Rapid automatic segmentation of abnormal tissue in late gadolinium enhancement cardiovascular magnetic resonance images for improved management of long-standing persistent atrial fibrillation

Assessment of left atrial fibrosis progression in canines following rapid ventricular pacing using 3D late gadolinium enhanced CMR images

Background

Atrial fibrillation (AF) is associated with extracellular matrix (ECM) remodelling and often coexists with myocardial fibrosis (MF); however, the causality of these conditions is not well established.

Objective

We aim to corroborate AF to MF causality by quantifying left atrial (LA) fibrosis in cardiac magnetic resonance (CMR) images after persistent rapid ventricular pacing and subsequent AF using a canine model and histopathological validation.

Methods

Twelve canines (9 experimental, 3 control) underwent baseline 3D LGE-CMR imaging at 3T followed by insertion of a pacing device and 5 weeks of rapid ventricular pacing to induce AF (experimental) or no pacing (control). Following the 5 weeks, pacing devices were removed to permit CMR imaging followed by excision of the hearts and histopathological imaging. LA myocardial segmentation was performed manually at baseline and post-pacing to permit volumetric %MF quantification using the image intensity ratio (IIR) technique, wherein fibrosis was defined as pixels > mean LA myocardium intensity + 2SD.

Results

Volumetric %MF increased by an average of 2.11 ± 0.88% post-pacing in 7 of 9 experimental dogs. While there was a significant difference between paired %MF measurements from baseline to post-pacing in experimental dogs (P = 0.019), there was no significant change in control dogs (P = 0.019 and P = 0.5, Wilcoxon signed rank tests). The median %MF for paced animals was significantly greater than that of non-paced dogs at the 5-week post-insertion time point (P = 0.009, Mann Whitney U test). Histopathological imaging yielded an average %MF of 19.42 ± 4.80% (mean ± SD) for paced dogs compared to 1.85% in one control dog.

Conclusion

Persistent rapid ventricular pacing and subsequent AF leads to an increase in LA fibrosis volumes measured by the IIR technique; however, quantification is limited by inherent image acquisition parameters and observer variability.

A fully automated left atrium segmentation approach from late gadolinium enhanced magnetic resonance imaging based on a convolutional neural network

Background

Several studies suggest that the evaluation of left atrial (LA) fibrosis is a relevant information for the assessment of the appropriate strategy in catheter ablation in atrial fibrillation (AF). Late gadolinium enhanced (LGE) cardiac magnetic resonance imaging (MRI) is a non-invasive technique, which might be employed for the non-invasive quantification of LA myocardial fibrotic tissue in patients with AF. Nowadays, the analysis of LGE MRI relies on manual tracing of LA boundaries and this procedure is time-consuming and prone to high inter-observer variability given the different degrees of observers' experience, LA wall thickness and data resolution. Therefore, an automated segmentation approach of the atrial cavity for the quantification of scar tissue would be highly desirable.

Methods

This study focuses on the design of a fully automated LGE MRI segmentation pipeline which includes a convolutional neural network (CNN) based on the successful architecture U-Net. The CNN was trained, validated and tested end-to-end with the data available from the Statistical Atlases and Computational Modelling of the Heart 2018 Atrial Segmentation Challenge (100 cardiac data). Two different approaches were tested: using both stacks of 2-D axial slices and using 3-D data (with the appropriate changes in the baseline architecture). In the latter approach, thanks to the 3-D convolution operator, all the information underlying 3-D data can be exploited. Once the training was completed using 80 cardiac data, a post-processing step was applied on 20 predicted segmentations belonging to the test set.

Results

By applying the 2-D and 3-D approaches, average Dice coefficient and mean Hausdorff distances were 0.896, 0.914, and 8.98 mm, 8.34 mm, respectively. Volumes of the anatomical LA meshes from the automated analysis were highly correlated with the volumes from ground truth [2-D: r=0.978, y=0.94x+0.07, bias=3.5 ml (5.6%), SD=5.3 mL (8.5%); 3-D: r=0.982, y=0.92x+2.9, bias=2.1 mL (3.5%), SD=5.2 mL (8.4%)].

Conclusions

These results suggest the proposed approach is feasible and provides accurate results. Despite the increase of the number of trainable parameters, the proposed 3-D CNN learns better features leading to higher performance, feasible for a real clinical application.

Bi-atrial fibrosis detected using three-dimensional late gadolinium enhancement magnetic resonance imaging in a patient with cardiac sarcoidosis

Presented is the case of a 62-year old male with a history of sarcoidosis and sinus node dysfunction, who underwent late gadolinium enhancement magnetic resonance imaging, which demonstrated left ventricular hyperenhancement and bi-atrial fibrosis.

Catheter Ablation versus Thoracoscopic Surgical Ablation in Long Standing Persistent Atrial Fibrillation (CASA-AF): study protocol for a randomised controlled trial

BACKGROUND

Atrial fibrillation is the commonest arrhythmia which raises the risk of heart failure, thromboembolic stroke, morbidity and death. Pharmacological treatments of this condition are focused on heart rate control, rhythm control and reduction in risk of stroke. Selective ablation of cardiac tissues resulting in isolation of areas causing atrial fibrillation is another treatment strategy which can be delivered by two minimally invasive interventions: percutaneous catheter ablation and thoracoscopic surgical ablation. The main purpose of this trial is to compare the effectiveness and safety of these two interventions.

