Use of the HAS-BLED Score in Risk Stratifying Patients on Dual Antiplatelet Therapy After Coronary Stent

Objectives: Use of the HAS-BLED score in risk stratifying patients on dual antiplatelet therapy after stent placement. Methods & Results: 304 patients who underwent stent placement from June, 2018 to December 2018. There is 6,57% patients with medium & severe bleeding. Area under the curve of HAS-BLED score (AUC); PRECISE-DAPT score and CRUSADE were sequential 0.59; 0,79 and 0,84 (p=0,0001) at post-PCI procedures; were sequential 0,72; 0,94 và 0,88 (p=0,00001) at less than 6 months after PCI procedures, and were sequential 0,87; 0,73 và 0,70 (p=0,0068) at more than 6 months after PCI procedures. Conclusion: the HAS-BLED score was most useful for predicting bleeding in patients on on dual antiplatelet therapy after stent placement at more than 6 months after PCI procedures. PRECISE-DAPT score was most useful for predicting bleeding at less than 6 months after PCI procedures and CRUSADE score was most useful for predicting bleeding at post procedure.

Hybrid Thresholding Method in Detection and Extraction of Brain Hemorrhage on the CT-Scan Image

Brain bleeding can occur because of the outbreak of the blood vessels in the brain which culminated into hemorrhagic stroke or stroke due to bleeding. Hemorrhagic Stroke occurs when there is a burst of blood vessels result from some trigger factor. Segmentation techniques to Scanner computed tomography images (CT scan of the brain) is one of the methods used by the radiologist to detect brain bleeding or congenital abnormalities that occur in the brain. This research will determine the area of the brain bleeding on each image slice CT - scan every patient, to detect and extract brain bleeding, so it can calculate the volume of the brain bleeding. The detection and extraction bleeding area of the brain is based on the hybrid thresholding method.

Combined method of stopping nasal hemorrage

Topicality: Nasal hemorrhage (NH) is one of the most common reasons for patients to seek emergency otorhinolaryngological care. Due to the significant increase in cardiovascular disease, endovascular interventions, as well as the wide use of anticoagulant and disaggregating therapy (in most cases, long courses or even lifelong), cases of recurrent NH have become more frequent. In reference, there is a problem of modification of local methods of stopping NH in patients who receive the above therapy for a long time, because intervention in the hemostasis system in this group of patients causes certain difficulties. Aim of the study: The development of an anatomical intranasal tampon that allows you to combine several types of effects on the bleeding area is an extremely important task. Materials and methods: We have proposed a combined method of stopping NH, which includes the use of a two-chambered hydraulic tampon of our self design in combination with gel “Nosochem” and thermal exposure. Results: The proposed method of stopping NH was used in 24 patients, the average duration of nasal tamponade was 52.4±5.3 hours. In 23 (95.8%) patients, the proposed method provided effective stoppage of NH. Conclusions. The proposed hydrotampon in combination with “Nosochem” gel and local thermal exposure is a simple, effective and convenient to use combined method of stopping NH, which can be used as a method of choice for NH in patients who take anticoagulants and disaggregants for a long time.

Automated Classification of Blood Loss from Transurethral Resection of the Prostate Surgery Videos Using Deep Learning Technique

Transurethral resection of the prostate (TURP) is a surgical removal of obstructing prostate tissue. The total bleeding area is used to determine the performance of the TURP surgery. Although the traditional method for the detection of bleeding areas provides accurate results, it cannot detect them in time for surgery diagnosis. Moreover, it is easily disturbed to judge bleeding areas for experienced physicians because a red light pattern arising from the surgical cutting loop often appears on the images. Recently, the automatic computer-aided technique and artificial intelligence deep learning are broadly used in medical image recognition, which can effectively extract the desired features to reduce the burden of physicians and increase the accuracy of diagnosis. In this study, we integrated two state-of-the-art deep learning techniques for recognizing and extracting the red light areas arising from the cutting loop in the TURP surgery. First, the ResNet-50 model was used to recognize the red light pattern appearing in the chipped frames of the surgery videos. Then, the proposed Res-Unet model was used to segment the areas with the red light pattern and remove these areas. Finally, the hue, saturation, and value color space were used to classify the four levels of the blood loss under the circumstances of non-red light pattern images. The experiments have shown that the proposed Res-Unet model achieves higher accuracy than other segmentation algorithms in classifying the images with the red and non-red lights, and is able to extract the red light patterns and effectively remove them in the TURP surgery images. The proposed approaches presented here are capable of obtaining the level classifications of blood loss, which are helpful for physicians in diagnosis.

