Abstract 224: A Deep Learning Approach to Left-Ventricular Chamber Quantification for Fully Automated Three Dimensional Strain Analysis in Cardiotoxicity

2020 ◽  
Vol 127 (Suppl_1) ◽  
Author(s):  
Bryant M Baldwin ◽  
Shane Joseph ◽  
Xiaodong Zhong ◽  
Ranya Kakish ◽  
Cherie Revere ◽  
...  
Keyword(s):  
Deep Learning ◽  
Interpolation Method ◽  
Three Dimensional ◽  
Strain Analysis ◽  
Correlation Coefficients ◽  
Semantic Segmentation ◽  
Left Ventricular ◽  
Breast Cancer Patients ◽  
Left Ventricular Chamber ◽  
Longitudinal Strains

This study investigated MRI and semantic segmentation-based deep-learning (SSDL) automation for left-ventricular chamber quantifications (LVCQ) and low longitudinal strain (LLS) determination, thus eliminating user-bias by providing an automated tool to detect cardiotoxicity (CT) in breast cancer patients treated with antineoplastic agents. Displacement Encoding with Stimulated Echoes-based (DENSE) myocardial images from 26 patients were analyzed with the tool’s Convolution Neural Network with underlying Resnet-50 architecture. Quantifications based on the SSDL tool’s output were for LV end-diastolic diameter (LVEDD), ejection fraction (LVEF), and mass (LVM) (see figure for phase sequence). LLS was analyzed with Radial Point Interpolation Method (RPIM) with DENSE phase-based displacements. LVCQs were validated by comparison to measurements obtained with an existing semi-automated vendor tool (VT) and strains by 2 independent users employing Bland-Altman analysis (BAA) and interclass correlation coefficients estimated with Cronbach’s Alpha (C-Alpha) index. F1 score for classification accuracy was 0.92. LVCQs determined by SSDL and VT were 4.6 ± 0.5 vs 4.6 ± 0.7 cm (C-Alpha = 0.93 and BAA = 0.5 ± 0.5 cm) for LVEDD, 58 ± 5 vs 58 ± 6 % (0.90, 1 ± 5%) for LVEF, 119 ± 17 vs 121 ± 14 g (0.93, 5 ± 8 g) for LV mass, while LLS was 14 ± 4 vs 14 ± 3 % (0.86, 0.2 ± 6%). Hence, equivalent LV dimensions, mass and strains measured by VT and DENSE imaging validate our unique automated analytic tool. Longitudinal strains in patients can then be analyzed without user bias to detect abnormalities for the indication of cardiotoxicity and the need for therapeutic intervention even if LVEF is not affected.

Abstract P345: A MRI Displacement-based Deep-learning Semantic Segmentation Tool For Left-ventricular Longitudinal Strain Analysis In Cardiotoxicity

2021 ◽  
Vol 129 (Suppl_1) ◽  
Author(s):  
Julia Kar ◽  
Michael V Cohen ◽  
Teja Poorsala ◽  
Samuel A McQuiston ◽  
Cheri Revere ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Cancer Patients ◽  
Healthy Subjects ◽  
Longitudinal Strain ◽  
Strain Analysis ◽  
Semantic Segmentation ◽  
Left Ventricular ◽  
Phase Unwrapping ◽  
Breast Cancer Patients

Global longitudinal strain (GLS) computed in the left-ventricle (LV) is an established metric for detecting cardiotoxicity in breast cancer patients treated with antineoplastic agents. The purpose of this study was to develop a novel, MRI-based, deep-learning semantic segmentation tool that automates the phase-unwrapping for LV displacement computation in GLS. Strain analysis via phase-unwrapping was conducted on 30 breast cancer patients and 30 healthy females acquired with the Displacement Encoding with Stimulated Echoes (DENSE) sequence. A ResNet-50 deep convolutional neural network (DCNN) architecture for automated phase-unwrapping, a previously validated ResNet-50 DCNN for chamber quantification and the Radial Point Interpolation Method were used for GLS computation (Figure 1). The DCNN's performance was measured with F1 and Dice scores, and validated in comparison to the robust transport of intensity equation (RTIE) and quality guided phase-unwrapping (QGPU) conventional algorithms. The three techniques were compared by intraclass correlation coefficient with Cronbach’s alpha (C-alpha) index. Classification accuracy with the DCNN was F1 score of 0.92 and Dice score of 0.89. The GLS results from RTIE, QGPU and DCNN were -16.0 ± 2%, -16.1 ± 3% and -15.9 ± 3% (C-alpha = 0.89) for patients and -18.9 ± 3%, -19.0 ± 4% and -18.9 ± 3% (C-alpha = 0.92) for healthy subjects. Comparable validation results from the three techniques show the feasibility of a DCNN-based approach to LV displacement and GLS analysis. The dissimilarities between patients and healthy subjects demonstrate that DCNN-based GLS computation may detect LV abnormalities related to cardiotoxicity.

