Fast Segmentation of the Left Atrial Appendage in 3-D Transesophageal Echocardiographic 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.

Stroke risk evaluation for patients with atrial fibrillation: Insights from left atrial appendage

Left atrial appendage (LAA) is believed to be a common site of thrombus formation in patients with atrial fibrillation (AF). However, the commonly-applied stroke risk stratification model (such as. CHA2DS2-VASc score) does not include any structural or hemodynamic features of LAA. Recent studies have suggested that it is important to incorporate LAA geometrical and hemodynamic features to evaluate the risk of thrombus formation in LAA, which may better delineate the AF patients for anticoagulant administration and prevent strokes. This review focuses on the LAA-related factors that may be associated with thrombus formation and cardioembolic events.

Assessment of LAA Strain and Thrombus Mobility and Its Impact on Thrombus Resolution-Added-Value of a Novel Echocardiographic Thrombus Tracking Method

PURPOSE

The mobility of left atrial appendage (LAA) thrombi and changes hereof under anticoagulation may serve as a marker of both risk of embolism and efficacy of treatment. In this study, we sought to evaluate thrombus mobility and hypothesized that LAA dynamics and thrombus mobility could serve as a baseline marker of thrombus dissolvability.

METHODS

Patients with two-dimensional transesophageal echocardiographic images of the LAA, and with evidence of LAA thrombus were included in this study. Using a speckle tracking algorithm, functional information from the LAA and thrombi of different patients was computed. While the LAA motion was quantified through the longitudinal strain, thrombus mobility was evaluated using a novel method by directly tracking the thrombus, isolated from the global cardiac motion. Baseline characteristics and echocardiographic parameters were compared between responders (thrombus resolution) and non-responders (thrombus persistence) to anticoagulation.

RESULTS

We included 35 patients with atrial fibrillation with evidence of LAA thrombi. Patients had a mean age of 72.9 ± 14.1 years, exhibited a high risk for thromboembolism (CHA2DS2-VASc-Score 4.1 ± 1.5) and had moderately reduced LVEF (41.7 ± 14.4%) and signs of diastolic dysfunction (E/E' = 19.7 ± 8.5). While anticoagulation was initiated in all patients, resolution was achieved in 51.4% of patients. Significantly higher LAA peak strain (- 3.0 ± 1.3 vs. - 1.6 ± 1.5%, p < 0.01) and thrombus mobility (0.33 ± 0.13 mm vs. 0.18 ± 0.08 mm, p < 0.01) were observed in patients in whom thrombi resolved (i.e. responders against non-responders). Receiver operating characteristic (ROC) analysis revealed a high discriminatory ability for thrombus mobility with regards to thrombus resolution (AUC 0.89).

CONCLUSION

Isolated tracking of thrombus mobility from echocardiographic images is feasible. In patients with LAA thrombus, higher thrombus mobility appeared to be associated with thrombus resolution. Future studies should be conducted to evaluate the role of the described technique to predict LAA thrombus resolution or persistence.

Analysis of the Mechanism of Breast Metastasis Based on Image Recognition and Ultrasound Diagnosis

Breast cancer is one of the cancers with the highest incidence among women. In the late stage, cancer cells may metastasize to a distance, causing multiple organ diseases, threatening the lives of patients. The detection of lymph node metastasis based on pathological images is a key indicator for the diagnosis and staging of breast cancer, and correct staging decisions are the prerequisite and basis for targeted treatment. At present, the detection of lymph node metastasis mainly relies on manual screening by pathologists, which is time-consuming and labor-intensive, and the diagnosis results are variable and subjective. The automatic staging method based on the panoramic image calculation of the sentinel lymph node of the breast proposed in this paper can provide a set of standardized, high-accuracy, and repeatable objective diagnosis results. However, it is very difficult to automatically detect and locate cancer metastasis areas in highly complex panoramic images of lymph nodes. This paper proposes a novel deep network training strategy based on the sliding window to train an automatic localization model of cancer metastasis area. The training strategy first trains the initial convolutional network in a small amount of data, extracts false-positive and false-negative image blocks, and uses manual screening combined with automatic network screening to reclassify the false-positive blocks to improve the class of negative categories. Using mammography, ultrasound, MRI, and 18F-FDG PET-CT examinations, the detection rate and diagnostic accuracy of primary cancers in the breast of patients with axillary lymph node metastasis as the first diagnosis were obtained. The detection rate and diagnostic accuracy of breast MRI for primary cancers in the breast are much higher than those of X-ray, ultrasound, and 18F-FDG PET-CT (all P values <0.001). Mammography, ultrasound, and PET-CT examinations showed no difference in the detection rate and diagnostic accuracy of primary cancers in the breast of patients with axillary lymph node metastasis as the first diagnosis. Breast MRI should be used as a routine examination for patients with axillary lymph node metastasis as the first diagnosis. The primary breast cancer in the first diagnosed patients with axillary lymph node metastasis is often presented as localized asymmetric compactness or calcification on X-ray; it often appears as small focal mass lesions and ductal lesions without three-dimensional space-occupying effect on ultrasound.

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.

Big data and new information technology: what cardiologists need to know

Technological progress in medicine is constantly garnering pace, requiring that physicians constantly update their knowledge. The new wave of technologies breaking through into clinical practice includes the following: a) mHealth, which allows constant monitoring of biological parameters, anytime, anyplace, of hundreds of patients at the same time; b) artificial intelligence, which, powered by new deep learning techniques, are starting to beat human experts at their own game: diagnosis by imaging or electrocardiography; c) 3-dimensional printing, which may lead to patient-specific prostheses; d) systems medicine, which has arisen from big data, and which will open the way to personalized medicine by bringing together genetic, epigenetic, environmental, clinical and social data into complex integral mathematical models to design highly personalized therapies. This state-of-the-art review aims to summarize in a single document the most recent and most important technological trends that are being applied to cardiology, and to provide an overall view that will allow readers to discern at a glance the direction of cardiology in the next few years.

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

Left atrial appendage (LAA) occlusion is used to reduce the risk of thromboembolism in patients with nonvalvular atrial fibrillation by obstructing the LAA through a percutaneously delivered device. Nonetheless, correct device sizing is complex, requiring the manual estimation of different measurements in preprocedural/periprocedural images, which is tedious and time-consuming and with high interobserver and intraobserver variability. In this paper, a semiautomatic solution to estimate the required relevant clinical measurements is described. This solution starts with the 3-D segmentation of the LAA in 3-D transesophageal echocardiographic images, using a constant blind-ended model initialized through a manually defined spline. Then, the segmented LAA surface is aligned with a set of templates, i.e., 3-D surfaces plus relevant measurement planes (manually defined by one observer), transferring the latter to the unknown situation. Specifically, the alignment is performed in three consecutive steps, namely: 1) rigid alignment using the LAA clipping plane position; 2) orientation compensation using the circumflex artery location; and 3) anatomical refinement through a weighted iterative closest point algorithm. The novel solution was evaluated in a clinical database with 20 volumetric TEE images. Two experiments were set up to assess: 1) the sensitivity of the model's parameters and 2) the accuracy of the proposed solution for the estimation of the clinical measurements. Measurement levels manually identified by two observers were used as ground truth. The proposed solution obtained results comparable to the interobserver variability, presenting narrower limits of agreement for all measurements. Moreover, this solution proved to be fast, taking nearly 40 s (manual analysis took 3 min) to estimate the relevant measurements while being robust to the variation of the model's parameters. Overall, the proposed solution showed its potential for fast and robust estimation of the clinical measurements for occluding device selection, proving its added value for clinical practice.