scholarly journals Deep learning from dual‐energy information for whole‐heart segmentation in dual‐energy and single‐energy non‐contrast‐enhanced cardiac CT

2020 ◽  
Vol 47 (10) ◽  
pp. 5048-5060
Author(s):  
Steffen Bruns ◽  
Jelmer M. Wolterink ◽  
Richard A. P. Takx ◽  
Robbert W. Hamersvelt ◽  
Dominika Suchá ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cardiac Ct ◽  
Dual Energy ◽  
Contrast Enhanced ◽  
Whole Heart ◽  
Energy Information

scholarly journals Deep learning-based whole-heart segmentation in 4D contrast-enhanced cardiac CT

2021 ◽  
pp. 105191
Author(s):  
Steffen Bruns ◽  
Jelmer M. Wolterink ◽  
Thomas P.W. van den Boogert ◽  
Jurgen H. Runge ◽  
Berto J. Bouma ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cardiac Ct ◽  
Contrast Enhanced ◽  
Whole Heart

scholarly journals Self-navigated 3D whole-heart MRA for non-enhanced surveillance of thoracic aortic dilation: a comparison to CTA

2021 ◽  
Vol 22 (Supplement_1) ◽  
Author(s):  
P Poskaite ◽  
M Pamminger ◽  
C Kranewitter ◽  
C Kremser ◽  
M Reindl ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Image Quality ◽  
Aortic Aneurysm ◽  
Thoracic Aortic Aneurysm ◽  
Aortic Dilation ◽  
Subjective Image Quality ◽  
Contrast Enhanced ◽  
Whole Heart ◽  
Enhanced Computed Tomography ◽  
Contrast Enhanced Computed Tomography

Abstract Funding Acknowledgements Type of funding sources: None. Background The natural history of thoracic aortic aneurysm (TAA) is one of progressive expansion. Asymptomatic patients who do not meet criteria for repair require conservative management including ongoing aneurysm surveillance, mostly carried out by contrast-enhanced computed tomography angiography (CTA). Purpose To prospectively compare image quality and reliability of a prototype non-contrast, self-navigated 3D whole-heart magnetic resonance angiography (MRA) with contrast-enhanced computed tomography angiography (CTA) for sizing of thoracic aortic aneurysm (TAA). Methods Self-navigated 3D whole-heart 1.5 T MRA was performed in 20 patients (aged 67 ± 8.6 years, 75% male) for sizing of TAA; a subgroup of 18 (90%) patients underwent additional contrast-enhanced CTA on the same day. Subjective image quality was scored according to a 4-point Likert scale and ratings between observers were compared by Cohen’s Kappa statistics. Continuous MRA and CTA measurements were analyzed with regression and Bland-Altman analysis. Results Overall subjective image quality as rated by two observers was 1 [interquartile range (IQR) 1-2] for self-navigated MRA and 1.5 [IQR 1-2] for CTA (p = 0.717). For MRA a perfect inter-observer agreement was found for presence of artefacts and subjective image sharpness (κ=1). Subjective signal inhomogeneity correlated highly with objectively quantified inhomogeneity of the blood pool signal (r = 0.78-0.824, all p <0.0001). Maximum diameters of TAA as measured by self-navigated MRA and CTA showed excellent correlation (r = 0.997, p < 0.0001) without significant inter-method bias (bias -0.0278, lower and upper limit of agreement -0.74 and 0.68, p = 0.749). Inter- and intraobserver correlation of aortic aneurysm as measured by MRA was excellent (r = 0.963 and 0.967, respectively) without significant bias (all p ≤ 0.05). Conclusion Self-navigated 3D whole-heart MRA enables reliable contrast- and radiation free aortic dilation surveillance without significant difference to standardized CTA while providing predictable acquisition time and by offering excellent image quality. Abstract Figure.

scholarly journals Liver fibrosis staging by deep learning: a visual-based explanation of diagnostic decisions of the model

2021 ◽  
Author(s):  
Yunchao Yin ◽  
Derya Yakar ◽  
Rudi A. J. O. Dierckx ◽  
Kim B. Mouridsen ◽  
Thomas C. Kwee ◽  
...  
Keyword(s):  
Deep Learning ◽  
Liver Fibrosis ◽  
Liver Parenchyma ◽  
Ct Images ◽  
Fibrosis Stage ◽  
Contrast Enhanced Ct ◽  
Contrast Enhanced ◽  
Enhanced Ct ◽  
Liver Surface ◽  
Fibrosis Staging

Abstract Objectives Deep learning has been proven to be able to stage liver fibrosis based on contrast-enhanced CT images. However, until now, the algorithm is used as a black box and lacks transparency. This study aimed to provide a visual-based explanation of the diagnostic decisions made by deep learning. Methods The liver fibrosis staging network (LFS network) was developed at contrast-enhanced CT images in the portal venous phase in 252 patients with histologically proven liver fibrosis stage. To give a visual explanation of the diagnostic decisions made by the LFS network, Gradient-weighted Class Activation Mapping (Grad-cam) was used to produce location maps indicating where the LFS network focuses on when predicting liver fibrosis stage. Results The LFS network had areas under the receiver operating characteristic curve of 0.92, 0.89, and 0.88 for staging significant fibrosis (F2–F4), advanced fibrosis (F3–F4), and cirrhosis (F4), respectively, on the test set. The location maps indicated that the LFS network had more focus on the liver surface in patients without liver fibrosis (F0), while it focused more on the parenchyma of the liver and spleen in case of cirrhosis (F4). Conclusions Deep learning methods are able to exploit CT-based information from the liver surface, liver parenchyma, and extrahepatic information to predict liver fibrosis stage. Therefore, we suggest using the entire upper abdomen on CT images when developing deep learning–based liver fibrosis staging algorithms. Key Points • Deep learning algorithms can stage liver fibrosis using contrast-enhanced CT images, but the algorithm is still used as a black box and lacks transparency. • Location maps produced by Gradient-weighted Class Activation Mapping can indicate the focus of the liver fibrosis staging network. • Deep learning methods use CT-based information from the liver surface, liver parenchyma, and extrahepatic information to predict liver fibrosis stage.

Sign in / Sign up

Export Citation Format

Share Document