Cardiac remodelling in non-alcoholic fatty liver disease in the general population

BACKGROUND AND AIMS

Non-alcoholic fatty liver disease (NAFLD) is associated with increased risk for cardiovascular disease. Our study investigates the contribution of NAFLD to changes in cardiac structure and function in a general population.

METHODS

One thousand ninety-six adults (49.3% female) from the Study of Health in Pomerania underwent magnetic resonance imaging including cardiac and liver imaging. The presence of NAFLD by proton density fat fraction was related to left cardiac structure and function. Results were adjusted for clinical confounders using multivariable linear regression model.

RESULTS

The prevalence for NAFLD was 35.9%. In adjusted multivariable linear regression models, NAFLD was positively associated with higher left ventricular mass index (β = 0.95; 95% confidence interval (CI): 0.45; 1.45), left ventricular concentricity (β = 0.043; 95% CI: 0.031; 0.056), left ventricular end-diastolic wall thickness (β = 0.29; 95% CI: 0.20; 0.38), left atrial end-diastolic volume index (β = 0.67; 95% CI: 0.01; 1.32) and inversely associated with left ventricular end-diastolic volume index (β = -0.78; 95% CI: -1.51; -0.05). When stratified by sex, we only found significant positive associations of NAFLD with left ventricular mass index, left atrial end-diastolic volume index, left ventricular cardiac output and an inverse association with global longitudinal strain in women. In contrast, men had an inverse association with left ventricular end-diastolic volume index and left ventricular stroke volume. Higher liver fat content was stronger associated with higher left ventricular mass index, left ventricular concentricity and left ventricular end-diastolic wall thickness.

CONCLUSION

NAFLD is associated with cardiac remodelling in the general population showing sex specific patterns in cardiac structure and function.

Automated localization and segmentation of cervical lymph nodes on contrast-enhanced CT using a 3D foveal fully convolutional neural network

BACKGROUND

In the management of cancer patients, determination of TNM status is essential for treatment decision-making and therefore closely linked to clinical outcome and survival. Here, we developed a tool for automatic three-dimensional (3D) localization and segmentation of cervical lymph nodes (LNs) on contrast-enhanced computed tomography (CECT) examinations.

METHODS

In this IRB-approved retrospective single-center study, 187 CECT examinations of the head and neck region from patients with various primary diseases were collected from our local database, and 3656 LNs (19.5 ± 14.9 LNs/CECT, mean ± standard deviation) with a short-axis diameter (SAD) ≥ 5 mm were segmented manually by expert physicians. With these data, we trained an independent fully convolutional neural network based on 3D foveal patches. Testing was performed on 30 independent CECTs with 925 segmented LNs with an SAD ≥ 5 mm.

RESULTS

In total, 4,581 LNs were segmented in 217 CECTs. The model achieved an average localization rate (LR), i.e., percentage of localized LNs/CECT, of 78.0% in the validation dataset. In the test dataset, average LR was 81.1% with a mean Dice coefficient of 0.71. For enlarged LNs with a SAD ≥ 10 mm, LR was 96.2%. In the test dataset, the false-positive rate was 2.4 LNs/CECT.

CONCLUSIONS

Our trained AI model demonstrated a good overall performance in the consistent automatic localization and 3D segmentation of physiological and metastatic cervical LNs with a SAD ≥ 5 mm on CECTs. This could aid clinical localization and automatic 3D segmentation, which can benefit clinical care and radiomics research.

RELEVANCE STATEMENT

Our AI model is a time-saving tool for 3D segmentation of cervical lymph nodes on contrast-enhanced CT scans and serves as a solid base for N staging in clinical practice and further radiomics research.

KEY POINTS

• Determination of N status in TNM staging is essential for therapy planning in oncology. • Segmenting cervical lymph nodes manually is highly time-consuming in clinical practice. • Our model provides a robust, automated 3D segmentation of cervical lymph nodes. • It achieves a high accuracy for localization especially of enlarged lymph nodes. • These segmentations should assist clinical care and radiomics research.

Transfer-Learning Deep Radiomics and Hand-Crafted Radiomics for Classifying Lymph Nodes from Contrast-Enhanced Computed Tomography in Lung Cancer

OBJECTIVES

Positron emission tomography (PET) is currently considered the non-invasive reference standard for lymph node (N-)staging in lung cancer. However, not all patients can undergo this diagnostic procedure due to high costs, limited availability, and additional radiation exposure. The purpose of this study was to predict the PET result from traditional contrast-enhanced computed tomography (CT) and to test different feature extraction strategies.

METHODS

In this study, 100 lung cancer patients underwent a contrast-enhanced ¹⁸F-fluorodeoxyglucose (FDG) PET/CT scan between August 2012 and December 2019. We trained machine learning models to predict FDG uptake in the subsequent PET scan. Model inputs were composed of (i) traditional "hand-crafted" radiomics features from the segmented lymph nodes, (ii) deep features derived from a pretrained EfficientNet-CNN, and (iii) a hybrid approach combining (i) and (ii).

