The accuracy of dipyridamole stress/rest 99mTc-MIBI myocardial imaging for detection of ischemia depends on reproducible image interpretation. To evaluate the reproducibility of visual assessment, agreement in interpretation among two independent obervers, blinded to clinieal data, was evaluated in SPECT images of 131 patients (94 males, 38 fe- males, mean age 58+7 yr) with suspected coronary artery disease who underwent both dipyridamole st,ress/rest 99mTc-MJBI myocardial SPECT and coronary angiography, The left ventricle was divided into twenty-nine segments in stress and rest SPECT images and each segment was visually graded according to a five point scale (segmental score : O=normal, 1 =equivocal, 2=mild decrease, 3=severe decrease and 4=absent uptake). Overall concordance of segmental scoring between the two observers was 80%. The Pear- sons correlat.ion coefficient (r) of the segmental scores for stress and rest images were 0.67 and 0.65, respectively, while the difference in score between the two images showed a correlat,ion of 0.45 (all p<0,001). Agreement between two observers in final SPECT diagnosis as absence or presence of disease was 93%. The degree of agr eement in segmental scoring showed no difference between patients with or without agreement as to the presence of disease. Therefore it appeared that cases with inconcordant diagnosis between the 2 observers were mainly due to a difference in individual threshold for interpretating the significance of a particular decreased uptake area rather (han to a difference in perceiving the degree of the hypoactivity, Thus, establishment of individual optimum thresholds in visual interpretation of myocardial SPECT may be helpful to improve reproducibility and acruracy of scan ditagnosis.