Piotr J Slomka1,2, Mariana Diaz-Zamudio3, Damini Dey4,5, Manish Motwani3, Yafim Brodov3, David Choi3, Sean Hayes3, Louise Thomson3, John Friedman3, Guido Germano3,4, Daniel Berman3. 1. Artificial Intelligence in Medicine Program, Departments of Imaging and Medicine, and Cedars-Sinai Heart Institute, Cedars-Sinai Medical Center, 8700 Beverly Blvd, Ste A047 N, Los Angeles, CA, 90048, USA. slomkap@cshs.org. 2. David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA. slomkap@cshs.org. 3. Artificial Intelligence in Medicine Program, Departments of Imaging and Medicine, and Cedars-Sinai Heart Institute, Cedars-Sinai Medical Center, 8700 Beverly Blvd, Ste A047 N, Los Angeles, CA, 90048, USA. 4. David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA, USA. 5. Biomedical Imaging Research Institute, Department of Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
Abstract
BACKGROUND: We aimed to evaluate the utility of fully automated software registration intended to improve CT attenuation correction (CTAC) map misalignments during cardiac (82)Rb PET/CT myocardial perfusion imaging (MPI). METHODS: 171 consecutive patients (108 males, mean age 69 years), undergoing both rest-stress (82)Rb PET/CT MPI and invasive coronary angiography within 6 months (mean 14 days, range 0-170), were studied. List mode data were automatically processed in batch mode to generate transaxial attenuation corrected slices with four different CTAC alignment correction strategies: (i) no alignment correction (NONE); (ii) manual correction (MANUAL); (iii) automated 6-parameter rigid correction (AUTO); and (iv) targeted use of automated correction only where PET-CTAC alignment was initially judged as incorrect on either stress or rest scan (AUTO for misalignment only). Initial and final registration quality was graded (1-3) by an experienced radiologist (1: satisfactory alignment (<2 mm misalignment), 2: slight misalignment (2-5 mm in any direction), or 3: poor (>5 mm misalignment in any direction). Total perfusion deficit (TPD) and ischemic TPD (ITPD) were computed automatically, and their diagnostic accuracy to detect significant coronary artery disease with each realignment technique was assessed using receiver operating characteristic analysis. RESULTS: The diagnostic accuracy of ITPD, expressed as area under curve, was .81 ± .03 with no alignment correction (NONE), .83 ± .03 with MANUAL correction, .85 ± .03 with AUTO correction (P < .05 vs. NONE and MANUAL), and .87 ± .03 with the targeted use of AUTO correction (P < .05 vs. NONE, MANUAL and AUTO). Both manual and software corrections increased the percentage of cases with satisfactory PET-CTAC map alignment (P < .05 for all) at rest (from 55% for NONE to 80% for MANUAL and 92% for AUTO) and at stress (from 51% for NONE to 78% for MANUAL and 84% for AUTO). CONCLUSION: The diagnostic accuracy of (82)Rb PET/CT MPI with automated rigid alignment is improved compared to data with no CTAC scan alignment or with manual alignment. The optimal strategy for diagnostic performance is to apply automatic alignment only in cases which are visually identified as misaligned.