Theoretical Study on Pressure Damage Based on Clinical Purpura during the Laser Irradiation of Port Wine Stains with Real Complex Vessels

Port wine stains (PWSs) are congenital dermal vascular lesions composed of a hyperdilated vasculature. Purpura represented by local hemorrhage from water vaporization in blood during laser therapy of PWS is typically considered a clinical feedback, but with a low cure rate. In this study, light propagation and heat deposition in skin and PWSs is simulated by a tetrahedron-based Monte Carlo method fitted to curved bio-tissues. A curvature-corrected pressure damage model was established to accurately evaluate the relationship between purpura-bleeding area (rate) and laser therapy strategy for real complex vessels. Results showed that the standard deviation of Gaussian curvature of the vessel wall has negative relation with the fluence threshold of vessel rupture, but has positive relation with the effective laser fluence of vessel damage. This finding indicated the probable reason for the poor treatment of PWS, that is, considering purpura formation as a treatment end point (TEP) only leads to partial removal of vascular lesions. Instead, appropriate purpura area ratio with marked effects or rehabilitation should be adopted as TEP. The quantitative correlation between the fluence of a pulsed dye laser and the characteristics of vascular lesions can provide personalized and precise guidance for clinical treatments.

Pre-processing Technique for Wireless Capsule Endoscopy Image Enhancement

<span>Wireless capsule endoscopy (WCE) is used to examine human digestive tract in order to detect abnormal area. However, it has been a challenging task to detect abnormal area such as bleeding due to poor quality and dark images of WCE. In this paper, pre-processing technique is introduced to ease classification of the bleeding area. Anisotropic contrast diffusion method is employed in our pre-processing technique as a contrast enhancement of the images. There is a drawback to the method proposed B. Li in which the quality of WCE image is degraded when the number of iteration increases. To solve this problem, variance is employed in our proposed method. To further enhance WCE image, Discrete Cosine Transform is used with anisotropic contrast diffusion. Experimental results show that both proposed contrast enhancement algorithm and sharpening WCE image algorithm provide better performance compared with B. Li’s algorithm since SDME and EBCM value is stable whenever number of iterations increases, and sharpness measurement using gradient and PSNR are both improved by 31.5% and 20.3% respectively.</span>

Pre-processing Technique for Wireless Capsule Endoscopy Image Enhancement

<span>Wireless capsule endoscopy (WCE) is used to examine human digestive tract in order to detect abnormal area. However, it has been a challenging task to detect abnormal area such as bleeding due to poor quality and dark images of WCE. In this paper, pre-processing technique is introduced to ease classification of the bleeding area. Anisotropic contrast diffusion method is employed in our pre-processing technique as a contrast enhancement of the images. There is a drawback to the method proposed B. Li in which the quality of WCE image is degraded when the number of iteration increases. To solve this problem, variance is employed in our proposed method. To further enhance WCE image, Discrete Cosine Transform is used with anisotropic contrast diffusion. Experimental results show that both proposed contrast enhancement algorithm and sharpening WCE image algorithm provide better performance compared with B. Li’s algorithm since SDME and EBCM value is stable whenever number of iterations increases, and sharpness measurement using gradient and PSNR are both improved by 31.5% and 20.3% respectively.</span>