In the present study, researchers compared the diagnostic performance of automated analysis with that of expert visual reading for the detection of obstructive coronary artery disease (CAD)

Traditionally, interpretation of myocardial perfusion imaging (MPI) is based on visual assessment. The computer-based automated analysis might be a simple alternative obviating the need for extensive reading experience

206 Patients (64% men, age 58.2 ± 8.7 years) with suspected CAD were included prospectively. All patients underwent 99mTc-tetrofosmin single-photon emission computed tomography (SPECT) and invasive coronary angiography with fractional flow reserve (FFR) measurements.

Non-corrected (NC) and attenuation-corrected (AC) SPECT images were analyzed both visually as well as automatically by commercially available SPECT software. The automated analysis comprised a segmental summed stress score (SSS), summed difference score (SDS), stress total perfusion deficit (S-TPD), and ischemic total perfusion deficit (I-TPD), representing the extent and severity of hypoperfused myocardium.

Diagnostic performances

Subsequently, the software was optimized with an institutional normal database and thresholds. Diagnostic performances of automated and visual analysis were compared taking FFR as a reference.

Sensitivity did not differ significantly between visual reading and most automated scoring parameters, except for SDS, which was significantly higher than visual assessment (p < 0.001). Specificity, however, was significantly higher for visual reading than for any of the automated scores (p < 0.001 for all).

Diagnostic accuracy was significantly higher for visual scoring (77.2%) than for all NC images scores (p < 0.05), but not compared with SSS AC and S-TPD AC (69.8% and 71.2%, p = 0.063 and p = 0.134). After optimization of the automated software, diagnostic accuracies were similar for visual (73.8%) and automated analysis. Among the automated parameters, S-TPD AC showed the highest accuracy (73.5%).

Visual analysis of SPECT imaging slightly outperforms automated analysis with standard software in the detection of FFR-defined significant CAD. After optimization with an institutional normal database and thresholds, however, diagnostic accuracy of automated analysis equalled expert visual analysis without the need for comprehensive reading experience.

Therefore, automatic assessment has the potential to simplify the diagnostic process using SPECT, particularly in conjunction with CT-based AC. Automated analysis of myocardial perfusion SPECT can be as accurate as visual interpretation by an expert reader in detecting significant CAD defined by FFR.