Semiautomatic Estimation of Device Size for Left Atrial Appendage Occlusion in 3-D TEE Images

Deep learning networks in the segmentation of the left atrial appendage in 2D ultrasound: A comparative analysis

Left atrial appendage (LAA) is the major source of thromboembolism in patients with non-valvular atrial fibrillation. Currently, LAA occlusion can be offered as a treatment for these patients, obstructing the LAA through a percutaneously delivered device. Nevertheless, correct device sizing is a complex task, requiring manual analysis of medical images. This approach is sub-optimal, time-demanding, and highly variable between experts. Different solutions were proposed to improve intervention planning, but, no efficient solution is available to 2D ultrasound, which is the most used imaging modality for intervention planning and guidance. In this work, we studied the performance of recently proposed deep learning methods when applied for the LAA segmentation in 2D ultrasound. For that, it was created a 2D ultrasound database. Then, the performance of different deep learning methods, namely Unet, UnetR, AttUnet, TransAttUnet was assessed. All networks were compared using seven metrics: i) Dice coefficient; ii) Accuracy iii) Recall; iv) Specificity; v) Precision; vi) Hausdorff distance and vii) Average distance error. Overall, the results demonstrate the efficiency of AttUnet and TransAttUnet with dice scores of 88.62% and 89.28%, and accuracy of 88.25% and 86.30%, respectively. The current results demonstrate the feasibility of deep learning methods for LAA segmentation in 2D ultrasound.Clinical relevance- Our results proved the clinical potential of deep neural networks for the LAA anatomical analysis.

Adversarial-based latent space alignment network for left atrial appendage segmentation in transesophageal echocardiography images

Left atrial appendage (LAA) is a leading cause of atrial fibrillation and thrombosis in cardiovascular disease. Clinicians can rely on LAA occlusion (LAAO) to effectively prevent and treat ischaemic strokes attributed to the LAA. The correct selection of the LAAO is one of the most critical stages in the successful surgical process, which relies on the quantification of the anatomical structure of the LAA for successful intervention in LAAO. In this paper, we propose an adversarial-based latent space alignment framework for LAA segmentation in transesophageal echocardiography (TEE) images by introducing prior knowledge from the label. The proposed method consists of an LAA segmentation network, a label reconstruction network, and a latent space alignment loss. To be specific, we first employ ConvNeXt as the backbone of the segmentation and reconstruction network to enhance the feature extraction capability of the encoder. The label reconstruction network then encodes the prior shape features from the LAA labels to the latent space. The latent space alignment loss consists of the adversarial-based alignment and the contrast learning losses. It can motivate the segmentation network to learn the prior shape features of the labels, thus improving the accuracy of LAA edge segmentation. The proposed method was evaluated on a TEE dataset including 1,783 images and the experimental results showed that the proposed method outperformed other state-of-the-art LAA segmentation methods with Dice coefficient, AUC, ACC, G-mean, and Kappa of 0.831, 0.917, 0.989, 0.911, and 0.825, respectively.

Comparative Analysis of Current Deep Learning Networks for Breast Lesion Segmentation in Ultrasound Images

Automatic lesion segmentation in breast ultrasound (BUS) images aids in the diagnosis of breast cancer, the most common type of cancer in women. Accurate lesion segmentation in ultrasound images is a challenging task due to speckle noise, artifacts, shadows, and lesion variability in size and shape. Recently, convolutional neural networks have demonstrated impressive results in medical image segmentation tasks. However, the lack of public benchmarks and a standardized evaluation method hampers the networks' performance comparison. This work presents a benchmark of seven state-of-the-art methods for the automatic breast lesion segmentation task. The methods were evaluated on a multi-center BUS dataset composed of three public datasets. Specifically, the U-Net, Dynamic U-Net, Semantic Segmentation Deep Residual Network with Variational Autoencoder (SegResNetVAE), U-Net Transformers, Residual Feedback Network, Multiscale Dual Attention-Based Network, and Global Guidance Network (GG-Net) architectures were evaluated. The training was performed with a combination of the cross-entropy and Dice loss functions and the overall performance of the networks was assessed using the Dice coefficient, Jaccard index, accuracy, recall, specificity, and precision. Despite all networks having obtained Dice scores superior to 75%, the GG-Net and SegResNetVAE architectures outperform the remaining methods, achieving 82.56% and 81.90%, respectively. Clinical Relevance- The results of this study allowed to prove the potential of deep neural networks to be used in clinical practice for breast lesion segmentation also suggesting the best model choices.

