A Two-Stage Multimodal Contrastive Framework for PET-Based Prediction of Obstructive Coronary Artery Disease

Background

Positron emission tomography (PET) myocardial perfusion imaging (MPI) provides complementary information on perfusion, myocardial blood flow and ventricular function. While these markers are often considered collectively during interpretation, their quantitative integration with imaging and clinical data into a unified predictive framework remains limited. We developed a multimodal artificial intelligence framework that combines PET polar maps with quantitative imaging and clinical features to improve obstructive coronary artery disease (CAD) detection.

Methods

We retrospectively analyzed the multicenter REFINE PET registry. Among 38,682 PET MPI studies from 14 sites, 2,833 patients without known prior CAD underwent invasive coronary angiography within 180 days. Obstructive CAD was defined as ≥50% left main stenosis or ≥70% stenosis in other major epicardial coronary arteries. We developed a two-stage contrastive learning framework to learn multimodal PET representations from studies without angiographic labels and transfer them to supervised CAD prediction. In Stage 1, PET image and tabular encoders were pretrained on 12,225 PET MPI studies from eight development sites using 15-channel PET polar maps, quantitative PET perfusion, flow and gated functional measures, and clinical variables. In Stage 2, the pretrained encoders and a lightweight classification head were fine-tuned in 968 angiography-labeled patients, using lower encoder learning rates to limit overfitting. The model was externally validated for angiographically defined obstructive CAD detection in 1,865 patients from six independent sites and compared with standard PET MPI metrics.

Results

The prevalence of obstructive CAD was 60% in the training cohort (66% male, median age of 70 years [63, 77]), and 55% in the external validation cohort (64% male, median age of 67 years [60–74]). In external validation, the AI model achieved an AUC of 0.85 (95% confidence interval (CI), 0.83–0.87) for obstructive CAD detection and outperformed conventional quantitative PET metrics (all P < 0.001). At a specificity matched to visual summed stress score, the AI model achieved higher sensitivity (89% [95% CI, 87–91] versus 85% [95% CI, 82–87]) and negative predictive value (81% [95% CI, 77–84] versus 73% [95% CI, 69–77]; both p<0.001). The overall net reclassification improvement was 8.9% (95% CI, 4.2–13.6%; p = 0.001).

Conclusions

Multimodal contrastive pretraining improved obstructive CAD detection from PET imaging beyond conventional perfusion-based scoring in independent multisite external validation.

Key question

Can multimodal contrastive pretraining leverage PET MPI studies without angiographic labels to improve detection of angiography-defined obstructive CAD by integrating PET polar maps, quantitative PET/CT measures, and clinical variables?

Key results

The AI model achieved the highest external AUC for obstructive CAD detection, outperforming SSS and other PET-derived metrics. At an SSS-matched threshold, it improved sensitivity, negative predictive value, reclassification, and net benefit.

Take-home message

Multimodal contrastive pretraining leverages PET studies without angiographic labels and improves obstructive CAD detection by integrating polar maps with quantitative PET/CT and clinical data.

A contrastively pretrained multimodal AI model integrated PET polar maps, quantitative PET metrics, CT-derived CAC, and clinical variables to predict obstructive CAD, improve performance over SSS, and provide patient-level attribution maps. SSS indicates summed stress score.