Automatic identification of coronary stent in coronary calcium scoring CT using deep learning

Abstract

Coronary artery calcium (CAC) scoring CT is a useful tool for screening coronary artery disease and for cardiovascular risk stratification. However, its efficacy in patients with coronary stents, who had pre-existing coronary artery disease, remains uncertain. Historically, CAC CT scans of these patients have been manually excluded from the CAC scoring process, even though most of the CAC scoring process is now fully automated. Therefore, we hypothesized that automating the filtering of patients with coronary stents using artificial intelligence could streamline the entire CAC workflow, eliminating the need for manual intervention. Consequently, we aimed to develop and evaluate a deep learning-based coronary stent filtering algorithm (StentFilter) in CAC scoring CT scans using a multicenter CAC dataset. We developed StentFilter 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. StentFilter's performance was evaluated on two independent internal test sets (Asan cohort- and 2; 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 StentFilter. StentFilter 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 (Asan cohort-1; 0.008 [3/355]) compared with the dataset without stents (Asan cohort-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 StentFilter accurately distinguished coronary stents from pre-existing coronary calcifications. This approach holds potential as a filter within a fully automated CAC scoring workflow, streamlining the process efficiently.

Keywords: Accuracy; Artificial intelligence; Computed tomography; Coronary artery calcium score; Coronary stent.

Fig. 1

The schematic process of the algorithm for automatic identification of coronary stents (StentFilter). Step (1) The convolutional neural network for identification of the stent after image pre-processing. Step (2) False-positive reduction algorithm based on the predictive volume (mm³) for each pixel of the mask. If the number of pixels (m) is greater than the predicted number of pixels for the suspected stent mask (n), it was considered a true positive.

Fig. 2

Identifying and distinguishing coronary stents from coronary calcifications. (A) In a coronary artery calcium (CAC) scoring image, both the coronary calcification (black arrow) and coronary stent (white arrow) are aligned in a single file within the left anterior descending artery. (B) A radiologist has annotated the coronary calcification with a red mask and the coronary stent with a green mask for clear identification. (C) StentFilter accurately identifies the coronary stent (white arrow), differentiating it from the coronary calcification (black arrow).

Fig. 3

False-positive identification by StentFilter: misclassification of coronary calcification as a stent. (A) A coronary artery calcium (CAC) scoring image showcases segment-long calcifications within the proximal segments of the left anterior descending (LAD) and left circumflex arteries (black arrows) (B) A radiologist annotated these calcifications with a red mask. (C) However, the StentFilter mistakenly recognized the calcification in the LAD as a coronary stent, leading to a false-positive result.