Jouni; Pulkkinen, Juhani; Häkkinen, Anna-Maija; Lundbom, Nina; Kauppinen, Risto.

    In: Journal of Magnetic Resonance, Vol. 154, No. 1, 2002, p. 1-5.

    Research output: Contribution to journalArticleScientificpeer-review

    TY - JOUR

    T1 - Quantification of human brain metabolites from in Vivo 1 H NMR magnitude spectra using automated artificial neural network analysis

    AU - Hiltunen, Yrjö

    AU - Kaartinen, Jouni

    AU - Pulkkinen, Juhani

    AU - Häkkinen, Anna-Maija

    AU - Lundbom, Nina

    AU - Kauppinen, Risto

    PY - 2002

    Y1 - 2002

    N2 - Long echo time (TE =270 ms) in vivo proton NMR spectra resembling human brain metabolite patterns were simulated for lineshape fitting (LF) and quantitative artificial neural network (ANN) analyses. A set of experimental in vivo 1 H NMR spectra were first analyzed by the LF method to match the signal-to-noise ratios and linewidths of simulated spectra to those in the experi-mental data. The performance of constructed ANNs was compared for the peak area determinations of choline-containing compounds (Cho), total creatine (Cr), and N-acetyl aspartate (NAA) signals using both manually phase-corrected and magnitude spectra as in-puts. The peak area data from ANN and LF analyses for simulated spectra yielded high correlation coefficients demonstrating that the peak areas quantified with ANNgave similar results as LF analysis. Thus, a fully automated ANN method based on magnitude spectra has demonstrated potential for quantification of in vivo metabolites from long echo time spectroscopic imaging.

    AB - Long echo time (TE =270 ms) in vivo proton NMR spectra resembling human brain metabolite patterns were simulated for lineshape fitting (LF) and quantitative artificial neural network (ANN) analyses. A set of experimental in vivo 1 H NMR spectra were first analyzed by the LF method to match the signal-to-noise ratios and linewidths of simulated spectra to those in the experi-mental data. The performance of constructed ANNs was compared for the peak area determinations of choline-containing compounds (Cho), total creatine (Cr), and N-acetyl aspartate (NAA) signals using both manually phase-corrected and magnitude spectra as in-puts. The peak area data from ANN and LF analyses for simulated spectra yielded high correlation coefficients demonstrating that the peak areas quantified with ANNgave similar results as LF analysis. Thus, a fully automated ANN method based on magnitude spectra has demonstrated potential for quantification of in vivo metabolites from long echo time spectroscopic imaging.

    KW - artificial neural network

    KW - 1H nuclear magnetic resonance spectroscopy

    KW - NMR spectroscopy

    KW - brain metabolites

    KW - metabolites

    KW - quantification

    KW - simulated spectra

    U2 - 10.1006/jmre.2001.2457

    DO - 10.1006/jmre.2001.2457

    M3 - Article

    VL - 154

    SP - 1

    EP - 5

    JO - Journal of Magnetic Resonance

    JF - Journal of Magnetic Resonance

    SN - 1090-7807

    IS - 1

    ER -