Purpose: Much evidence suggests long-term cigarette smoking alters coronary vascular endothelial response. In this study, we applied nonnegative matrix factorization (NMF), an unsupervised learning algorithm, to CO-less H2 15O-PET to investigate coronary endothelial dysfunction caused by smoking noninvasively. Materials and methods: This study enrolled eighteen young male volunteers consisting of 9 smokers (23.8±1.1 yr; 6.6±2.5 pack-years) and 9 nonsmokers (23.8±2.9 yr). They do not have any cardiovascular risk factor or disease history. Myocardial H2 15O-PET was performed at rest, during cold (5℃) pressor stimulation and during adenosine infusion. Left ventricular blood pool and myocardium were segmented on dynamic PET data by NMF method. Myocardial blood flow (MBF) was calculated from input and tissue functions by a single compartmental model with correction of partial volume and spillover effects. Results: There were no significant difference in resting MBF between the two groups (Smokers: 1.43 0.41 ml/g/min and non-smokers: 1.37±0.41 ml/g/min; p = NS). during cold pressor stimulation, MBF in smokers was significantly lower than that in non-smokers (1.25±0.34 ml/g/min vs 1.59±0.29 ml/g/min ; p=0.019). The difference in the ratio of cold pressor MBF to resting MBF between the two groups was also significant (p=0.024; 90±24% in smokers and 122±28% in non-smokers.). During adenosine infusion, however, hyperemic MBF did not differ significantly between smokers and non-smokers (5.81±1.99 ml/g/min vs 5.11 ±1.31 ml/g/min ; p=NS). Conclusion: In smokers, MBF during cold pressor stimulation was significantly lower compared with nonsmokers, reflecting smoking-induced endothelial dysfunction. However, there was no significant difference in MBF during adenosine-induced hyperemia between the two groups.