PT - JOURNAL ARTICLE AU - Yuka Otaki AU - Balaji Tamarappoo AU - Ananya Singh AU - Tali Sharir AU - Lien-Hsin Hu AU - Heidi Gransar AU - Andrew Einstein AU - Mathews Fish AU - Terrence Ruddy AU - Philipp Kaufmann AU - Albert Sinusas AU - Edward Miller AU - Timothy Bateman AU - Sharmila Dorbala AU - Marcelo Di Carli AU - Joanna Liang AU - Damini Dey AU - Daniel Berman AU - Piotr Slomka TI - <strong>Diagnostic Accuracy of Deep Learning for Myocardial Perfusion Imaging in Men and Women with a High-Efficiency Parallel-Hole-Collimated Cadmium-Zinc-Telluride Camera: multicenter study</strong> DP - 2020 May 01 TA - Journal of Nuclear Medicine PG - 92--92 VI - 61 IP - supplement 1 4099 - http://jnm.snmjournals.org/content/61/supplement_1/92.short 4100 - http://jnm.snmjournals.org/content/61/supplement_1/92.full SO - J Nucl Med2020 May 01; 61 AB - 92Purpose: We developed a deep learning (DL) model for combined analysis of raw upright and supine stress myocardial perfusion imaging (MPI) polar maps from a parallel-hole-collimated camera with cadmium-zinc-telluride detectors and we sought to evaluate DL performance compared to total perfusion deficit (TPD) and visual assessments in men vs. women. Methods: MPI and invasive angiography were performed within a 6-month interval in 1,160 patients (64% men) in 4 separate centers without known coronary artery disease (CAD) obtained from REFINE SPECT registry. Images were acquired in supine and upright positions after stress. Standard 17-segment summed stress score (SSS) was performed visually. Diameter stenosis ≥50% of the left main artery, or ≥70% in the left anterior descending, left circumflex, or right coronary artery, was considered obstructive CAD. DL was developed using raw polar maps, with specification of sex, and body mass index (BMI) as auxiliary variables. Training and testing data-sets included both men and women for prediction of obstructive CAD using repeated leave-one-center-out external validation (4 models built from 3 centers and tested in 4th center). Gradient-weighted Class Activation Mapping (Grad-CAM) was employed to visualize regions contributing to disease prediction on polar maps. Stress TPD was obtained for upright (U-TPD) and supine (S-TPD) acquisitions. Receiver operating characteristic analysis and pairwise comparisons of the area under the curve (AUC) were performed to test diagnostic performance separately in men and women on the stacked data from 4 models. For TPD and DL, the diagnostic cutoff values were set to match the specificity of visual read with SSS≥4 threshold. Results: The AUC for detection of obstructive CAD by DL was higher than SSS, S-TPD and U-TPD in men (p for all &lt;0.001, left top in the Figure) whereas, in women, the AUC of DL, U-TPD and visual SSS were equivalent. In women, DL was superior for prediction of obstructive CAD only when compared to S-TPD (p=0.0007, right top in the Figure). The sensitivity by DL, SSS, U-TPD and S-TPD was 82%, 75%, 77%, and 73%in men, and was 71%, 71%, 70% and 65% in women respectively. The sensitivity by DL was higher than SSS, S-TPD and U-TPD in men (p for all &lt;0.001), while it was similar to SSS, U-TPD and S-TPD in women. GradCAM visualized abnormal regions by DL, as illustrated in the Figure. Conclusion: We observed sex differences in the diagnostic performance of DL for prediction of obstructive CAD from D-SPECT, with DL outperforming visual and TPD in men but not in women. Whether this reflects sex-specific factors including differences in cardiac size, requires further investigation.