• DocumentCode
    1851770
  • Title

    Prostate cancer computer-assisted diagnosis software using dynamic contrast-enhanced MRI

  • Author

    Puech, P. ; Betrouni, N. ; Viard, R. ; Villers, A. ; Leroy, X. ; Lemaitre, Laurent

  • Author_Institution
    Univ. Hosp. of Lille, Lille
  • fYear
    2007
  • fDate
    22-26 Aug. 2007
  • Firstpage
    5567
  • Lastpage
    5570
  • Abstract
    ProCAD is a computer assisted diagnosis (CAD) software dedicated to prostate DCE-MRI analysis. In addition to standard visualization features, 2D and multislice 2D contouring tools based on a seeded growing region algorithm were included in the software. Tumor volume assessment and semiquantitative analysis of suspicious lesions can be performed. A 5-levels cancer suspicion score (ranging from "probably benign" to "highly suspicious") is calculated on the basis of adjusted parameters extracted from the data of 121 suspicious benign or tumoral lesions. RESULTS: Using a simple scoring algorithm based the median w.i and w.o values of TZK, TZB, PZK and PZB and designed to provide the highest sensitivity we had respective Se/Sp of 100/49% for peripheral zone cancers, and 100/40% for transition zone cancers characterization. CONCLUSION: This software provides useful data for an unbiased an reproducible assessment of hypervascularized prostatic areas in routine practice.
  • Keywords
    biomedical MRI; cancer; medical image processing; tumours; DCE-MRI analysis; ProCAD; benign lesions; computer-assisted diagnosis software; dynamic contrast-enhanced MRI; multislice 2D contouring; prostate cancer; seeded growing region algorithm; tumor volume assessment; tumoral lesions; Computer aided diagnosis; Data visualization; Lesions; Magnetic resonance imaging; Neoplasms; Performance analysis; Prostate cancer; Software algorithms; Software standards; Software tools; Algorithms; Artificial Intelligence; Contrast Media; Humans; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Information Storage and Retrieval; Magnetic Resonance Imaging; Male; Pattern Recognition, Automated; Prostatic Neoplasms; Reproducibility of Results; Sensitivity and Specificity; Software; Software Design; User-Computer Interface;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE
  • Conference_Location
    Lyon
  • ISSN
    1557-170X
  • Print_ISBN
    978-1-4244-0787-3
  • Type

    conf

  • DOI
    10.1109/IEMBS.2007.4353608
  • Filename
    4353608