AIM: Evaluation of the diagnostic accuracy of stress perfusion cardiovascular magnetic resonance for the diagnosis of significant obstructive coronary artery disease (CAD) through meta-analysis of the available data. METHODOLOGY: Original articles in any language published before July 2009 were selected from available databases (MEDLINE, Cochrane Library and BioMedCentral) using the combined search terms of magnetic resonance, perfusion, and coronary angiography; with the exploded term coronary artery disease. Statistical analysis was only performed on studies that: (1) used a [greater than or equal to] 1.5 Tesla MR scanner; (2) employed invasive coronary angiography as the reference standard for diagnosing significant obstructive CAD, defined as a [greater than or equal to] 50% diameter stenosis; and (3) provided sufficient data to permit analysis. RESULTS: From the 263 citations identified, 55 relevant original articles were selected. Only 35 fulfilled all of the inclusion criteria, and of these 26 presented data on patient-based analysis. The overall patient-based analysis demonstrated a sensitivity of 89% (95% CI: 88-91%), and a specificity of 80% (95% CI: 78-83%). Adenosine stress perfusion CMR had better sensitivity than with dipyridamole (90% (88-92%) versus 86% (80-90%), P = 0.022), and a tendency to a better specificity (81% (78-84%) versus 77% (71-82%), P = 0.065). CONCLUSION: Stress perfusion CMR is highly sensitive for detection of CAD but its specificity remains moderate.