• DocumentCode
    1826015
  • Title

    Multi-modality 3D breast imaging with X-Ray tomosynthesis and automated ultrasound

  • Author

    Sinha, S.P. ; Roubidoux, M.A. ; Helvie, M.A. ; Nees, A.V. ; Goodsitt, M.M. ; LeCarpentier, G.L. ; Fowlkes, J. Brian ; Chalek, C.L. ; Carson, P.L.

  • Author_Institution
    Michigan Univ., Ann Arbor
  • fYear
    2007
  • fDate
    22-26 Aug. 2007
  • Firstpage
    1335
  • Lastpage
    1338
  • Abstract
    This study evaluated the utility of 3D automated ultrasound in conjunction with 3D digital X-ray tomosynthesis for breast cancer detection and assessment, to better localize and characterize lesions in the breast. Tomosynthesis image volumes and automated ultrasound image volumes were acquired in the same geometry and in the same view for 27 patients. 3 MQSA certified radiologists independently reviewed the image volumes, visually correlating the images from the two modalities with in-house software. More sophisticated software was used on a smaller set of 10 cases, which enabled the radiologist to draw a 3D box around the suspicious lesion in one image set and isolate an anatomically correlated, similarly boxed region in the other modality image set. In the primary study, correlation was found to be moderately useful to the readers. In the additional study, using improved software, the median usefulness rating increased and confidence in localizing and identifying the suspicious mass increased in more than half the cases. As automated scanning and reading software techniques advance, superior results are expected.
  • Keywords
    biomedical ultrasonics; cancer; diagnostic radiography; mammography; 3D breast imaging; X-ray tomosynthesis; automated ultrasound image volumes; breast cancer detection; Breast cancer; Cancer detection; Geometry; Image coding; Optical imaging; Ultrasonic imaging; Ultrasonic transducers; X-ray detection; X-ray detectors; X-ray imaging; automated ultrasound; breast cancer digital tomosynthesis; multi-modality breast imaging; Algorithms; Artificial Intelligence; Breast Neoplasms; Female; Humans; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Mammography; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Tomography, X-Ray Computed; Ultrasonography, Mammary;
  • 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.2007.4352544
  • Filename
    4352544