Classification of Left Atrial Appendage Morphology Using Deep Learning

2020 ◽  
Author(s):  
Mikayle A. Holm ◽  
Alex Deakyne ◽  
Erik Gaasedelen ◽  
Weston Upchurch ◽  
Paul A. Iaizzo
Keyword(s):  
Left Atrial ◽  
Left Atrial Appendage ◽  
Blood Clot ◽  
3D Models ◽  
Atrial Appendage ◽  
Blood Clots ◽  
Mri Scans ◽  
2D Images ◽  
Trained Network

Abstract Atrial fibrillation, a common cardiac arrhythmia, can lead to blood clots in the left atrial appendage (LAA) of the heart, increasing the risk of stroke. Understanding the LAA morphology can indicate the likelihood of a blood clot. Therefore, a classification convolutional neural network was implemented to predict the LAA morphology. Using 2D images of 3D models created from MRI scans of fixed human hearts and a pre-trained network, an 8.7% error rate was achieved. The network can be improved with more data or expanded to classify the LAA from the automatically segmented DICOM datasets and measure the LAA ostia.

scholarly journals Acute Device-Related Thrombus after Watchman Device Implant

2019 ◽  
Vol 2019 ◽  
pp. 1-4
Author(s):  
Muhammad Ajmal ◽  
Vijendra Swarup
Keyword(s):  
Left Atrial ◽  
Left Atrial Appendage ◽  
Blood Clot ◽  
Heart Rhythm ◽  
Bleeding Risk ◽  
Atrial Appendage ◽  
Acute Thrombosis ◽  
Increased Risk ◽  
Watchman Device ◽  
Laa Closure

Atrial fibrillation is characterized by irregularly irregular heart rhythm with an increased morbidity and mortality. It is associated with an increased risk of thromboembolism due to formation of blood clot in the left atrium. Most of these blood clots are formed in the left atrial appendage. The risk of blood clot formation is reduced with the use of anticoagulants. The patients who cannot take anticoagulants due to an increased bleeding risk can undergo percutaneous left atrial appendage (LAA) closure. A Watchman device is used for this purpose. LAA closure with the Watchman device is associated with some adverse effects, and one of them is device-related thrombus. Currently, there are no specific guidelines for the management of device-related thrombus. We present a case of Watchman device-related thrombus which developed 16 hours after the device placement. We will also discuss various options for the management of acute thrombosis.

scholarly journals The predictive value of a concise classification of left atrial appendage morphology to thrombosis in non‐valvular atrial fibrillation patients

2020 ◽  
Vol 43 (7) ◽  
pp. 789-795 ◽  
Author(s):  
Jionghong He ◽  
Zenan Fu ◽  
Long Yang ◽  
Wei Liu ◽  
Ye Tian ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Predictive Value ◽  
Left Atrial ◽  
Left Atrial Appendage ◽  
Atrial Appendage

Printed MDCT 3D models for prediction of left atrial appendage (LAA) occluder device size: a feasibility study

2017 ◽  
Vol 13 (9) ◽  
pp. e1076-e1079 ◽  
Author(s):  
Orly Goitein ◽  
Noam Fink ◽  
Victor Guetta ◽  
Roy Beinart ◽  
Yafim Brodov ◽  
...  
Keyword(s):  
Feasibility Study ◽  
Left Atrial ◽  
Left Atrial Appendage ◽  
3D Models ◽  
Atrial Appendage ◽  
Occluder Device ◽  
Device Size

scholarly journals The Value of 3D Printing Models of Left Atrial Appendage Using Real-Time 3D Transesophageal Echocardiographic Data in Left Atrial Appendage Occlusion: Applications toward an Era of Truly Personalized Medicine

Cardiology ◽  
2016 ◽  
Vol 135 (4) ◽  
pp. 255-261 ◽  
Author(s):  
Peng Liu ◽  
Rijing Liu ◽  
Yan Zhang ◽  
Yingfeng Liu ◽  
Xiaoming Tang ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
3D Printing ◽  
Real Time ◽  
Left Atrial ◽  
Left Atrial Appendage ◽  
3D Models ◽  
Atrial Appendage ◽  
Patient Specific ◽  
The Real ◽  
Echocardiographic Image

