Chapter

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2011

Volume 6893 of the series Lecture Notes in Computer Science pp 479-486

Automatic View Planning for Cardiac MRI Acquisition

  • Xiaoguang LuAffiliated withImage Analytics and Informatics, Siemens Corporate Research
  • , Marie-Pierre JollyAffiliated withImage Analytics and Informatics, Siemens Corporate Research
  • , Bogdan GeorgescuAffiliated withImage Analytics and Informatics, Siemens Corporate Research
  • , Carmel HayesAffiliated withHealthcare Sector, H IM MR PLM-AW CARD, Siemens AG
  • , Peter SpeierAffiliated withHealthcare Sector, H IM MR PLM-AW CARD, Siemens AG
  • , Michaela SchmidtAffiliated withHealthcare Sector, H IM MR PLM-AW CARD, Siemens AG
  • , Xiaoming BiAffiliated withSiemens Medical Solutions USA
  • , Randall KroekerAffiliated withSiemens Medical Solutions Canada
  • , Dorin ComaniciuAffiliated withImage Analytics and Informatics, Siemens Corporate Research
    • , Peter KellmanAffiliated withNational Institutes of Health
    • , Edgar MuellerAffiliated withHealthcare Sector, H IM MR PLM-AW CARD, Siemens AG
    • , Jens GuehringAffiliated withHealthcare Sector, H IM MR PLM-AW CARD, Siemens AG

Abstract

Conventional cardiac MRI acquisition involves a multi-step approach, requiring a few double-oblique localizers in order to locate the heart and prescribe long- and short-axis views of the heart. This approach is operator-dependent and time-consuming. We propose a new approach to automating and accelerating the acquisition process to improve the clinical workflow. We capture a highly accelerated static 3D full-chest volume through parallel imaging within one breath-hold. The left ventricle is localized and segmented, including left ventricle outflow tract. A number of cardiac landmarks are then detected to anchor the cardiac chambers and calculate standard 2-, 3-, and 4-chamber long-axis views along with a short-axis stack. Learning-based algorithms are applied to anatomy segmentation and anchor detection. The proposed algorithm is evaluated on 173 localizer acquisitions. The entire view planning is fully automatic and takes less than 10 seconds in our experiments.