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

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.

Download Full-text

Clinical Application of Non‐Contrast‐Enhanced Dixon Water‐Fat Separation Compressed SENSE Whole‐Heart Coronary MR Angiography at 3.0 T With and Without Nitroglycerin

Journal of Magnetic Resonance Imaging ◽

10.1002/jmri.27829 ◽

2021 ◽

Author(s):

Hongfei Lu ◽

Shihai Zhao ◽

Di Tian ◽

Shan Yang ◽

Jianying Ma ◽

...

Keyword(s):

Clinical Application ◽

Mr Angiography ◽

Contrast Enhanced ◽

3.0 T ◽

Whole Heart ◽

Coronary Mr Angiography

Download Full-text

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

European Radiology ◽

10.1007/s00330-021-08046-x ◽

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.

Download Full-text

Region-of-Interest-Based Cardiac Image Segmentation with Deep Learning

Applied Sciences ◽

10.3390/app11041965 ◽

2021 ◽

Vol 11 (4) ◽

pp. 1965

Author(s):

Raul-Ronald Galea ◽

Laura Diosan ◽

Anca Andreica ◽

Loredana Popa ◽

Simona Manole ◽

...

Keyword(s):

Image Segmentation ◽

Deep Learning ◽

Diagnostic System ◽

Region Of Interest ◽

General Purpose ◽

Medical Image Segmentation ◽

Dice Similarity Coefficient ◽

Learning Methods ◽

Study Results ◽

Whole Heart

Despite the promising results obtained by deep learning methods in the field of medical image segmentation, lack of sufficient data always hinders performance to a certain degree. In this work, we explore the feasibility of applying deep learning methods on a pilot dataset. We present a simple and practical approach to perform segmentation in a 2D, slice-by-slice manner, based on region of interest (ROI) localization, applying an optimized training regime to improve segmentation performance from regions of interest. We start from two popular segmentation networks, the preferred model for medical segmentation, U-Net, and a general-purpose model, DeepLabV3+. Furthermore, we show that ensembling of these two fundamentally different architectures brings constant benefits by testing our approach on two different datasets, the publicly available ACDC challenge, and the imATFIB dataset from our in-house conducted clinical study. Results on the imATFIB dataset show that the proposed approach performs well with the provided training volumes, achieving an average Dice Similarity Coefficient of the whole heart of 89.89% on the validation set. Moreover, our algorithm achieved a mean Dice value of 91.87% on the ACDC validation, being comparable to the second best-performing approach on the challenge. Our approach provides an opportunity to serve as a building block of a computer-aided diagnostic system in a clinical setting.

Download Full-text

Assessing the Role of Pericardial Fat as a Biomarker Connected to Coronary Calcification—A Deep Learning Based Approach Using Fully Automated Body Composition Analysis

Journal of Clinical Medicine ◽

10.3390/jcm10020356 ◽

2021 ◽

Vol 10 (2) ◽

pp. 356

Author(s):

Lennard Kroll ◽

Kai Nassenstein ◽

Markus Jochims ◽

Sven Koitka ◽

Felix Nensa

Keyword(s):

Adipose Tissue ◽

Deep Learning ◽

Coronary Artery ◽

Cardiac Ct ◽

Coronary Calcification ◽

Risk Scores ◽

Agatston Score ◽

Composition Analysis ◽

Significance Level ◽

Tissue Quantification

(1) Background: Epi- and Paracardial Adipose Tissue (EAT, PAT) have been spotlighted as important biomarkers in cardiological assessment in recent years. Since biomarker quantification is an increasingly important method for clinical use, we wanted to examine fully automated EAT and PAT quantification for possible use in cardiovascular risk stratification. (2) Methods: 966 patients with intermediate Framingham risk scores for Coronary Artery Disease referred for coronary calcium scans were included in clinical routine retrospectively. The Coronary Artery Calcium Score (CACS) was extracted and tissue quantification was performed by a deep learning network. (3) Results: The Computed Tomography (CT) segmentations predicted by the network indicated no significant correlation between EAT volume and EAT radiodensity when compared to Agatston score (r = 0.18, r = −0.09). CACS 0 category patients showed significantly lower levels of total EAT and PAT volumes and higher EAT and PAT densities than CACS 1–99 category patients (p < 0.01). Notably, this difference did not reach significance regarding EAT attenuation in male patients. Women older than 50 years, thus more likely to be postmenopausal, were shown to be at higher risk of coronary calcification (p < 0.01, OR = 4.59). CACS 1–99 vs. CACS ≥100 category patients remained below significance level (EAT volume: p = 0.087, EAT attenuation: p = 0.98). (4) Conclusions: Our study proves the feasibility of a fully automated adipose tissue analysis in clinical cardiac CT and confirms in a large clinical cohort that volume and attenuation of EAT and PAT are not correlated with CACS. Broadly available deep learning based rapid and reliable tissue quantification should thus be discussed as a method to assess this biomarker as a supplementary risk predictor in cardiac CT.

Download Full-text