皿井 正義

PURPOSE:Artificial neural networks (ANN) might help to diagnose coronary artery disease. This study aimed to determine whether the diagnostic accuracy of an ANN-based diagnostic system and conventional quantitation are comparable.;METHODS:The ANN was trained to classify potentially abnormal areas as true or false based on the nuclear cardiology expert interpretation of 1001 gated stress/rest (99m)Tc-MIBI images at 12 hospitals. The diagnostic accuracy of the ANN was compared with 364 expert interpretations that served as the gold standard of abnormality for the validation study. Conventional summed stress/rest/difference scores (SSS/SRS/SDS) were calculated and compared with receiver operating characteristics (ROC) analysis.;RESULTS:The ANN generated a better area under the ROC curves (AUC) than SSS (0.92 vs. 0.82, p < 0.0001), indicating better identification of stress defects. The ANN also generated a better AUC than SDS (0.90 vs. 0.75, p < 0.0001) for stress-induced ischemia. The AUC for patients with old myocardial infarction based on rest defects was 0.97 (0.91 for SRS, p = 0.0061), and that for patients with and without a history of revascularization based on stress def

The optimal cardiac phases for coronary CT angiography (CTA) are end-systole and mid-diastole, in which cardiac movement is slow. In conventional methods, these cardiac phases are determined by visual selection. We have compared the images in the optimal cardiac phases that were selected by the conventional method and cardiac-phase search software (Phase Navi), and examined the clinical usefulness of Phase Navi in patients with atrial fibrillation. The subjects were 38 patients (regular rhythm: 20, atrial fibrillation: 18). The continuity scores of patients with regular rhythm (Phase Navi, conventional methods) were 2.4±0.3–2.5±0.3 in end-systole and 2.4±0.5–2.4±0.4 in mid-diastole. The scores of patients with atrial fibrillation (Phase Navi, conventional methods) were 2.3±0.4–2.3±0.4 in end-systole, and 2.2±0.5–2.1±0.6 in mid-diastole. Because the continuity scores of the optimal images from Phase Navi were similar to those from the conventional method, Phase Navi had clinical usefulness in patients with atrial fibrillation.