• DocumentCode
    239494
  • Title

    Generation of conspicuity-improved synthetic image from digital breast tomosynthesis

  • Author

    Seong Tae Kim ; Dae Hoe Kim ; Yong Man Ro

  • Author_Institution
    Dept.. of Electr. Eng., KAIST, Daejeon, South Korea
  • fYear
    2014
  • fDate
    20-23 Aug. 2014
  • Firstpage
    395
  • Lastpage
    399
  • Abstract
    Digital breast tomosynthesis (DBT) is a new 3-D imaging modality that alleviates the tissue overlap problem of mammography. Currently, DBT has been used in combination with full-field digital mammography (FFDM). Although some studies have shown the superiority of combination of DBT and FFDM in diagnosing the breast cancer, this combined procedure has the drawback that radiation doses are increased compared to the FFDM alone. In this paper, we propose a novel approach for generating 2-D synthetic image from 3-D DBT volume to eliminate the need for acquiring additional FFDM. The proposed approach utilizes the conspicuity of the voxels of 3-D DBT volume to improve the conspicuity of lesions in generating 2-D synthetic image. Comparative experiments have been conducted using clinical data set to investigate the quality of images generated by the proposed method. Experimental results demonstrated that the lesion conspicuity was the best in the synthetic image generated by proposed method.
  • Keywords
    cancer; diagnostic radiography; mammography; medical image processing; tomography; 2D synthetic image generation; 3D DBT volume voxels; 3D imaging modality; breast cancer diagnosis; digital breast tomosynthesis; full-field digital mammography; lesion conspicuity; radiation doses; Biomedical imaging; Breast; Digital signal processing; Image generation; Image quality; Lesions; Radiology; digital breast tomosynthesis; lesion conspicuity; mammography; synthetic image; thick slice;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Digital Signal Processing (DSP), 2014 19th International Conference on
  • Conference_Location
    Hong Kong
  • Type

    conf

  • DOI
    10.1109/ICDSP.2014.6900693
  • Filename
    6900693