METHODS/DESIGN

Catheter Ablation versus Thoracoscopic Surgical Ablation in Long Standing Persistent Atrial Fibrillation (CASA-AF) is a prospective, multi-centre, randomised controlled trial within three NHS tertiary cardiovascular centres specialising in treatment of atrial fibrillation. Eligible adults (n = 120) with symptomatic, long-standing, persistent atrial fibrillation will be randomly allocated to either catheter ablation or thoracoscopic ablation in a 1:1 ratio. Pre-determined lesion sets will be delivered in each treatment arm with confirmation of appropriate conduction block. All patients will have an implantable loop recorder (ILR) inserted subcutaneously immediately following ablation to enable continuous heart rhythm monitoring for at least 12 months. The devices will be programmed to detect episodes of atrial fibrillation and atrial tachycardia ≥ 30 s in duration. The patients will be followed for 12 months, completing appropriate clinical assessments and questionnaires every 3 months. The ILR data will be wirelessly transmitted daily and evaluated every month for the duration of the follow-up. The primary endpoint in the study is freedom from atrial fibrillation and atrial tachycardia at the end of the follow-up period.

DISCUSSION

The CASA-AF Trial is a National Institute for Health Research-funded study that will provide first-class evidence on the comparative efficacy, safety and cost-effectiveness of thoracoscopic surgical ablation and conventional percutaneous catheter ablation for long-standing persistent atrial fibrillation. In addition, the results of the trial will provide information on the effects on patients' quality of life.

TRIAL REGISTRATION

ISRCTN Registry, ISRCTN18250790 . Registered on 24 April 2015.

Virtual medicine: Utilization of the advanced cardiac imaging patient avatar for procedural planning and facilitation

Advances in imaging technology have led to a paradigm shift from planning of cardiovascular procedures and surgeries requiring the actual patient in a "brick and mortar" hospital to utilization of the digitalized patient in the virtual hospital. Cardiovascular computed tomographic angiography (CCTA) and cardiovascular magnetic resonance (CMR) digitalized 3-D patient representation of individual patient anatomy and physiology serves as an avatar allowing for virtual delineation of the most optimal approaches to cardiovascular procedures and surgeries prior to actual hospitalization. Pre-hospitalization reconstruction and analysis of anatomy and pathophysiology previously only accessible during the actual procedure could potentially limit the intrinsic risks related to time in the operating room, cardiac procedural laboratory and overall hospital environment. Although applications are specific to areas of cardiovascular specialty focus, there are unifying themes related to the utilization of technologies. The virtual patient avatar computer can also be used for procedural planning, computational modeling of anatomy, simulation of predicted therapeutic result, printing of 3-D models, and augmentation of real time procedural performance. Examples of the above techniques are at various stages of development for application to the spectrum of cardiovascular disease processes, including percutaneous, surgical and hybrid minimally invasive interventions. A multidisciplinary approach within medicine and engineering is necessary for creation of robust algorithms for maximal utilization of the virtual patient avatar in the digital medical center. Utilization of the virtual advanced cardiac imaging patient avatar will play an important role in the virtual health care system. Although there has been a rapid proliferation of early data, advanced imaging applications require further assessment and validation of accuracy, reproducibility, standardization, safety, efficacy, quality, cost effectiveness, and overall value to medical care.

Multimodality Cardiac Imaging for the Assessment of Left Atrial Function and the Association With Atrial Arrhythmias

Several cardiac imaging modalities are able to visualize the left atrium (LA) and, therefore, allow for quantification of both structural and functional properties of this cardiac chamber. In echocardiography, only the maximal LA volume is included in the assessment of diastolic function at the current moment. Numerous studies, however, have shown that functional measures may be superior to the maximal LA volume in several aspects and to possess clinical value even in the absence of structural abnormalities. Such functional measures could prove particularly useful in the setting of predicting atrial fibrillation, which will be a point of focus in this review. Pivotal cardiac magnetic resonance imaging studies have revealed high correlation between LA fibrosis and risk of atrial fibrillation recurrence after catheter ablation, and subsequent multimodality imaging studies have uncovered an inverse relationship between LA reservoir function and degree of LA fibrosis. This has sparked an increased interest into the application of advanced imaging modalities, including both speckle tracking echocardiography and tissue tracking by cardiac magnetic resonance imaging. Even though increasing evidence has supported the use of functional measures and proven its superiority to the maximal LA volume, they have still not been adopted in clinical guidelines. The reason for this discrepancy may rely on the fact that there is little to no agreement on how to technically perform deformation analysis of the LA. Such technical considerations, limitations, and alternate imaging prospects will be addressed in this review.

A Combined Random Forests and Active Contour Model Approach for Fully Automatic Segmentation of the Left Atrium in Volumetric MRI

Segmentation of the left atrium (LA) from cardiac magnetic resonance imaging (MRI) datasets is of great importance for image guided atrial fibrillation ablation, LA fibrosis quantification, and cardiac biophysical modelling. However, automated LA segmentation from cardiac MRI is challenging due to limited image resolution, considerable variability in anatomical structures across subjects, and dynamic motion of the heart. In this work, we propose a combined random forests (RFs) and active contour model (ACM) approach for fully automatic segmentation of the LA from cardiac volumetric MRI. Specifically, we employ the RFs within an autocontext scheme to effectively integrate contextual and appearance information from multisource images together for LA shape inferring. The inferred shape is then incorporated into a volume-scalable ACM for further improving the segmentation accuracy. We validated the proposed method on the cardiac volumetric MRI datasets from the STACOM 2013 and HVSMR 2016 databases and showed that it outperforms other latest automated LA segmentation methods. Validation metrics, average Dice coefficient (DC) and average surface-to-surface distance (S2S), were computed as 0.9227 ± 0.0598 and 1.14 ± 1.205 mm, versus those of 0.6222-0.878 and 1.34-8.72 mm, obtained by other methods, respectively.