Toward automated classification of pathological transcranial Doppler waveform morphology via spectral clustering.

Cerebral Blood Flow Velocity waveforms acquired via Transcranial Doppler (TCD) can provide evidence for cerebrovascular occlusion and stenosis. Thrombolysis in Brain Ischemia (TIBI) flow grades are widely used for this purpose, but require subjective assessment by expert evaluators to be reliable. In this work we seek to determine whether TCD morphology can be objectively assessed using an unsupervised machine learning approach to waveform categorization. TCD beat waveforms were recorded at multiple depths from the Middle Cerebral Arteries of 106 subjects; 33 with Large Vessel Occlusion (LVO). From each waveform, three morphological features were extracted, quantifying onset of maximal velocity, systolic canopy length, and the number/prominence of peaks/troughs. Spectral clustering identified groups implicit in the resultant three-dimensional feature space, with gap statistic criteria establishing the optimal cluster number. We found that gap statistic disparity was maximized at four clusters, referred to as flow types I, II, III, and IV. Types I and II were primarily composed of control subject waveforms, whereas types III and IV derived mainly from LVO patients. Cluster morphologies for types I and IV aligned clearly with Normal and Blunted TIBI flows, respectively. Types II and III represented commonly observed flow-types not delineated by TIBI, which nonetheless deviate from normal and blunted flows. We conclude that important morphological variability exists beyond that currently quantified by TIBI in populations experiencing or at-risk for acute ischemic stroke, and posit that the observed flow-types provide the foundation for objective methods of real-time automated flow type classification.

Towards optimal visual presentation design for hybrid EEG-fTCD brain-computer interfaces.

OBJECTIVE: In this paper, we introduce a novel hybrid brain-computer interface (BCI) system that measures electrical brain activity as well as cerebral blood velocity using electroencephalography (EEG) and functional transcranial Doppler ultrasound (fTCD) respectively in response to flickering mental rotation (MR) and flickering word generation (WG) cognitive tasks as well as a fixation cross that represents the baseline. This work extends our previous approach, in which we showed that motor imagery induces simultaneous changes in EEG and fTCD to enable task discrimination; and hence, provides a design approach for a hybrid BCI. Here, we show that instead of using motor imagery, the proposed visual stimulation technique enables the design of an EEG-fTCD based BCI with higher accuracy. APPROACH: Features based on the power spectrum of EEG and fTCD signals were calculated. Mutual information and support vector machines were used for feature selection and classification purposes. MAIN RESULTS: EEG-fTCD combination outperformed EEG by 4.05% accuracy for MR versus baseline problem and by 5.81% accuracy for WG versus baseline problem. An average accuracy of 92.38% was achieved for MR versus WG problem using the hybrid combination. Average transmission rates of 4.39, 3.92, and 5.60 bits min-1 were obtained for MR versus baseline, WG versus baseline, and MR versus WG problems respectively. SIGNIFICANCE: In terms of accuracy, the current visual presentation outperforms the motor imagery visual presentation we designed before for the EEG-fTCD system by 10% accuracy for task versus task problem. Moreover, the proposed system outperforms the state of the art hybrid EEG-fNIRS BCIs in terms of accuracy and/or information transfer rate. Even though there are still limitations of the proposed system, such promising results show that the proposed hybrid system is a feasible candidate for real-time BCIs.

El ABC de la ecografía transfontanelar y más / The ABCs of transfontanellar ultrasound and more

La ecografía transfontanelar es una técnica diagnóstica ampliamente utilizada en el estudio de la neuroanatomía y patología propia del encéfalo neonatal gracias a sus múltiples ventajas, como la ausencia de radiaciones, disponibilidad, portabilidad y bajo coste. El desarrollo de equipos más potentes junto con la mejora de sondas microcurvadas y lineares de distintas frecuencias ha permitido una ostensible mejoría en la calidad de la imagen ecográfica del cerebro neonatal. Para obtener el máximo rendimiento de esta técnica es importante familiarizarse con la anatomía y patología neurológica de este grupo de edad. De hecho, es la primera técnica en el estudio de complicaciones a corto y medio plazo de los recién nacidos prematuros. En el neonato a término es muy útil para abordar múltiples situaciones clínicas, ya que permite seleccionar qué pacientes se beneficiarán de otras técnicas invasivas, más caras o que requieran sedación, como la resonancia magnética. Sus desventajas son ser operador dependiente y la necesidad de una adecuada ventana acústica. Tiene limitaciones en el estudio de la patología traumática obstétrica, la valoración de la patología malformativa compleja y el daño de la sustancia blanca. Con los conocimientos básicos de neurología neonatal, el equipamiento apropiado y una técnica cuidadosa que incluya el uso de distintas fontanelas, es un método fiable que permite el diagnóstico y seguimiento de patologías tanto congénitas como adquiridas en el neonato (AU)

