No abstract

No abstract

This article aims to develop a method for the detection and segmentation of a cytoplast and nucleus from a cervix smear image. First, the technique of equalization method with Gaussian filter is adopted to eliminate noise in the image. Second, a new edge enhancement technique is proposed to work out the coarseness of each pixel, which is later used as a determining characteristic of reinforced object images. A two-group object enhancement technique is then used to reinforce this object according to rough pixels. Third, the proposed detector enhances the gradients of the edges of the cytoplast and nucleus while suppressing the noise gradients, and then specifies the pixels with higher gradients as possible edge pixels. Finally, it picks out the two longest closed curves constructed by part of the edge pixels. Detection and segmentation performance of the proposed method is later compared with seed region growing feature extraction and level set method using 10 cervix smear images as example. Besides comparing the contour segment of the cytoplast and nucleus obtained by using different methods, we also compare the quality of the segmentation results. Experimental results show that the proposed detector demonstrates an impressive performance.

No abstract

No abstract

No abstract

Left ventricular hypertrophy (LVH) indicates subclinical organ damage, associating with the incidence of cardiovascular diseases. From the medical perspective, electrocardiogram (ECG) is a low-cost, non-invasive, and easily reproducible tool that is often used as a preliminary diagnosis for the detection of heart disease. Nowadays, there are many criteria for assessing LVH by ECG. These criteria usually include that voltage combination of RS peaks in multi-lead ECG must be greater than one or more thresholds for diagnosis. We developed a system for detecting LVH using ECG signals by two steps: firstly, the R-peak and S-valley amplitudes of the 12-lead ECG were extracted to automatically obtain a total of 24 features and ECG beats of each case (LVH or non-LVH) were segmented; secondly, a back propagation neural network (BPN) was trained using a dataset with these features. Echocardiography (ECHO) was used as the gold standard for diagnosing LVH. The number of LVH cases (of a Taiwanese population) identified was 173. As each ECG sequence generally included 8 to 13 cycles (heartbeats) due to differences in heart rate, etc., we identified 1466 ECG cycles of LVH patients after beat segmentation. Results showed that our BPN model for detecting LVH reached the testing accuracy, precision, sensitivity, and specificity of 0.961, 0.958, 0.966 and 0.956, respectively. Detection performances of our BPN model, on the whole, outperform 7 methods using ECG criteria and many ECG-based artificial intelligence (AI) models reported previously for detecting LVH.

No abstract