Validation of three‐dimensional echocardiographic principal strain analysis for assessing left ventricular contractility: An animal study

2019 ◽  
Vol 46 (5) ◽  
pp. 2137-2144
Author(s):  
Sahmin Lee ◽  
Seunghyun Choi ◽  
Sehwan Kim ◽  
Yeongjin Jeong ◽  
Kyusup Lee ◽  
...  
Keyword(s):  
Animal Study ◽  
Three Dimensional ◽  
Strain Analysis ◽  
Left Ventricular ◽  
Principal Strain ◽  
Ventricular Contractility ◽  
Left Ventricular Contractility

Automated Pancreas Segmentation And Volumetry Using Deep Neural Network On Computed Tomography

2021 ◽  
Author(s):  
Sang-Heon Lim ◽  
Young Jae Kim ◽  
Yeon-Ho Park ◽  
Doojin Kim ◽  
Kwang Gi Kim ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Deep Learning ◽  
Automatic Segmentation ◽  
External Validation ◽  
Three Dimensional ◽  
Semantic Segmentation ◽  
Quantitative Information ◽  
Similarity Coefficients ◽  
Internal Validation ◽  
Pancreas Segmentation

Abstract Pancreas segmentation is necessary for observing lesions, analyzing anatomical structures, and predicting patient prognosis. Therefore, various studies have designed segmentation models based on convolutional neural networks for pancreas segmentation. However, the deep learning approach is limited by a lack of data, and studies conducted on a large computed tomography dataset are scarce. Therefore, this study aims to perform deep-learning-based semantic segmentation on 1,006 participants and evaluate the automatic segmentation performance of the pancreas via four individual three-dimensional segmentation networks. In this study, we performed internal validation with 1,006 patients and external validation using the Cancer Imaging Archive (TCIA) pancreas dataset. We obtained mean precision, recall, and dice similarity coefficients of 0.869, 0.842, and 0.842, respectively, for internal validation via a relevant approach among the four deep learning networks. Using the external dataset, the deep learning network achieved mean precision, recall, and dice similarity coefficients of 0.779, 0.749, and 0.735, respectively. We expect that generalized deep-learning-based systems can assist clinical decisions by providing accurate pancreatic segmentation and quantitative information of the pancreas for abdominal computed tomography.

Abstract 964: Effect of Volume Overload on Left Ventricular Torsion and Extra Cellular Matrix

Circulation ◽  
2007 ◽  
Vol 116 (suppl_16) ◽  
Author(s):  
Hosakote M Nagaraj ◽  
Thomas S Denney ◽  
Steven G Lloyd ◽  
David Calhoun ◽  
Inmaculada Aban ◽  
...  
Keyword(s):  
Picric Acid ◽  
Three Dimensional ◽  
Volume Overload ◽  
Left Ventricular ◽  
Deformation Model ◽  
Data Set ◽  
Left Ventricular Torsion ◽  
Tissue Tagging ◽  
Ventricular Torsion ◽  
Longitudinal Strains

Background: Muscle fibers are arranged in a spiral network and are connected by extracellular matrix (ECM). LV torsion is increased in the pressure overloaded heart where there is an increase in ECM. However, torsion and its relation to ECM have not been systematically studied in the volume overloaded heart. Hypothesis: The volume overloaded heart has a decrease in LV torsion due a loss of ECM. Methods: Primary mitral regurgitation (MR) (n=29), resistant hypertension (HTN) (n=77) and normal volunteers (NL) (n±37) were studied. Comprehensive cardiac magnetic resonance imaging (MRI) with tissue tagging was performed and analyzed using three-dimensional data set. Torsion was computed by fitting a B-spline deformation model in prolate-spheroidal coordinates to the tag line data. A subset of MR subjects had LV collagen assessed by picric acid Sirius red from biopsy samples taken at the time of surgery. Results: LV ejection fraction was 65% in MR and 70% in HTN. MR demonstrated eccentric remodeling and HTN demonstrated concentric remodeling. HTN had significantly higher torsion angle and systolic twist compared to NL and MR. This was associated with a simultaneous decrease in longitudinal strain. In contrast, MR patients had similar torsion indices, circumferential and longitudinal strains compared to NL. LV biopsy in MR demonstrated a decrease in interstitial collagen compared to NL. Conclusions: As opposed to the pure volume overloaded heart, LV torsional forces are increased in the pressure overloaded heart. This difference may be related to a rearrangement of the laminar structure due to a differential effect on ECM in the volume overloaded versus the pressure overloaded heart.

scholarly journals Transmural distribution of three-dimensional strain in the isolated arrested canine left ventricle