RESULTS

In total, 2734 lymph nodes [555 (20.3%) PET-positive] from 100 patients [49% female; mean age 65, SD: 14] with lung cancer (60% adenocarcinoma, 21% plate epithelial carcinoma, 8% small-cell lung cancer) were included in this study. The area under the receiver operating characteristic curve (AUC) ranged from 0.79 to 0.87, and the scaled Brier score (SBS) ranged from 16 to 36%. The random forest model (iii) yielded the best results [AUC 0.871 (0.865-0.878), SBS 35.8 (34.2-37.2)] and had significantly higher model performance than both approaches alone (AUC: p < 0.001, z = 8.8 and z = 22.4; SBS: p < 0.001, z = 11.4 and z = 26.6, against (i) and (ii), respectively).

CONCLUSION

Both traditional radiomics features and transfer-learning deep radiomics features provide relevant and complementary information for non-invasive N-staging in lung cancer.

Radiomics for the Prediction of Overall Survival in Patients with Bladder Cancer Prior to Radical Cystectomy

(1) Background: To evaluate radiomics features as well as a combined model with clinical parameters for predicting overall survival in patients with bladder cancer (BCa). (2) Methods: This retrospective study included 301 BCa patients who received radical cystectomy (RC) and pelvic lymphadenectomy. Radiomics features were extracted from the regions of the primary tumor and pelvic lymph nodes as well as the peritumoral regions in preoperative CT scans. Cross-validation was performed in the training cohort, and a Cox regression model with an elastic net penalty was trained using radiomics features and clinical parameters. The models were evaluated with the time-dependent area under the ROC curve (AUC), Brier score and calibration curves. (3) Results: The median follow-up time was 56 months (95% CI: 48−74 months). In the follow-up period from 1 to 7 years after RC, radiomics models achieved comparable predictive performance to validated clinical parameters with an integrated AUC of 0.771 (95% CI: 0.657−0.869) compared to an integrated AUC of 0.761 (95% CI: 0.617−0.874) for the prediction of overall survival (p = 0.98). A combined clinical and radiomics model stratified patients into high-risk and low-risk groups with significantly different overall survival (p < 0.001). (4) Conclusions: Radiomics features based on preoperative CT scans have prognostic value in predicting overall survival before RC. Therefore, radiomics may guide early clinical decision-making.

Value of cardiac magnetic resonance imaging derived spectral myocardial strain pattern for non-invasive diagnosis of myocarditis

Funding Acknowledgements

Type of funding sources: Public grant(s) – EU funding. Main funding source(s): European Society of Radiology European Institute for Biomedical Imaging Research

Background

Traditionally, cardiac function is quantified by measures of peak excursion, for example ejection fraction. However, myocardial strain estimation from cine- cardiac MRI allows quantification of cardiac motion over the whole heart cycle. We propose a spectral decomposition of the strain curves applying Discrete Fourier transformation (DFT).

Purpose

To evaluate a potential additive diagnostic value of spectral temporal strain curve quantification for non-invasive diagnosis of myocarditis using cardiac MRI.

Methods

In the single-center prospective study patients with suspected myocarditis underwent comprehensive cardiac MRI followed by biventricular endomyocardial biopsy (EMB) between 2012 and 2014. DFT was applied to myocardial strain curves extracted from cine-Images. As reference model, a L1- and L2-penalized logistic regression model using global native T1 time, T2 time and presence of late-gadolinium enhancement was trained to predict EMB results and compared to two models which additionally include three orders of DFT coefficients and ejection fraction, respectively. Predictive performance was evaluated in a tournament-leave-pair-out cross-validation approach with a bootstrap correction for testing of multiple hyperparameter configurations.

Results

Out of 100 patients (28 % female, median age 40 [IQR 32 to 56) years) with acute symptom-onset (&lt;30 days) 65 had pathologically proven myocarditis in EMB. The DFT model showed best discrimination (Area under the receiver-operating-curve [AUC] 0.72 [95% CI 52 to 87]). Addition of ejection fraction (AUC 0.60 [95% CI: 0.43 to 0.74]) did not increase AUC compared to the reference (AUC 0.60 [95% CI: 0.43 to 0.74]). Posterior distribution of the bootstrap-corrected AUC difference between DFT and reference model was gaussian (mean 12%, standard deviation 12%) with a posterior probability of 86%, that DFT has a greater AUC.

Conclusions

Discrimination of myocarditis from similar clinical presentations remains challenging. The results support incremental discriminatory value of DFT-decomposed myocardial strain for non-invasive diagnosis of myocarditis. Future research should address the value of the spectral decomposition of cardiac motion trajectories in larger samples and different disease entities.