scholarly journals Retraining Convolutional Neural Networks for Specialized Cardiovascular Imaging Tasks: Lessons from Tetralogy of Fallot

2021 ◽  
Author(s):  
Animesh Tandon ◽  
Navina Mohan ◽  
Cory Jensen ◽  
Barbara E. U. Burkhardt ◽  
Vasu Gooty ◽  
...  
Keyword(s):  
Tetralogy Of Fallot ◽  
Hausdorff Distance ◽  
Volumetric Analysis ◽  
Dice Similarity Coefficient ◽  
Algorithm Performance ◽  
Comprehensive Method ◽  
Combined Use ◽  
Median Error ◽  
Structural Abnormalities ◽  
Testing Data

AbstractVentricular contouring of cardiac magnetic resonance imaging is the gold standard for volumetric analysis for repaired tetralogy of Fallot (rTOF), but can be time-consuming and subject to variability. A convolutional neural network (CNN) ventricular contouring algorithm was developed to generate contours for mostly structural normal hearts. We aimed to improve this algorithm for use in rTOF and propose a more comprehensive method of evaluating algorithm performance. We evaluated the performance of a ventricular contouring CNN, that was trained on mostly structurally normal hearts, on rTOF patients. We then created an updated CNN by adding rTOF training cases and evaluated the new algorithm’s performance generating contours for both the left and right ventricles (LV and RV) on new testing data. Algorithm performance was evaluated with spatial metrics (Dice Similarity Coefficient (DSC), Hausdorff distance, and average Hausdorff distance) and volumetric comparisons (e.g., differences in RV volumes). The original Mostly Structurally Normal (MSN) algorithm was better at contouring the LV than the RV in patients with rTOF. After retraining the algorithm, the new MSN + rTOF algorithm showed improvements for LV epicardial and RV endocardial contours on testing data to which it was naïve (N = 30; e.g., DSC 0.883 vs. 0.905 for LV epicardium at end diastole, p < 0.0001) and improvements in RV end-diastolic volumetrics (median %error 8.1 vs 11.4, p = 0.0022). Even with a small number of cases, CNN-based contouring for rTOF can be improved. This work should be extended to other forms of congenital heart disease with more extreme structural abnormalities. Aspects of this work have already been implemented in clinical practice, representing rapid clinical translation. The combined use of both spatial and volumetric comparisons yielded insights into algorithm errors.

scholarly journals Segmentation of Skull-infiltrated Tumors Using ITK: Methods and Validation

2005 ◽  
Author(s):  
Aleksandra Popovic ◽  
Martin Engelhardt ◽  
Klaus Radermacher
Keyword(s):  
Computed Tomography ◽  
Hausdorff Distance ◽  
Distance Measure ◽  
Ct Images ◽  
Similarity Coefficient ◽  
Simulated Dataset ◽  
Dice Similarity Coefficient ◽  
Validation Metrics ◽  
Chi Squared ◽  
Sensitivity Specificity

Methods for segmentation of skull infiltrated tumors in Computed Tomography (CT) images using Insight Segmentation and Registration Toolkit ITK (www.itk.org) are presented. Pipelines of filters and algorithms from ITK are validated on the basis of different criteria: sensitivity, specificity, dice similarity coefficient, Chi-squared, and Hausdorff distance measure. The method to rate segmentation results in relation to validation metrics is presented together with analysis of importance of different goodness measures. Results for one simulated dataset and three patient are presented.

scholarly journals A novel specific grading standard study of auto-segmentation of organs at risk in thorax: subjective–objective-combined grading standard

2021 ◽  
Vol 20 (1) ◽  
Author(s):  
Yanchen Ying ◽  
Hao Wang ◽  
Hua Chen ◽  
Jianfan Cheng ◽  
Hengle Gu ◽  
...  
Keyword(s):  
At Risk ◽  
Hausdorff Distance ◽  
Evaluation Method ◽  
Organs At Risk ◽  
Subjective Evaluation ◽  
The Other ◽  
Dice Similarity Coefficient ◽  
Evaluation Standard ◽  
Segmentation Accuracy ◽  
The Difference

Abstract Background To develop a novel subjective–objective-combined (SOC) grading standard for auto-segmentation for each organ at risk (OAR) in the thorax. Methods A radiation oncologist manually delineated 13 thoracic OARs from computed tomography (CT) images of 40 patients. OAR auto-segmentation accuracy was graded by five geometric objective indexes, including the Dice similarity coefficient (DSC), the difference of the Euclidean distance between centers of mass (ΔCMD), the difference of volume (ΔV), maximum Hausdorff distance (MHD), and average Hausdorff distance (AHD). The grading results were compared with those of the corresponding geometric indexes obtained by geometric objective methods in the other two centers. OAR auto-segmentation accuracy was also graded by our subjective evaluation standard. These grading results were compared with those of DSC. Based on the subjective evaluation standard and the five geometric indexes, the correspondence between the subjective evaluation level and the geometric index range was established for each OAR. Results For ΔCMD, ΔV, and MHD, the grading results of the geometric objective evaluation methods at our center and the other two centers were inconsistent. For DSC and AHD, the grading results of three centers were consistent. Seven OARs’ grading results in the subjective evaluation standard were inconsistent with those of DSC. Six OARs’ grading results in the subjective evaluation standard were consistent with those of DSC. Finally, we proposed a new evaluation method that combined the subjective evaluation level of those OARs with the range of corresponding DSC to determine the grading standard. If the DSC ranges between the adjacent levels did not overlap, the DSC range was used as the grading standard. Otherwise, the mean value of DSC was used as the grading standard. Conclusions A novel OAR-specific SOC grading standard in thorax was developed. The SOC grading standard provides a possible alternative for evaluation of the auto-segmentation accuracy for thoracic OARs.

