Search

Accurate segmentation of pediatric echocardiograms is a challenging task, because significant heart-size changes with age and faster heart rate lead to more blurred boundaries on cardiac ultrasound images compared with adults. To address these problems, a dual decoder network model combining channel attention and scale attention is proposed in this paper. Firstly, an attention-guided decoder with deep supervision strategy is used to obtain attention maps for the ventricular regions. Then, the generated ventricular attention is fed back to multiple layers of the network through skip connections to adjust the feature weights generated by the encoder and highlight the left and right ventricular areas. Finally, a scale attention module and a channel attention module are utilized to enhance the edge features of the left and right ventricles. The experimental results demonstrate that the proposed method in this paper achieves an average Dice coefficient of 90.63% in acquired bilateral ventricular segmentation dataset, which is better than some conventional and state-of-the-art methods in the field of medical image segmentation. More importantly, the method has a more accurate effect in segmenting the edge of the ventricle. The results of this paper can provide a new solution for pediatric echocardiographic bilateral ventricular segmentation and subsequent auxiliary diagnosis of congenital heart disease.

Copyright of Imaging Science & Photochemistry is the property of Imaging Science & Photochemistry Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Imaging Science & Photochemistry is the property of Imaging Science & Photochemistry Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Kunming Medical University / Kunming Yike Daxue Xuebao is the property of Kunming Medical Journal and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Imaging Science & Photochemistry is the property of Imaging Science & Photochemistry Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Imaging Science & Photochemistry is the property of Imaging Science & Photochemistry Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In view of the existing endocardium and epicardium contour of left ventricle segmentation methods, there are some problems such as the poor regularity of segmented contour, segmenting the fuzzy edge of ventricular membrane incompletely and low segmentation efficiency. This paper proposed a new double well potential function and anisotropy gradient vector flow (AGVF) energy function improved level set model, with the fusion of zero level set and k level set of the double level set, the division of left ventricular inner and outer membrane method at the same time. First of all, with the modified Hough change detection algorithm, positioned ventricular endocardium and epicardium initial position; then, it used the double level set model to segment the endocardium and epicardium simultaneously. The experimental results show that the proposed method can segment smooth endocardium and epicardium contour of left ventricle. The analysis of experimental datum demonstrates that the proposed method can segment endocardium and epicardium contour of left ventricle confirms to the clinical definition, and increases averagely the overlap rate of the endocardium and epicardium contour on MRI images to 0. 956 9. [ABSTRACT FROM AUTHOR]

This paper is to compare dual-source computed tomography (DSCT) with trans-thoracic echocardiography (TTE) in the evaluation of anomalous pulmonary venous connection (APVC) to explore the advantages of DSCT. Thirty-one patients with APVC detected by DSCT were enrolled in this study. In this cohort, 16 patients underwent echocardiography followed by operative treatments; and among the remained 15 patients who did not received surgical treatment, echocardiography was performed in 10 patients. The numbers and drainage sites of anomalous pulmonary veins, and accompanied defects on DSCT and TTE were retrospectively analyzed. In terms of diagnosis of the numbers and the drainage sites of anomalous pulmonary veins, the accuracy of DSCT was 98% (49/50) and 93.8% (15/16), while the accuracy of echocardiography was 80% (40/50) and 56.3% (9/16), respectively. There were statistical differences between the two modalities (P < 0.05). Although the detection rates of accompanied defects were 89.1% (41/46) and 78.3% (36/46) for DSCT and echocardiography, respectively, no statistically significant difference was found between the two modalities (P > 0.05). The 15 patients without receiving surgical treatments were partial APVC confirmed by DSCT, but APVC was found in 40% (4/10) patients by echocardiography. In conclusion, DSCT could be superior to evaluating APVC in comparison with echocardiography, and should be recommended as an important procedure for preoperative assessment of the anomaly in patients with APVC.

In this paper is presented the research and development of a new myocardial contrast echocardiography (MCE)-based quantitative analysis system for myocardial microcirculation. The system can measure the values of A, beta, A x beta, A-EER (endo-epi ratio of A), beta-EER and A x beta-EER from the signal intensity of real-time 2-D grayscale images and power Doppler images; it can draw the time-intensity curves to indicate the variation of the intensity of microbubbles scattering in subendocardial layer and subepicardial layer with the varying of myocardial segments; and it can estimate the hemodynamic parameters by nonlinear regression analysis. So the MCE software system has brought the quantitative analysis of real-time MCE to success.

