This paper presents an asynchronously intracortical brain-computer interface (BCI) which allows the subject to continuously drive a mobile robot. This system has a great implication for disabled patients to move around. By carefully designing a multiclass support vector machine (SVM), the subject's self-paced instantaneous movement intents are continuously decoded to control the mobile robot. In particular, we studied the stability of the neural representation of the movement directions. Experimental results on the nonhuman primate showed that the overt movement directions were stably represented in ensemble of recorded units, and our SVM classifier could successfully decode such movements continuously along the desired movement path. However, the neural representation of the stop state for the self-paced control was not stably represented and could drift.
In this work, we proposed to demonstrate the entire 3D coronary tree using panoramic maximum intensity projection (MIP) of coronary arteries, and to detect and quantify coronary stenosis from computed tomography coronary angiography (CTCA). The performance of the proposed method was assessed in comparison with invasive coronary angiography (ICA) as reference standard. Six anonymized CTCA datasets were tested. MIP method achieved a sensitivity of 82% and a specificity of 95% for the stenosis detection with a good reproducibility (i.e. Cohen's kappa coefficient of 0.74 for the intra-rater agreement, and 0.45 for the inter-raters agreement). In stenosis quantification, three image options are provided. The original density images resulted in an accuracy of 0.85. The edge map images resulted in an accuracy of 0.79. The image combination had a better accuracy of 0.89 than any single image option. In conclusion, the panoramic MIP provided fast and accurate way for the stenosis detection and quantification. It may be helpful to assist the radiologist in identifying the location of the greatest narrowing in clinical practice.
Non-invasive cardiac computed tomography angiography (CTA) is widely used to assess coronary artery stenosis and give clinical decision-making support to clinicians. The severity of stenosis lesion is commonly graded by a range of percent Diameter Stenosis (DS), which can introduce false positive diagnoses or over-estimation, triggering unnecessary further procedures. In this paper, a system and the associate methods to quantify stenosis by the percent Area Stenosis (AS) from cardiac CTA is presented. In the process, coronary artery tree is segmented and the centerline is extracted by Hessian filtering and the minimal path method. After a serial of 2D cross-sectional artery images along the artery centerline are obtained, lumen areas are segmented by ellipse-fitting with deformable models, and consequently to compute the lesion's AS. Experimental results on 5 CTA data sets show that compared to DS, AS better correlates to the reference standard for stenosis quantification, suggesting the efficacy of the proposed system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.