Multichannel heuristic learning based single layer neural network filter for mixed noise suppression from color Doppler ultrasound images

Author(s):  
Manish Kumar ◽  
Sudhansu Kumar Mishra ◽  
Dilip Kumar Choubey ◽  
Sunil Kumar Jangir ◽  
Dinesh Goyal
Kanzo ◽  
1989 ◽  
Vol 30 (11) ◽  
pp. 1637-1638 ◽  
Author(s):  
Yousuke ARITA ◽  
Kazuaki YASUHARA ◽  
Jyunji FURUSE ◽  
Shoichi MATSUTANI ◽  
Masaaki EBARA ◽  
...  

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Peng Bian ◽  
Xiyu Zhang ◽  
Ruihong Liu ◽  
Huijie Li ◽  
Qingqing Zhang ◽  
...  

The neural network algorithm of deep learning was applied to optimize and improve color Doppler ultrasound images, which was used for the research on elderly patients with chronic heart failure (CHF) complicated with sarcopenia, so as to analyze the effect of the deep-learning-based color Doppler ultrasound image on the diagnosis of CHF. 259 patients were selected randomly in this study, who were admitted to hospital from October 2017 to March 2020 and were diagnosed with sarcopenia. Then, all of them underwent cardiac ultrasound examination and were divided into two groups according to whether deep learning technology was used for image processing or not. A group of routine unprocessed images was set as the control group, and the images processed by deep learning were set as the experimental group. The results of color Doppler images before and after processing were analyzed and compared; that is, the processed images of the experimental group were clearer and had higher resolution than the unprocessed images of the control group, with the peak signal-to-noise ratio (PSNR) = 20 and structural similarity index measure (SSIM) = 0.09; the similarity between the final diagnosis results and the examination results of the experimental group (93.5%) was higher than that of the control group (87.0%), and the comparison was statistically significant ( P < 0.05 ); among all the patients diagnosed with sarcopenia, 88.9% were also eventually diagnosed with CHF and only a small part of them were diagnosed with other diseases, with statistical significance ( P < 0.05 ). In conclusion, deep learning technology had certain application value in processing color Doppler ultrasound images. Although there was no obvious difference between the color Doppler ultrasound images before and after processing, they could all make a better diagnosis. Moreover, the research results showed the correlation between CHF and sarcopenia.


2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
YunShuang Wu ◽  
Yan Shen ◽  
Hailing Sun

Objective. The study focused on the correlation between lower extremity arteriosclerosis and diabetic mellitus (DM) foot, and it was explored by virtue of ultrasound images processed by an intelligent algorithm. Methods. A total of 60 DM foot patients admitted to our hospital in the past three years were selected and divided into two groups according to their condition. Patients with DM foot alone were in group B (30 cases), and patients with DM foot combined with lower extremity arteriosclerosis occlusion were in group C (30 cases). 30 healthy people were in group A as a control. Color Doppler ultrasound was used to examine the arteries of the lower extremities of all subjects. It the intramedia thickness (IMT) from the femoral artery to the dorsal foot artery was recorded, whether there was plaque in the artery or knowing the size of the plaque, its echo, and distribution, and whether the artery had stenosis. Next, the stenosis percentage was calculated. Additionally, the general information of patients was analyzed. At the same time, an intelligent algorithm was used to process ultrasound images, and its effects on image quality were evaluated. Results. Doppler ultrasound images processed by Artificial Bee Colony (ABC) had less noise and better quality, and key information about the lesion was clearly displayed. There was no statistical difference between the general data of the three groups of patients; group B and group C had higher IMT value, plaque incidence, arterial stenosis incidence, and degree of stenosis versus group A, and there were statistically significant differences between groups B and C. In particular, the incidence of femoral artery stenosis and the degree of stenosis were significantly higher in group C than in group B. The rate of stenosis above grade I in group C was as high as 71%, while that in group B was only 19%; in Group C, the incidence of stenosis above grade II was 30%, and that in group B was 13.1%. Compared with group A, group B and group C had decreased peak arterial blood velocity (PSV), resistance index (RI), and pulse index (PI), and there were statistically significant differences between groups B and C. Conclusion. DM foot is a risk factor for arteriosclerosis occlusion; color Doppler ultrasound demonstrates good diagnostic effects on arteriosclerosis occlusion; the algorithm proposed in this study can improve the quality of Doppler ultrasound images and has a high application value.


2014 ◽  
Vol 539 ◽  
pp. 395-399
Author(s):  
Hong Yan Jiang

In this paper, the advantages and disadvantages of the existing ultrasonic image management system are analyzed, and also a multi-functional color Doppler ultrasound image-text management system is researched and developed in combination with the experience of color Doppler ultrasound doctors. With this system, the related operations such as color Doppler ultrasound images acquisition, processing, preservation, and medical records are implemented. In the design of the system, a professional acquisition card is used for implementing the acquisition of ordinary video signals. In the meantime, DICOM interface is designed using DICOM3.0 protocol for implementing multi-mode acquisition.


Author(s):  
Joonsung Park ◽  
Doo Heon Song ◽  
Kwang Baek Kim

Automatic segmentation of brachial artery and blood-flow dynamics are important for early detection of cardiovascular disease and other vascular endothelial malfunctions. In this paper, we propose a software that is noise tolerant and fully automatic in segmentation of brachial artery from color Doppler ultrasound images. Possibilistic C-Means clustering algorithm is applied to make the automatic segmentation. We use HSV color model to enhance the contrast of bloodstream area in the input image. Our software also provides index of hemoglobin distribution with respect to the blood flow velocity for pathologists to proceed further analysis. In experiment, the proposed method successfully extracts the target area in 59 out of 60 cases (98.3%) with field expert’s verification.


Sign in / Sign up

Export Citation Format

Share Document