A segmentation concept for positron emission tomography imaging using multiresolution analysis

A Amira, S Chandrasekaran, DWG Montgomery, IS Uzun

    Research output: Contribution to journalArticle

    7 Citations (Scopus)

    Abstract

    Positron emission tomography (PET) imaging is an emerging medical imaging modality. Due to its high sensitivity and ability to model function, it is effective in identifying active regions that may be associated with various types of tumours. Increasing numbers of patient scans have led to an urgent need for efficient data archival and the development of new image analysis techniques to aid clinicians in the diagnosis of disease. Additionally, to handle the large volumes of data generated using complex processing algorithms, it is becoming evident that co-processing solutions are essential. In this paper, an automated system for the segmentation of oncological PET data is developed. Initially, the Bayesian information criterion (BIC) is utilised for optimal segmentation level selection. Expectation maximisation (EM) based mixture modelling is then performed, using a k-means clustering procedure which varies voxel order for initialisation. A multiscale Markov model is then used to refine this segmentation by modelling spatial correlations between neighbouring image voxels. A field programmable gate array (FPGA) based co-processing solution is also proposed to offload the most complex computations onto hardware, in order to achieve high performance. (C) 2008 Elsevier B.V. All rights reserved.
    LanguageEnglish
    Pages1954-1965
    JournalNeurocomputing
    Volume71
    Issue number10-12
    DOIs
    Publication statusPublished - Jun 2008

    Fingerprint

    Multiresolution analysis
    Positron emission tomography
    Imaging techniques
    Processing
    Medical imaging
    Image analysis
    Field programmable gate arrays (FPGA)
    Tumors
    Hardware

    Keywords

    • positron emission tomography (PET)
    • medical image segmentation
    • multiscale Markov modelling
    • Gaussian mixture modelling
    • wavelet
    • tumour quantification
    • co-processing
    • field programmable gate arrays
    • (FPGAs)

    Cite this

    Amira, A ; Chandrasekaran, S ; Montgomery, DWG ; Uzun, IS. / A segmentation concept for positron emission tomography imaging using multiresolution analysis. In: Neurocomputing. 2008 ; Vol. 71, No. 10-12. pp. 1954-1965.
    @article{3b86bf753dc543d7ac3b5906b773b591,
    title = "A segmentation concept for positron emission tomography imaging using multiresolution analysis",
    abstract = "Positron emission tomography (PET) imaging is an emerging medical imaging modality. Due to its high sensitivity and ability to model function, it is effective in identifying active regions that may be associated with various types of tumours. Increasing numbers of patient scans have led to an urgent need for efficient data archival and the development of new image analysis techniques to aid clinicians in the diagnosis of disease. Additionally, to handle the large volumes of data generated using complex processing algorithms, it is becoming evident that co-processing solutions are essential. In this paper, an automated system for the segmentation of oncological PET data is developed. Initially, the Bayesian information criterion (BIC) is utilised for optimal segmentation level selection. Expectation maximisation (EM) based mixture modelling is then performed, using a k-means clustering procedure which varies voxel order for initialisation. A multiscale Markov model is then used to refine this segmentation by modelling spatial correlations between neighbouring image voxels. A field programmable gate array (FPGA) based co-processing solution is also proposed to offload the most complex computations onto hardware, in order to achieve high performance. (C) 2008 Elsevier B.V. All rights reserved.",
    keywords = "positron emission tomography (PET), medical image segmentation, multiscale Markov modelling, Gaussian mixture modelling, wavelet, tumour quantification, co-processing, field programmable gate arrays, (FPGAs)",
    author = "A Amira and S Chandrasekaran and DWG Montgomery and IS Uzun",
    year = "2008",
    month = "6",
    doi = "10.1016/j.neucom.2007.10.026",
    language = "English",
    volume = "71",
    pages = "1954--1965",
    journal = "Neurocomputing",
    issn = "0925-2312",
    publisher = "Elsevier",
    number = "10-12",

    }

    Amira, A, Chandrasekaran, S, Montgomery, DWG & Uzun, IS 2008, 'A segmentation concept for positron emission tomography imaging using multiresolution analysis', Neurocomputing, vol. 71, no. 10-12, pp. 1954-1965. https://doi.org/10.1016/j.neucom.2007.10.026

    A segmentation concept for positron emission tomography imaging using multiresolution analysis. / Amira, A; Chandrasekaran, S; Montgomery, DWG; Uzun, IS.

    In: Neurocomputing, Vol. 71, No. 10-12, 06.2008, p. 1954-1965.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - A segmentation concept for positron emission tomography imaging using multiresolution analysis

    AU - Amira, A

    AU - Chandrasekaran, S

    AU - Montgomery, DWG

    AU - Uzun, IS

    PY - 2008/6

    Y1 - 2008/6

    N2 - Positron emission tomography (PET) imaging is an emerging medical imaging modality. Due to its high sensitivity and ability to model function, it is effective in identifying active regions that may be associated with various types of tumours. Increasing numbers of patient scans have led to an urgent need for efficient data archival and the development of new image analysis techniques to aid clinicians in the diagnosis of disease. Additionally, to handle the large volumes of data generated using complex processing algorithms, it is becoming evident that co-processing solutions are essential. In this paper, an automated system for the segmentation of oncological PET data is developed. Initially, the Bayesian information criterion (BIC) is utilised for optimal segmentation level selection. Expectation maximisation (EM) based mixture modelling is then performed, using a k-means clustering procedure which varies voxel order for initialisation. A multiscale Markov model is then used to refine this segmentation by modelling spatial correlations between neighbouring image voxels. A field programmable gate array (FPGA) based co-processing solution is also proposed to offload the most complex computations onto hardware, in order to achieve high performance. (C) 2008 Elsevier B.V. All rights reserved.

    AB - Positron emission tomography (PET) imaging is an emerging medical imaging modality. Due to its high sensitivity and ability to model function, it is effective in identifying active regions that may be associated with various types of tumours. Increasing numbers of patient scans have led to an urgent need for efficient data archival and the development of new image analysis techniques to aid clinicians in the diagnosis of disease. Additionally, to handle the large volumes of data generated using complex processing algorithms, it is becoming evident that co-processing solutions are essential. In this paper, an automated system for the segmentation of oncological PET data is developed. Initially, the Bayesian information criterion (BIC) is utilised for optimal segmentation level selection. Expectation maximisation (EM) based mixture modelling is then performed, using a k-means clustering procedure which varies voxel order for initialisation. A multiscale Markov model is then used to refine this segmentation by modelling spatial correlations between neighbouring image voxels. A field programmable gate array (FPGA) based co-processing solution is also proposed to offload the most complex computations onto hardware, in order to achieve high performance. (C) 2008 Elsevier B.V. All rights reserved.

    KW - positron emission tomography (PET)

    KW - medical image segmentation

    KW - multiscale Markov modelling

    KW - Gaussian mixture modelling

    KW - wavelet

    KW - tumour quantification

    KW - co-processing

    KW - field programmable gate arrays

    KW - (FPGAs)

    U2 - 10.1016/j.neucom.2007.10.026

    DO - 10.1016/j.neucom.2007.10.026

    M3 - Article

    VL - 71

    SP - 1954

    EP - 1965

    JO - Neurocomputing

    T2 - Neurocomputing

    JF - Neurocomputing

    SN - 0925-2312

    IS - 10-12

    ER -