BACKGROUND: We aimed to evaluate the utility of fully automated software registration intended to improve CT attenuation correction (CTAC) map misalignments during cardiac (82)Rb PET/CT myocardial perfusion imaging (MPI). METHODS: 171 consecutive patients (108 males, mean age 69 years), undergoing both rest-stress (82)Rb PET/CT MPI and invasive coronary angiography within 6 months (mean 14 days, range 0-170), were studied. List mode data were automatically processed in batch mode to generate transaxial attenuation corrected slices with four different CTAC alignment correction strategies: (i) no alignment correction (NONE); (ii) manual correction (MANUAL); (iii) automated 6-parameter rigid correction (AUTO); and (iv) targeted use of automated correction only where PET-CTAC alignment was initially judged as incorrect on either stress or rest scan (AUTO for misalignment only). Initial and final registration quality was graded (1-3) by an experienced radiologist (1: satisfactory alignment (<2 mm misalignment), 2: slight misalignment (2-5 mm in any direction), or 3: poor (>5 mm misalignment in any direction). Total perfusion deficit (TPD) and ischemic TPD (ITPD) were computed automatically, and their diagnostic accuracy to detect significant coronary artery disease with each realignment technique was assessed using receiver operating characteristic analysis. RESULTS: The diagnostic accuracy of ITPD, expressed as area under curve, was .81 ± .03 with no alignment correction (NONE), .83 ± .03 with MANUAL correction, .85 ± .03 with AUTO correction (P < .05 vs. NONE and MANUAL), and .87 ± .03 with the targeted use of AUTO correction (P < .05 vs. NONE, MANUAL and AUTO). Both manual and software corrections increased the percentage of cases with satisfactory PET-CTAC map alignment (P < .05 for all) at rest (from 55% for NONE to 80% for MANUAL and 92% for AUTO) and at stress (from 51% for NONE to 78% for MANUAL and 84% for AUTO). CONCLUSION: The diagnostic accuracy of (82)Rb PET/CT MPI with automated rigid alignment is improved compared to data with no CTAC scan alignment or with manual alignment. The optimal strategy for diagnostic performance is to apply automatic alignment only in cases which are visually identified as misaligned.
Authors: Piotr J Slomka; Hidetaka Nishina; Daniel S Berman; Cigdem Akincioglu; Aiden Abidov; John D Friedman; Sean W Hayes; Guido Germano Journal: J Nucl Cardiol Date: 2005 Jan-Feb Impact factor: 5.952
Authors: K Lance Gould; Nils P Johnson; Timothy M Bateman; Rob S Beanlands; Frank M Bengel; Robert Bober; Paolo G Camici; Manuel D Cerqueira; Benjamin J W Chow; Marcelo F Di Carli; Sharmila Dorbala; Henry Gewirtz; Robert J Gropler; Philipp A Kaufmann; Paul Knaapen; Juhani Knuuti; Michael E Merhige; K Peter Rentrop; Terrence D Ruddy; Heinrich R Schelbert; Thomas H Schindler; Markus Schwaiger; Stefano Sdringola; John Vitarello; Kim A Williams; Donald Gordon; Vasken Dilsizian; Jagat Narula Journal: J Am Coll Cardiol Date: 2013-08-28 Impact factor: 24.094
Authors: Todd D Miller; David O Hodge; Timothy F Christian; James J Milavetz; Kent R Bailey; Raymond J Gibbons Journal: Am J Med Date: 2002-03 Impact factor: 4.965
Authors: Adam M Alessio; Steve Kohlmyer; Kelley Branch; Grace Chen; James Caldwell; Paul Kinahan Journal: J Nucl Med Date: 2007-05 Impact factor: 10.057
Authors: Fabio P Esteves; Jonathan A Nye; Akbar Khan; Russell D Folks; Raghuveer K Halkar; Ernest V Garcia; David M Schuster; Stamatios Lerakis; Paolo Raggi; John R Votaw Journal: J Nucl Cardiol Date: 2009-11-24 Impact factor: 5.952
Authors: Mouaz H Al-Mallah; Timothy M Bateman; Kelley R Branch; Andrew Crean; Eric L Gingold; Randall C Thompson; Sarah E McKenney; Edward J Miller; Venkatesh L Murthy; Koen Nieman; Todd C Villines; Michael V Yester; Andrew J Einstein; John J Mahmarian Journal: J Nucl Cardiol Date: 2022-09-02 Impact factor: 3.872
Authors: Evangelos Tzolos; Martin Lyngby Lassen; Tinsu Pan; Jacek Kwiecinski; Sebastien Cadet; Damini Dey; Marc R Dweck; David E Newby; Daniel Berman; Piotr Slomka Journal: J Nucl Cardiol Date: 2020-07-02 Impact factor: 5.952
Authors: Timothy M Bateman; Gary V Heller; Rob Beanlands; Dennis A Calnon; James Case; Rob deKemp; E Gordon DePuey; Marcelo Di Carli; Emel C Guler; Venkatesh L Murthy; Jeffrey Rosenblatt; Ronald Sher; Piotr Slomka; Terrence D Ruddy Journal: J Nucl Med Date: 2021-03-31 Impact factor: 11.082