Decoding the Myocardium: Tracer-Aware Deep Learning for Patient-Level Classification in Stress-Rest SPECT…

AI / informaticsDiagnostics (Basel, Switzerland)· Jun 2026

Decoding the Myocardium: Tracer-Aware Deep Learning for Patient-Level Classification in Stress-Rest SPECT Myocardial Perfusion Imaging.

Dimitrios Samaras, Dimitra Tsivaka, Maria Vakalopoulou … Ioannis Tsougos

Cardiovascular ImagingAI / informaticsQ2IF 4.4

Stress-only deep learning distinguished normal from abnormal technetium-99m myocardial perfusion, AUC 0.88.

Decoding the Myocardium: Tracer-Aware Deep Learning for Patient-Level Classification in Stress-Rest SPECT Myocardial Perfusion Imaging.

Dimitrios Samaras … Ioannis Tsougos

Diagnostics (Basel, Switzerland) · Jun 2026 · Q2 in General Medicine

Background

Single-photon emission computed tomography (single-photon emission computed tomography) myocardial perfusion imaging (myocardial perfusion imaging) is widely used for non-invasive assessment of coronary artery disease under stress and rest conditions.

Purpose

This study developed and evaluated a multi-task deep learning framework with tracer-specific prediction heads for patient-level single-photon emission computed tomography myocardial perfusion imaging classification.

Methods

A convolutional neural network with a shared feature encoder and tracer-specific heads was implemented using polar map representations from technetium-99m (Tc-99m) and thallium-201 (Tl-201) studies.

Results

AUROC, closer to 1 means better distinction between normal and abnormal scans

AUC 0.88 (95% CI 0.67 to 0.99)

CI excludes the null - significant

More results

In both tracer-specific tasks, stress-phase information showed favorable performance, but the endpoints differed and should be interpreted separately.

“

Conclusion · 1 of 2

Stress-phase polar maps provided strong discriminative information within this single-center cohort.

Conclusion · 2 of 2

These findings should be interpreted in a tracer- and task-specific manner supporting stress-phase imaging as an informative input for AI-based single-photon emission computed tomography myocardial perfusion imaging classification while underscoring the need for external validation before broader clinical generalization.

Decoding the Myocardium: Tracer-Aware Deep Learning for Patient-Level Classification in Stress-Rest SPECT Myocardial Perfusion Imaging.

Decoding the Myocardium: Tracer-Aware Deep Learning for Patient-Level Classification in Stress-Rest SPECT Myocardial Perfusion Imaging.

Related papers