Transfontanellar ultrasound is widely used to study neonatal neuroanatomy and disease. This technique has many advantages, such as the absence of ionizing radiation and its wide availability, portability, and low cost. The development of more powerful ultrasound scanners and improved microcurved and linear probes of different frequencies have resulted in improved image quality. To take full advantage of this technique, it is important to know the normal and pathologic anatomy in neonates. Transfontanellar ultrasound is the first-line technique for studying short-term and mid-term complications in premature newborns. In full-term newborns, it is very useful in many clinical situations, making it possible to select which patients will benefit from other techniques that are more invasive or more expensive, or that require sedation, such as MRI. The disadvantages of the technique are that it is operator dependent and that an appropriate acoustic window is necessary. It also has limitations in the study of obstetric trauma, in the evaluation of complex malformations, and in the assessment of damage to white matter. With a basic understanding of neonatal neurology, the appropriate equipment, and a careful technique taking advantage of the different fontanels, transfontanellar ultrasound is a reliable method that makes it possible to diagnose and follow up both congenital and acquired conditions in neonates (AU)

Detection of right-to-left shunts: comparison between the International Consensus and Spencer Logarithmic Scale criteria.

BACKGROUND: International Consensus Criteria (ICC) consider right-to-left shunt (RLS) present when Transcranial Doppler (TCD) detects even one microbubble (microB). Spencer Logarithmic Scale (SLS) offers more grades of RLS with detection of >30 microB corresponding to a large shunt. We compared the yield of ICC and SLS in detection and quantification of a large RLS. SUBJECTS AND METHODS: We prospectively evaluated paradoxical embolism in consecutive patients with ischemic strokes or transient ischemic attack (TIA) using injections of 9 cc saline agitated with 1 cc of air. Results were classified according to ICC [negative (no microB), grade I (1-20 microB), grade II (>20 microB or "shower" appearance of microB), and grade III ("curtain" appearance of microB)] and SLS criteria [negative (no microB), grade I (1-10 microB), grade II (11-30 microB), grade III (31100 microB), grade IV (101300 microB), grade V (>300 microB)]. The RLS size was defined as large (>4 mm) using diameter measurement of the septal defects on transesophageal echocardiography (TEE). RESULTS: TCD comparison to TEE showed 24 true positive, 48 true negative, 4 false positive, and 2 false negative cases (sensitivity 92.3%, specificity 92.3%, positive predictive value (PPV) 85.7%, negative predictive value (NPV) 96%, and accuracy 92.3%) for any RLS presence. Both ICC and SLS were 100% sensitive for detection of large RLS. ICC and SLS criteria yielded a false positive rate of 24.4% and 7.7%, respectively when compared to TEE. CONCLUSIONS: Although both grading scales provide agreement as to any shunt presence, using the Spencer Scale grade III or higher can decrease by one-half the number of false positive TCD diagnoses to predict large RLS on TEE.

Classification of transcranial Doppler signals using their chaotic invariant measures.

In this study, chaos analysis was performed on the transcranial Doppler (TCD) signals recorded from the temporal region of the brain of 82 patients as well as of 24 healthy people. Two chaotic invariant measures, i.e. the maximum Lyapunov exponent and the correlation dimension, were calculated for the TCD signals after applying nonlinearity and stationarity tests to them. The sonograms obtained via Burg autoregressive (AR) method demonstrated that the chaotic invariant measures represented the unpredictability and complexity levels of the TCD signals. According to the multiple linear regression analysis, the chaotic invariant measures were found to be highly significant for the regression equation which fitted to the data. This result suggested that the chaotic invariant measures could be used for automatically differentiating various cerebrovascular conditions via an appropriate classifier. For comparison purposes, we investigated several different classification algorithms. The k-nearest neighbour algorithm outperformed all the other classifiers with a classification accuracy of 94.44% on the test data. We used the receiver operating characteristic (ROC) curves in order to assess the performance of the classifiers. The results suggested that the classification systems which use the chaotic invariant measures as input have potential in detecting the blood flow velocity changes due to various brain diseases.

O Doppler colorido na avaliaçäo do fluxo arterial cerebral em recém-natos normais. Influência da sucçäo ao seio materno / Evalution by color Doppler of arterial blood flow of healthy newborns. Influence os breast feeding

Resumo: No período de abril de 1996 foram realizados exames de Doppler colorido em 256 recém-natos normais nas artérias cerebrais médias direita e esquerda e na artéria cerebral anterior. Definiram-se como critérios de avaliaçäo por artéria a velocidade média, o índice de resistência e o índice de pulsatilidade. Foi verificada influência significativa (p<0,01) da idade pós-natal nos índices previamente estabelecidos, e do peso no índice de resistência. O Capurro somático foi fator influente no espectro do fluxo arterial, embora näo tenha apresentado significado estatístico nos resultados. Verificou-se, ainda, que a sucçäo ao seio materno durante o exame de Doppler colorido, prática adotada em exames ambulatoriais, é também fator influente (p<0,01) no espectro do fluxo arterial, aumentando a velocidade média e reduzindo os valores dos índices de avaliaçäo. Näo foi observada influência do sexo, da gemeralidade, do tipo de parto e do Apgar no espectro arterial.