scholarly journals Clinical Target Volume Auto-Segmentation of Esophageal Cancer for Radiotherapy After Radical Surgery Based on Deep Learning

2021 ◽  
Vol 20 ◽  
pp. 153303382110342
Author(s):  
Ruifen Cao ◽  
Xi Pei ◽  
Ning Ge ◽  
Chunhou Zheng
Keyword(s):  
Esophageal Cancer ◽  
Hausdorff Distance ◽  
Clinical Target Volume ◽  
Radical Surgery ◽  
Target Volume ◽  
Similarity Coefficient ◽  
Kappa Coefficient ◽  
Test Time ◽  
Dice Similarity Coefficient ◽  
Dilated Convolution

Radiotherapy plays an important role in controlling the local recurrence of esophageal cancer after radical surgery. Segmentation of the clinical target volume is a key step in radiotherapy treatment planning, but it is time-consuming and operator-dependent. This paper introduces a deep dilated convolutional U-network to achieve fast and accurate clinical target volume auto-segmentation of esophageal cancer after radical surgery. The deep dilated convolutional U-network, which integrates the advantages of dilated convolution and the U-network, is an end-to-end architecture that enables rapid training and testing. A dilated convolution module for extracting multiscale context features containing the original information on fine texture and boundaries is integrated into the U-network architecture to avoid information loss due to down-sampling and improve the segmentation accuracy. In addition, batch normalization is added to the deep dilated convolutional U-network for fast and stable convergence. In the present study, the training and validation loss tended to be stable after 40 training epochs. This deep dilated convolutional U-network model was able to segment the clinical target volume with an overall mean Dice similarity coefficient of 86.7% and a respective 95% Hausdorff distance of 37.4 mm, indicating reasonable volume overlap of the auto-segmented and manual contours. The mean Cohen kappa coefficient was 0.863, indicating that the deep dilated convolutional U-network was robust. Comparisons with the U-network and attention U-network showed that the overall performance of the deep dilated convolutional U-network was best for the Dice similarity coefficient, 95% Hausdorff distance, and Cohen kappa coefficient. The test time for segmentation of the clinical target volume was approximately 25 seconds per patient. This deep dilated convolutional U-network could be applied in the clinical setting to save time in delineation and improve the consistency of contouring.

scholarly journals Automated segmentation of cardiac adipose tissue in Dixon magnetic resonance images

2017 ◽  
Vol 8 (1) ◽  
pp. 1 ◽  
Author(s):  
Jon D. Klingensmith ◽  
Addison L. Elliott ◽  
Maria Fernandez-del-Valle ◽  
Sunanda Mitra
Keyword(s):  
Adipose Tissue ◽  
Magnetic Resonance ◽  
Hausdorff Distance ◽  
Linear Regression Analysis ◽  
Magnetic Resonance Images ◽  
Morphological Processing ◽  
Computer Algorithm ◽  
Dice Similarity Coefficient ◽  
Automated Segmentation ◽  
Time Required

Objective: Increasing evidence suggests a strong link between excess cardiac adipose tissue (CAT) and the risk of a cardiovascular event. Multi-echo Dixon magnetic resonance imaging (MRI), providing fat-only and water-only images, is a useful tool for quantification but requires the segmentation of CAT from a large number of images. The intent of this study was to evaluate an automated technique for CAT segmentation from Dixon MRI by comparing the contours identified by the automated algorithm to those manually traced by an observer. Methods: An automated segmentation algorithm, based on optimal thresholds and custom morphological processing, was applied to the registered fat-only and water-only images to identify CAT in the volume scans. CAT contours in 446 images, from 10 MRI scans, were selected for validation analysis. Cross-sectional area (CSA) and volume were computed and compared using Bland-Altman analysis. In addition, Hausdorff distance and Dice Similarity Coefficient (DSC) were used for assessment.Results: Linear regression analysis yielded correlation of R2 = 0.381 for CSA and R2 = 0.879 for volume. When compared to the observer, the computer algorithm under-estimated CSA by 27.5 ± 40.0% and volume by 26.4 ± 10.4%. The average bidirectional Hausdorff distance was 26.2 ± 16.0 mm while the average unidirectional Hausdorff distances were 24.5 ± 15.7 mm and 12.4 ± 11.7 mm. The average DSC was 0.561 ± 0.100. The time required for manual tracing was 15.84 ± 3.73 min and the time required for the computer algorithm was 2.81 ± 0.12 min.Conclusions: This study provided a technique, faster and less tedious than manual tracing (p < 0.00001), for quantification of CAT in Dixon MRI data, demonstrating feasibility of this approach for cardiac risk stratification.