Objective: To establish a novel speckle tracking algorithm for estimating myocardial motion., Method: A search method was proposed to find the optimal window size for image matching. Simulation and clinical experiment were conducted to demonstrate the validity of this algorithm., Result: The optimal window size for image matching was determined using this algorithm. Correct speckle tracking could be fulfilled with the algorithm proposed., Conclusion: The method proposed in this paper is effective for speckle tracking.

Based on the application of box-counting fractal model to the texture analysis of ultrasonic image after intravenous injection of Levovist acoustics contrast agent in a dog, this paper presents a method to calculate the fractal dimension(D) and assistant characteristic (C(L)) of the ultrasonic images of left ventricle. It was found that the D and C(L) changed regularly in the continued cardiac cycles, that is, the maximum value of D appears during diastasis, the minimum value appears during end-systole; as the ventricular systole begins, D changes from maximum to smallness, and as the diastole begins, D changes from smallness to maximum; the maximum value of C(L) appears around end-systole, the minimum value appears around diastasis; from the start of left ventricular systole to end-systole, C(l) shows a tendency to change from smallness to maximum, and from the start of diastole to diastasis, it shows a tendency to change from maximum to smallness. The changes of D and C(L) are very similar to the changes of left ventricular pressure. It is thus evident that there is correlation between the fractal texture characteristics of the contrast agent ultrasonic images and the changes of intracardiac pressure. The results demonstrate that it is possible to measure the intracardiac pressure noninvasively.

Objective Hypereosinophilic syndrome (HES) is a hematological disorder that may involve multiple organs, especially the heart as the targeting organ, and is the most important cause of death among patients. This paper summarizes the clinical and echocardiographic results of patients diagnosed with HES so as to provide an accurate and feasible method for early detection and timely treatment of the disease. Methods We retrospectively analyzed the clinical data of five HES patients who came to the Department of Cardiology, Xi'an Jiaotong University, from 2004 to 2014 with the purpose of finding out the common and specific manifestations in transthoracic echo imaging. Results There were five patients diagnosed with HES, with four cases of idiopathic HES and one of secondary HES after parasitic infection. Atrial enlargement was detected in the five patients, including four cases with double atria expansion and two cases with ventricular dilatation. Endocardial thickening was observed in all the patients with thrombosis, including four cases of thrombus detected in the double chambers' apex of and one case of thrombus only in the left ventricular apex. Changes of the valves and the pericardium were also shown in the transthoracic echocardiographic images and might be the characteristic features. Conclusion Cardiac damage caused by HES is the main cause of death in the patients. Echocardiography can accurately show characteristic changes and provide help for early detection and correct treatment. [ABSTRACT FROM AUTHOR]

In the present paper, a method of three dimension direct matching interpolation for a series of 2-D echo-cardial images with intersecting each other and arranging at an angle in space has been developed. It is different from the conventional interpolation. During the interpolation, sectional images are acquired and the 3-D spatial position of "empty voxel" in sectional images is located; secondly, the cubic volume is constructed, and the motion orbit of images between two windows where the nearest original image intersects to the volume is found up, passing through the "empty voxel"; In the end, based on the matching pixels, the "empty voxel" is interpolated. This method simplifies the two interopolating procedures of the conventional methods into one procedure, and overcomes the shortcoming of the overlap of image data. Experiments show that the accuracy and reasonability of interpolation can be improved by the proposed method.

Copyright of Journal of Shanghai Jiaotong University (Medical Science) is the property of Journal of Shanghai Jiaotong University (Medical Science) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Segmentation is one of the most difficult problems in multidimensional reconstruction of ultrasonic heart image. In the present paper, a segmentation method of ultrasonic heart image using the self-organization neural network has been studied. This is an unsupervised segmentation method, which can segment images through clustering automatically. The results show that the present method has significant benefits over the traditional K-means algorithm.

In this paper, an omni-direction M-mode ultrasonic imaging method is introduced, in which M-mode sample line can rotate and move freely. In this way the measurement of parameters such as amplitude and speed of movement of organs can be conducted in any position or direction. We analyzed the sources of errors of the method and the way to overcome them.

Fourty five patients with COPD underwent right heart hemodynamics and M-mode echocardiographic study. 5 echocardiographic parameters were screened for diagnosing pulmonary hypertension. Whichever two or more parameters positive were regarded as diagnostic criteria, the sensitivity, specificity and correct rate of diagnosis were 71.43%, 85.00%, and 78.05% respectively. The hemodynamics basis of M-mode echocardiography used for diagnosis of pulmonary hypertension and cor pulmonale was provided in this paper.

Copyright of Journal of Shanghai Jiaotong University (Medical Science) is the property of Journal of Shanghai Jiaotong University (Medical Science) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)