Automatic classification of HITS into artifacts or solid or gaseous emboliby a wavelet representation combined with dual-gate TCD

Background and Purpose-Transcranial Doppler (TCD) can detect high-intensity transient signals (HITS) in the cerebral circulation. HITS may correspond to artifacts or solid or gaseous emboli. The aim of this study was to devel op an offline automated Doppler system allowing the classification of HITS. Methods-We studied 600 HITS in vivo, including 200 artifacts from normal su bjects, 200 solid emboli from patients with symptomatic internal carotid ar tery stenosis, and 200 gaseous emboli in stroke patients with patent forame n ovale. The study was 2-fold, each part involving 300 HITS (100 of each ty pe). The first 300 HITS (learning set) were used to construct an automated classification algorithm. The remaining 300 HITS (validation set) were used to check the validity of this algorithm. To classify HITS, we combined dua l-gate TCD with a wavelet representation and compared it with the current " gold standard," the human experts. Results-A combination of the peak frequency of HITS and the time delay make s it possible to separate artifacts from emboli. On the validation set, we achieved a sensitivity of 97%, a specificity of 98%, a positive predictive value (PPV) of 99%, and a negative predictive value (NPV) of 94%. To distin guish between solid and gaseous emboli, where positive refers now to the so lid emboli, we used the peak frequency, the relative power, and the envelop e symmetry of HITS. On the validation set, we achieved a sensitivity of 89% , a specificity of 86%, a conditional PPV of 89%, and a conditional NPV of 89%. Conclusions-An automated wavelet representation combined with dual-gate TCD can reliably reject artifacts from emboli. From a clinical standpoint, how ever, this approach has only a fair accuracy in differentiating between sol id and gaseous emboli.