Although radio frequency ablation is the most effective treatment for atrial fibrillation (AF), there is still a high recurrence rate. The purpose of this paper was to initially assess the probability of the recurrence of AF based on the preoperative body surface potential mapping (BSPM) signals, in other words, to predict the efficiency of ablation and assist physicians in developing more effective treatment options. At present, deep learning methods based on convolutional neural networks (CNNs) do not require complex mathematical abstractions or manual interventions; thus, higher computation efficiency can be obtained in such research. However, the use of the fully connected multi-layer perceptron (MLP) algorithms has shown low classification performance. This paper proposes an improved CNN algorithm (CNN-SVM method) for the recurrence classification in AF patients by combining with the support vector machine (SVM) architecture. The algorithm is validated on the preoperative AF signals of 14 patients for classification. All postoperative patients are followed up for one year; ten of them remain in sinus rhythm, whereas the other four turn back to AF. The ECG data for these patients are obtained through the 128-Lead BSPM system. The results show that the proposed CNN-SVM method can automatically extract the characteristic information through the CNN network. The constructed model ultimately achieved an accuracy of 96%, a sensitivity of 88%, and a specificity of 96%. It is concluded that the CNN-SVM method solves the drawbacks of MLP only for separating linear data. It improves the overall performance of AF recurrence classification, thereby providing a valuable reference for doctors to develop personalized treatment plans. INDEX TERMS Classification of AF recurrence, deep learning, body surface potential mapping, support vector machines. The associate editor coordinating the review of this manuscript and approving it for publication was Yonghong Peng.

Automatic detection of ventricular fibrillation (VF) is of great important for automated external defibrillators (AEDs). However, it is a difficult issue due to the similarity between ventricular fibrillation and ventricular tachycardia (VT). In this paper, a novel scheme based on empirical mode decomposition (EMD) is proposed to disclosure the underlying information of VT, VF and normal electrocardiogram (ECG). The intrinsic mode functions (IMFs), especially the first IMF, may demonstrate distinct properties of different types of ECG signals. Two efficient features derived from IMFs are used for discrimination, namely Frequency Spectrum Entropy (SpEn) and Energy Rate ER IMF . Data from the standard database of MIT-BIH and AHA are used to evaluate the method. With Bayes theory classifier, our method can successfully differentiate VF, VT and normal ECG with the accuracy of 99.78%, 99.78% and 100% respectively. Thus it may provide a new vision for understanding mechanism of cardiac activity and an effective method for VF detection.

Image-to-patient space registration is to make the accurate alignment between the actual operating space and the image space. Although the image-to-patient space registration using paired-point is used in some image-guided neurosurgery systems, the current paired-point registration method has some drawbacks and usually cannot achieve the best registration result. Therefore, surface-matching registration is proposed to solve this problem. This paper proposes a surface-matching method that accomplishes image-to-patient space registration automatically. We represent the surface point clouds by the Gaussian Mixture Model (GMM), which can smoothly approximate the probability density distribution of an arbitrary point set. We also use mutual information as the similarity measure between the point clouds and take into account the structure information of the points. To analyze the registration error, we introduce a method for the estimation of Target Registration Error (TRE) by generating simulated data. In the experiments, we used the point sets of the cranium surface and the model of the human head determined by a CT and laser scanner. The TRE was less than 2[Formula: see text]mm, and the TRE had better accuracy in the front and the posterior region. Compared to the Iterative Closest Point algorithm, the surface registration based on GMM and the structure information of the points proved superior in registration robustness and accurate implementation of image-to-patient registration.

No abstract

No abstract