Automated MSCT Analysis for Planning Left Atrial Appendage Occlusion Using Artificial Intelligence

Background

The number of multislice computed tomography (MSCT) analyses performed for planning structural heart interventions is rapidly increasing. Further automation is required to save time, increase standardization, and reduce the learning curve.

Objective

The purpose of this study was to investigate the feasibility of a fully automated artificial intelligence (AI)-based MSCT analysis for planning structural heart interventions, focusing on left atrial appendage occlusion (LAAO) as the selected use case.

Methods

Different deep learning models were trained, validated, and tested using a cohort of 583 patients for which manually annotated data were available. These models were used independently or in combination to detect the anatomical ostium, the landing zone, the mitral valve annulus, and the fossa ovalis and to segment the left atrium (LA) and left atrial appendage (LAA). The accuracy of the models was evaluated through comparison with the manually annotated data.

Results

The automated analysis was performed on 25 randomly selected patients of the test cohort. The results were compared to the manually identified landmarks. The predicted segmentation of the LA(A) was similar to the manual segmentation (dice score of 0.94 ± 0.02). The difference between the automatically predicted and manually measured perimeter-based diameter was −0.8 ± 1.3 mm (anatomical ostium), −1.0 ± 1.5 mm (Amulet landing zone), and −0.1 ± 1.3 mm (Watchman FLX landing zone), which is similar to the operator variability on these measurements. Finally, the detected mitral valve annulus and fossa ovalis were close to the manual detection of these landmarks, as shown by the Hausdorff distance (3.9 ± 1.2 mm and 4.8 ± 1.8 mm, respectively). The average runtime of the complete workflow, including data pre- and postprocessing, was 57.5 ± 34.5 seconds.

Conclusions

A fast and accurate AI-based workflow is proposed to automatically analyze MSCT images for planning LAAO. The approach, which can be easily extended toward other structural heart interventions, may help to handle the rapidly increasing volumes of patients.

Feasibility and Accuracy of Automated Three-Dimensional Echocardiographic Analysis of Left Atrial Appendage for Transcatheter Closure

BACKGROUND

Procedural success of transcatheter left atrial appendage closure (LAAC) is dependent on correct device selection. Three-dimensional (3D) transesophageal echocardiography (TEE) is more accurate than the two-dimensional modality for evaluation of the complex anatomy of the left atrial appendage (LAA). However, 3D transesophageal echocardiographic analysis of the LAA is challenging and highly expertise dependent. The aim of this study was to evaluate the feasibility and accuracy of a novel software tool for automated 3D analysis of the LAA using 3D transesophageal echocardiographic data.

METHODS

Intraprocedural 3D transesophageal echocardiographic data from 158 patients who underwent LAAC were retrospectively analyzed using a novel automated LAA analysis software tool. On the basis of the 3D transesophageal echocardiographic data, the software semiautomatically segmented the 3D LAA structure, determined the device landing zone, and generated measurements of the landing zone dimensions and LAA length, allowing manual editing if necessary. The accuracy of LAA preimplantation anatomic measurement reproducibility and time for analysis of the automated software were compared against expert manual 3D analysis. The software feasibility to predict the optimal device size was directly compared with implanted models.

RESULTS

Automated 3D analysis of the LAA on 3D TEE was feasible in all patients. There was excellent agreement between automated and manual measurements of landing zone maximal diameter (bias, -0.32; limits of agreement, -3.56 to 2.92), area-derived mean diameter (bias, -0.24; limits of agreement, -3.12 to 2.64), and LAA depth (bias, 0.02; limits of agreement, -3.14 to 3.18). Automated 3D analysis, with manual editing if necessary, accurately identified the implanted device size in 90.5% of patients, outperforming two-dimensional TEE (68.9%; P < .01). The automated software showed results competitive against the manual analysis of 3D TEE, with higher intra- and interobserver reproducibility, and allowed quicker analysis (101.9 ± 9.3 vs 183.5 ± 42.7 sec, P < .001) compared with manual analysis.

CONCLUSIONS

Automated LAA analysis on the basis of 3D TEE is feasible and allows accurate, reproducible, and rapid device sizing decision for LAAC.