Patterns of Transcranial Doppler Flow Velocities in Recent Ischemic Stroke Patients

Identification of middle cerebral artery stenosis in transcranial Doppler using a modified VGG-16

Objectives

The diagnosis of intracranial atherosclerotic stenosis (ICAS) is of great significance for the prevention of stroke. Deep learning (DL)-based artificial intelligence techniques may aid in the diagnosis. The study aimed to identify ICAS in the middle cerebral artery (MCA) based on a modified DL model.

Methods

This retrospective study included two datasets. Dataset1 consisted of 3,068 transcranial Doppler (TCD) images of the MCA from 1,729 patients, which were assessed as normal or stenosis by three physicians with varying levels of experience, in conjunction with other medical imaging data. The data were used to improve and train the VGG16 models. Dataset2 consisted of TCD images of 90 people who underwent physical examination, which were used to verify the robustness of the model and compare the consistency between the model and human physicians.

Results

The accuracy, precision, specificity, sensitivity, and area under curve (AUC) of the best model VGG16 + Squeeze-and-Excitation (SE) + skip connection (SC) on dataset1 reached 85.67 ± 0.43(%),87.23 ± 1.17(%),87.73 ± 1.47(%),83.60 ± 1.60(%), and 0.857 ± 0.004, while those of dataset2 were 93.70 ± 2.80(%),62.65 ± 11.27(%),93.00 ± 3.11(%),100.00 ± 0.00(%), and 0.965 ± 0.016. The kappa coefficient showed that it reached the recognition level of senior doctors.

Conclusion

The improved DL model has a good diagnostic effect for MCV stenosis in TCD images and is expected to help in ICAS screening.

Effect of Jiawei Tongqiao Huoxue decoction in basilar artery dolichoectasia mice through yes-associated protein/transcriptional Co-activator with PDZ-binding motif pathway

ETHNOPHARMACOLOGICAL RELEVANCE

The Jiawei Tongqiao Huoxue decoction (JTHD), composed of Acorus calamus var. angustatus Besser, Paeonia lactiflora Pall., Conioselinum anthriscoides 'Chuanxiong', Prunus persica (L.) Batsch, Ziziphus jujuba Mill., Carthamus tinctorius L., Pueraria montana var. lobata (Willd.) Maesen & S.M.Almeida ex Sanjappa & Predeep, Zingiber officinale Roscoe, Leiurus quinquestriatus, and Moschus berezovskii Flerov, was developed based on Tongqiao Huoxue decoction in Wang Qingren's "Yilin Gaicuo" in the Qing Dynasty. It has the effect of improving not only the blood flow velocity of vertebral and basilar arteries but also the blood flow parameters and wall shear stress. Especially in recent years, the potential efficacy of traditional Chinese medicine (TCM) for the treatment of basilar artery dolichoectasia (BAD) has attracted great attention as there are still no specific remedies for this disease. However, its molecular mechanism has not been elucidated. To identify the potential mechanisms of JTHD will help to intervene BAD and provide a reference for its clinical application.

AIM OF THE STUDY

This study aims to establish a mouse model of BAD and explore the mechanism of JTHD regulating yes-associated protein/transcriptional co-activator with PDZ-binding motif (YAP/TAZ) pathway for attenuating BAD mice development.

MATERIALS AND METHODS

Sixty post-modeling C57/BL6 female mice were randomly divided into sham-operated, model, atorvastatin calcium tablet, low-dose JTHD, and high-dose JTHD groups. After 14 days of modeling, the pharmacological intervention was given for 2 months. Then, JTHD was analyzed by liquid chromatography-tandem mass spectrometry (LC-MS). ELISA was utilized to detect the changes in vascular endothelial growth factor (VEGF) and lipoprotein a (Lp-a) in serum. EVG staining was conducted to observe the pathological changes of blood vessels. TUNEL method was employed to detect the apoptosis rate of vascular smooth muscle cells (VSMCs). Micro-CT and ImagePro Plus software were used to observe and calculate the tortuosity index, lengthening index, percentage increase in vessel diameter, and tortuosity of the basilar artery vessels in mice. Western blot analysis was performed to detect the expression levels of YAP and TAZ proteins in the vascular tissues of mice.

RESULTS

Many effective compounds such as choline, tryptophan, and leucine with anti-inflammation and vascular remodeling were identified in the Chinese medicine formula by LC-MS analysis. The serum levels of VEGF in the model mice decreased significantly while the levels of Lp-a increased obviously compared with those in the sham-operated group. The intima-media of the basilar artery wall showed severe disruption of the internal elastic layer, atrophy of the muscular layer, and hyaline changes of the connective tissue. Apoptosis of VSMCs added. Dilatation, elongation, and tortuosity of the basilar artery became notable, and tortuosity index, lengthening index, percentage increase in vessel diameter, and bending angle remarkably improved. The expression levels of YAP and TAZ protein in blood vessels elevated conspicuously (P < 0.05, P < 0.01). JTHD group markedly reduced the lengthening, bending angle, percentage increase in vessel diameter, and tortuosity index of basilar artery compared with the model group after 2 months of pharmacological intervention. The group also decreased the secretion of Lp-a and increased the content of VEGF. It inhibited the destruction of the internal elastic layer, muscular atrophy, and hyaline degeneration of connective tissue in basilar artery wall. The apoptosis of VSMCs was decreased, and the expression levels of YAP and TAZ proteins were abated (P < 0.05, P < 0.01).

CONCLUSIONS

The mechanism of inhibition of basilar artery elongation, dilation, and tortuosity by JTHD, which has various anti-BAD effective compound components, may be related to the reduction in VSMCs apoptosis and downregulation of YAP/TAZ pathway expression.

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.