Aims and Objectives: The objective of this study was to assess the clinical feasibility of generating 3D printing models of left atrial appendage (LAA) using real-time 3D transesophageal echocardiogram (TEE) data for preoperative reference of LAA occlusion. Background: Percutaneous LAA occlusion can effectively prevent patients with atrial fibrillation from stroke. However, the anatomical structure of LAA is so complicated that adequate information of its structure is essential for successful LAA occlusion. Emerging 3D printing technology has the demonstrated potential to structure more accurately than conventional imaging modalities by creating tangible patient-specific models. Typically, 3D printing data sets are acquired from CT and MRI, which may involve intravenous contrast, sedation, and ionizing radiation. It has been reported that 3D models of LAA were successfully created by the data acquired from CT. However, 3D printing of the LAA using real-time 3D TEE data has not yet been explored. Methods: Acquisition of 3D transesophageal echocardiographic data from 8 patients with atrial fibrillation was performed using the Philips EPIQ7 ultrasound system. Raw echocardiographic image data were opened in Philips QLAB and converted to ‘Cartesian DICOM' format and imported into Mimics® software to create 3D models of LAA, which were printed using a rubber-like material. The printed 3D models were then used for preoperative reference and procedural simulation in LAA occlusion. Results: We successfully printed LAAs of 8 patients. Each LAA costs approximately CNY 800-1,000 and the total process takes 16-17 h. Seven of the 8 Watchman devices predicted by preprocedural 2D TEE images were of the same sizes as those placed in the real operation. Interestingly, 3D printing models were highly reflective of the shape and size of LAAs, and all device sizes predicted by the 3D printing model were fully consistent with those placed in the real operation. Also, the 3D printed model could predict operating difficulty and the presence of a peridevice leak. Conclusions: 3D printing of the LAA using real-time 3D transesophageal echocardiographic data has a perfect and rapid application in LAA occlusion to assist with physician planning and decision making.

Abstract 126: A Simple Classification of the Left Atrial Appendage Morphology Based on Stroke Risk: The LAA H/L Classification System

Stroke ◽  
2019 ◽  
Vol 50 (Suppl_1) ◽  
Author(s):  
Shadi Yaghi ◽  
Andrew Chang ◽  
Hooman Kamel ◽  
Karen Furie ◽  
Mitchell S Elkind ◽  
...  
Keyword(s):  
Classification System ◽  
Left Atrial ◽  
Stroke Risk ◽  
Left Atrial Appendage ◽  
Atrial Appendage ◽  
Simple Classification

Abstract 1869: Real-Time Three-Dimensional Echocardiography of the Left Atrial Appendage: Initial Experience in Humans with Validation by 64-Slice Computed Tomography

Circulation ◽  
2007 ◽  
Vol 116 (suppl_16) ◽  
Author(s):  
Sanjiv J Shah ◽  
Dianna M Bardo ◽  
Lynn Weinert ◽  
Lissa Sugeng ◽  
Bradley P Knight ◽  
...  
Keyword(s):  
Real Time ◽  
Left Atrial ◽  
Left Atrial Appendage ◽  
Three Dimensional ◽  
Frame Rate ◽  
Atrial Appendage ◽  
Orifice Diameter ◽  
Orifice Area ◽  
2D And 3D ◽  
2D Images

Background: Real-time left atrial appendage (LAA) quantification is increasingly important with the advent of LAA occluder devices for stroke prevention. However, accurate quantification is difficult using 2D-TEE because measurements must be made in multiple views, and LAA orifice cannot be viewed directly. We aimed to determine the accuracy of LAA geometry measured by a new matrix-array (mTEE) probe which can provide unique real-time 3D (RT3D) views of the LAA. Methods: 29 consecutive patients (age 53±18) referred for 2D-TEE underwent additional RT3D-mTEE (Philips ie33; frame rate 8–10/s). The LAA orifice diameter and LAA depth were measured from biplane 2D images, and 2D LAA orifice area was calculated as an ellipse. LAA orifice area and LAA depth were measured in 3D and correlated to 2D. In 8 patients who had cardiac CT available, 2D- and 3D-TEE LAA measurements were correlated with 64-slice CT. All LAA measurements were made at atrial end-diastole. Results: All 29 patients underwent RT3D-mTEE without complication. The LAA was well-visualized in 3D in 26/29 (90%). Because the shape of the LAA orifice in 3D was an ellipsoid with an irregular contour, 2D images resulted in underestimation of area vs. 3D (3.0±1.2 vs. 4.2±2.2 cm 2 ). LAA depth by 2D and 3D correlated well (3.7±0.7 vs. 3.4±0.7; r=0.72, p=0.001). CT LAA orifice area correlated well with 3D-TEE (r=0.98, p<0.0001) but not with 2D-TEE (p=0.78). Conclusions: RT3D-TEE for analysis of LAA geometry is safe and feasible and appears to be more accurate than 2D-TEE. RT3D-TEE provides unique visualization of the LAA orifice in real-time, making it the ideal tool for intra-procedural sizing and placement of LAA occluder devices.

