Abstract
Automatic pre-screening of pre-existing stents, whose prognostic value remains uncertain, could potentially reduce workload and enhance efficiency. However, such a solution has not yet been developed and validated. We aimed to develop and evaluate a deep learning-based coronary stent filtering algorithm (Stent_filter) in CAC scoring CT scans using a multicenter CAC dataset. We developed Stent_filter comprising two main processes: stent identification and false-positive reduction. Development utilized 108 non-enhanced echocardiography-gated CAC scans (including 74 with manually labeled stents), and for false positive reduction, 2063 CAC scans with significant coronary calcium (average Agatston score: 523.8) but no stents were utilized. Stent_filter’s performance was evaluated on two independent internal test sets (n = 355 and 396; one without coronary stents) and two external test sets from different institutions (n = 105 and 62), each with manually labeled stents. We calculated the per-patient sensitivity, specificity, and false-positive rate of Stent_filter. Stent_filter demonstrated a high overall per-patient sensitivity of 98.8% (511/517 cases with stents) and a false-positive rate of 0.022 (20/918). Notably, the false-positive ratio was significantly lower in the dataset containing stents (Internal-1; 0.008 [3/355]) compared with the dataset without stents (Internal-2; 0.043 [17/396], p = 0.008). All false-positive identifications were attributed to dense coronary calcifications, with no false positives identified in extracoronary locations. The automated Stent_filter accurately distinguished coronary stents from preexisting coronary calcifications. This approach holds potential as a filter within a fully automated CAC scoring workflow, streamlining the process efficiently.