Mutual information-based multimodality registration of cardiac ultrasound and SPECT images: a preliminary investigation Vivek Walimbe 1,2 , Vladimir Zagrodsky 1 , Shanker Raja 3 , Wael A. Jaber 3,4 , Frank P. DiFilippo 3 , Mario J. Garcia 4 , Richard C. Brunken 3,4 , James D. Thomas 4 & Raj Shekhar 1 1 Department of Biomedical Engineering, Lerner Research Institute, The Cleveland Clinic Foundation, Cleveland; 2 Biomedical Engineering Center, The Ohio State University, Columbus; 3 Department of Molecular and Functional Imaging; 4 Department of Cardiovascular Medicine, The Cleveland Clinic Foundation, Cleveland, OH, USA Received 6 January 2003; accepted in revised form 14 July 2003 Key words: coronary disease, diagnostic imaging, emission-computed, single-photon, stress ultrasono- graphy, three-dimensional, tomography, ultrasonography Abstract Background: Ultrasound (US) and single photon emission computed tomography (SPECT) are the two most commonly prescribed procedures for diagnosing coronary artery disease (CAD). We have demon- strated the feasibility of multimodality registration of two-dimensional (2D) and three-dimensional (3D) cardiac US images with cardiac SPECT images with an aim to simultaneously present the complementary anatomical and perfusion information from the two modalities. We have also tested the clinicians’ as- sessment of the clinical adequacy of the registered images. Methods and Results: We have demonstrated temporal and spatial registration for nine sets of cardiac US and SPECT cine loops covering the entire cardiac cycle. Temporal alignment was performed by interpolation of existing SPECT images at cardiac phases corresponding to available US images. Spatial registration was performed in 3D image space using a mutual information-based approach. Experts from echocardiography and nuclear medicine determined the clinical utility of the registration by rating each registration on a scale of 1 to 5, a rating of 3 or above indicating clinical utility. 2DUS-SPECT registration (five cases) received an average rating of 4.2, whereas 3DUS-SPECT registration (four cases) received an average rating of 2.85. By one-sample t test, the overall evaluations (mean 3.58) were greater than the pre-specified clinical cut-off of 3 with p < 0.05, indicating likelihood of clinical utility. Conclusion: Our method demonstrates the feasibility of registering cardiac US and SPECT images in their present as well as possible future forms. Such registration has the potential to provide a more accurate and powerful tool for diagnosing CAD. Abbreviations: ADE – Average distance error; AVI – Audio Video Interleave; CI – Confidence interval; CAD – Coronary artery disease; 4D – Four-dimensional; LV – Left ventricular; MI – Mutual information; MR – Magnetic resonance; SPECT – Single photon emission computed tomography; 3D – Three-dimensional; 3DUS – Three-dimensional ultrasound; T – Transformations; 2D – Two-dimensional; 2DUS – Two-dimensional ultra- sound; US – Ultrasound; US1 – Seeded ultrasound image The International Journal of Cardiovascular Imaging 19: 483–494, 2003. Ó 2003 Kluwer Academic Publishers. Printed in the Netherlands. 483