scholarly journals Structural Abnormalities of the Pulmonary Trunk in Tetralogy of Fallot and Potential Clinical Implications

2009 ◽  
Vol 54 (20) ◽  
pp. 1883-1890 ◽  
Author(s):  
Elisabeth Bédard ◽  
Karen P. McCarthy ◽  
Konstantinos Dimopoulos ◽  
Georgios Giannakoulas ◽  
Michael A. Gatzoulis ◽  
...  
Keyword(s):  
Tetralogy Of Fallot ◽  
Pulmonary Trunk ◽  
Clinical Implications ◽  
Structural Abnormalities

GIS-analysis of the power grid sustainability to climatic loads

2019 ◽  
Vol 943 (1) ◽  
pp. 127-135
Author(s):  
B.A. Novakovskiy ◽  
P.E. Kargashin ◽  
A.M. Karpachevskiy
Keyword(s):  
Energy Supply ◽  
Climate Modeling ◽  
Power Grids ◽  
Electrical Networks ◽  
End User ◽  
Gis Modeling ◽  
Comprehensive Method ◽  
Combined Use ◽  
Power Centers ◽  
The Stability

This paper presents a comprehensive method of GIS-modeling and mapping the sustainability of electrical networks to climatic affects (including wind and sleet loads) on the example of the southwestern part of the Krasnodar region. We have proposed a number of improvements in the part of climate modeling (the use of morphometric indicators, spatially weighted regression) on the example of maximum sleet loads during 25 years period. We have also suggested an original approach to the assessment of structural sustainability of power grids. It provides the stability of energy supply to the end user due to the availability of alternative options for connecting to the power centers. Structural stability assessment is carried out on the basis of network modeling and acts as an indicator of the network parts which are the most vulnerable to natural disasters. The combined use of climate and network model allows justifying the strategy of the energy systemdevelopment by increasing the reliability of energy supply to the end user.

Ultrastructure of Giant Mitochondria and Their Inclusions in Schwann Cells of Bovine Splenic Nerve

1974 ◽  
Vol 32 ◽  
pp. 194-195
Author(s):  
Å. Thureson-Klein
Keyword(s):  
Schwann Cells ◽  
Cell Organelles ◽  
Giant Mitochondria ◽  
Matrix Density ◽  
Physiological Conditions ◽  
Unmyelinated Axons ◽  
Internal Structures ◽  
Structural Abnormalities ◽  
Cytotoxic Compounds ◽  
Cell Components

Giant mitochondria of various shapes and with different internal structures and matrix density have been observed in a great number of tissues including nerves. In most instances, the presence of giant mitochondria has been associated with a known disease or with abnormal physiological conditions such as anoxia or exposure to cytotoxic compounds. In these cases degenerative changes occurred in other cell organelles and, therefore the giant mitochondria also were believed to be induced structural abnormalities.Schwann cells ensheating unmyelinated axons of bovine splenic nerve regularly contain giant mitochondria in addition to the conventional smaller type (Fig. 1). These nerves come from healthy inspected animals presumed not to have been exposed to noxious agents. As there are no drastic changes in the small mitochondria and because other cell components also appear reasonably well preserved, it is believed that the giant mitochondria are normally present jin vivo and have not formed as a post-mortem artifact.

Mitochondrial Changes in Choline-Deficient Rat Myocardium

1968 ◽  
Vol 26 ◽  
pp. 112-113
Author(s):  
F. G. Zaki
Keyword(s):  
Muscle Fibers ◽  
Liver Mitochondria ◽  
Ultrastructural Changes ◽  
Choline Deficiency ◽  
Nutritional Disorder ◽  
Low Protein ◽  
Structural Abnormalities ◽  
Cross Striation ◽  
Pericardial Edema ◽  
Myocardial Lesions

Choline-deficiency was induced in Holtzman young rats of both sexes by feeding them a high fat - low protein diet.Preliminary studies of the ultrastructural changes in the myocardium of these animals have been recently reported from this laboratory. Myocardial lesions first appeared in the form of intraventricular mural thrombi, loss of cross striation of muscle fibers and focal necrosis of muscle cells associated with interstitial myocarditis. Prolonged choline-deficiency induced cardiomegaly associated with pericardial edema.During the early phase of this nutritional disorder, heart mitochondria - despite of not showing any swelling similar to that usually encountered in liver mitochondria of the same animal - ware the most ubiquitous site of marked structural abnormalities. Early changes in mitochondria appeared as vacuolation, disorganization, disruption and loss of cristae. Degenerating mitochondria were often seen quite enlarged and their matrix was replaced by whorls of myelin figures resembling lysosomal structures especially where muscle fibers were undergoing necrosis. In some areas, mitochondria appeared to be unusually clumped together where some contained membranelined vacuoles and others enclosed dense bodies and granular inclusions.

Sign in / Sign up

Export Citation Format

Share Document