P1002Echocardiographic assessment of optimal device position after percutaneous left atrial appendage occlusion - introduction of a novel classification and its impact on outcome

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
V O Vij ◽  
B Al-Kassou ◽  
D Nelles ◽  
M Stuhr ◽  
R Schueler ◽  
...  
Keyword(s):  
Left Atrial ◽  
Left Atrial Appendage ◽  
Transoesophageal Echocardiography ◽  
Atrial Appendage ◽  
The Novel ◽  
Left Atrial Appendage Occlusion ◽  
Implantation Depth ◽  
The Impact

Abstract Background Left atrial appendage occlusion (LAAo) is an established therapy in patients with atrial fibrillation. However, criteria regarding optimal device position are not well defined making comparability of procedural results virtually impossible. We therefore sought to a) introduce a classification describing optimal vs. suboptimal device-position by assessing predefined parameters in transoesophageal echocardiography (TEE) and to b) analyze the impact of device-position on outcome in patients treated with different LAAo devices. Methods and results We retrospectively analyzed 120 patients who were treated by LAAo and had undergone follow-up TEEs after 3 or 6 months. Patients were at mean age: 76±8 years; female 40% and presented an increased CHADS-VASC- (4.6±1.4) and HAS-BLED-score (3.7±1). TEE-guidance was performed in all cases. In 62.5% (75/120) pacifier occluders (PO) (ACP/Amulet, Lambre, Ultraseal) were used, whereas 37.5% (45/120) were treated with non-pacifier occluders (NPO) (Watchman, Wavecrest, Occlutech). To assess device position, TEE images in a commissural view (60–90°) were analyzed and characterised by 1) implantation depth in the left atrial appendage, 2) peridevice flow (PF) and 3) the angle between occluder disc and pulmonal ridge (LUPV). For the purpose of this study, optimal device position was defined as a) ostial (LUPV length <10mm) or slightly subostial position (LUPV length ≤15mm, angle ≥100°) with b) the absence of major PF (>3mm). Overall, occluders were implanted at a depth of 12±7.8 mm with ostial positioning being achieved in 47.5% (57/120). Major PF was seen in 7.5% (9/120). NPOs were implanted deeper than POs (depth: 15.6±7.1 vs. 9.8±7.4 mm, p<0.01; ostial position: 31.1% vs. 57.3%, p<0.01) and were associated with a higher incidence of major PF (15.6% vs. 2.7%, p=0.01). Also, the depth/angle ratio was higher (i.e. “worse”) in NPOs (18.3±9 vs. 14.6±8, p<0.04). As a result, optimal device position was achieved in 48.3% (58/120) of all patients, with lower rates in NPOs than in POs (26.7% vs. 61.3%, p<0.01). Procedural aspects revealed slight differences in occluder size (optimal: 23.7±3.2 vs. suboptimal: 24.5±3.7 mm, p=0.3), need for repositioning (10.3% vs. 17.7%, p=0.25) and procedural duration (48±36 vs. 52±34 min, p=0.3). Of interest, device related thrombi (DRT) occurred less frequently in optimally implanted devices (3.4% vs. 12.9%, p=0.06). Hereby, implantation depth and depth/angle ratio were found to be predictors for DRT in ROC-analysis, respectively (AUC: 0.7, 95% Confidence interval [CI]: 0.56–0.84, p=0.05 and AUC: 0.72, 95% CI: 0.58–0.86, p=0.03). Optimal vs. suboptimal position Conclusion Echocardiographic classification of device-position is warranted to provide comparability and appears to be feasible. Based on the novel classification provided, optimal device-position is achieved in 50% and is found more often with the use of POs. DRT appeared to occur more often in suboptimal device-position.

Sign in / Sign up

Export Citation Format

Share Document