1991 ◽  
Vol 261 (3) ◽  
pp. H918-H928 ◽  
Author(s):  
J. H. Omens ◽  
K. D. May ◽  
A. D. McCulloch
Keyword(s):  
Three Dimensional ◽  
Left Ventricular Pressure ◽  
Ventricular Volume ◽  
Left Ventricular ◽  
Fiber Direction ◽  
Plane Shear ◽  
Left Handed ◽  
Longitudinal Strains ◽  
Transverse Shear Strains ◽  
Principal Strains

Three-dimensional myocardial strains in seven isolated, potassium-arrested dog hearts were measured by biplane radiography of 3 transmural columns of 4-6 radiopaque beads implanted in the midanterior left ventricular free wall. Transmural distributions of strain during inflation of a left ventricular balloon to 20-30 mmHg were computed with respect to the zero pressure state. Magnitudes of the 3 principal strains increased in proportion to ventricular volume (0.0088, 0.0037, and -0.0059 ml-1). At a left ventricular pressure of 8 +/- 4 mmHg, mean circumferential (E11) and longitudinal strains (E22) were similar, increasing from epicardium (0.058 +/- 0.055 and 0.036 +/- 0.024) to subendocardium (0.139 +/- 0.102 and 0.120 +/- 0.084) as did the transmural (wall thinning) strain E33 (-0.053 +/- 0.071 to -0.128 +/- 0.083). Negative in-plane shear E12 was small (-0.008 to -0.052), consistent with a left-handed torsion of the left ventricular wall. Mean transverse shear strains E13 and E23 were small (-0.029 to 0.007) but showed considerable variability between hearts. Fiber strain had no significant transmural variation (P = 0.57). The principal axis of greatest strain was close to the fiber orientation on the epicardium (-15 degrees) but closer to the cross-fiber direction near the endocardium (-40 degrees). Therefore, the end-diastolic fiber lengths are maximized on the epicardium and minimized on the endocardium.

scholarly journals Voxel-based 3D Point Cloud Semantic Segmentation: Unsupervised Geometric and Relationship Featuring vs Deep Learning Methods

2019 ◽  
Vol 8 (5) ◽  
pp. 213 ◽  
Author(s):  
Florent Poux ◽  
Roland Billen
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Semantic Representation ◽  
Structural Connectivity ◽  
Three Dimensional ◽  
Strong Support ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Learning Methods ◽  
Cloud Data

Automation in point cloud data processing is central in knowledge discovery within decision-making systems. The definition of relevant features is often key for segmentation and classification, with automated workflows presenting the main challenges. In this paper, we propose a voxel-based feature engineering that better characterize point clusters and provide strong support to supervised or unsupervised classification. We provide different feature generalization levels to permit interoperable frameworks. First, we recommend a shape-based feature set (SF1) that only leverages the raw X, Y, Z attributes of any point cloud. Afterwards, we derive relationship and topology between voxel entities to obtain a three-dimensional (3D) structural connectivity feature set (SF2). Finally, we provide a knowledge-based decision tree to permit infrastructure-related classification. We study SF1/SF2 synergy on a new semantic segmentation framework for the constitution of a higher semantic representation of point clouds in relevant clusters. Finally, we benchmark the approach against novel and best-performing deep-learning methods while using the full S3DIS dataset. We highlight good performances, easy-integration, and high F1-score (> 85%) for planar-dominant classes that are comparable to state-of-the-art deep learning.

scholarly journals Moderated Posters: Deformation imagingP96How accurate can different strain analysis tools detect regional function?abnormalities, a report from the second inter-vendor comparison?studyP97Variability and reproducibility of segmental longitudinal strain measurements, a report form the second intervendor comparison studyP98Systolic and diastolic left atrial deformation parameters before and after optimization of dual chamber pacemaker parametersP99The timing of the post systolic shortening in prediction of scarred myocardiumP100Altered contribution of longitudinal and radial motion to right ventricular ejection and filling in heart transplant recipientsP101Left ventricular and atrial function in old patients underwent transcatheter aortic valve implantation, evaluated by two and three-dimensional speckle tracking at eighteen-month follow-upP102Age-related changes in left ventricular strain measured by speckle-tracking echocardiography and association with telomere length in healthy peopleP103Intracardiac speckle tracking echocardiography-based method for assessment of pulmonary vein isolation in patients with atrial fibrillation

2016 ◽  
Vol 17 (suppl 2) ◽  
pp. ii9-ii11
Author(s):  
O. Mirea ◽  
O. Mirea ◽  
A. Karuzas ◽  
E. Nestaas ◽  
BK. Lakatos ◽  
...  
Keyword(s):  
Speckle Tracking ◽  
Speckle Tracking Echocardiography ◽  
Three Dimensional ◽  
Strain Analysis ◽  
Left Ventricular ◽  
Old Patients ◽  
Left Ventricular Strain ◽  
Transcatheter Aortic Valve ◽  
Before And After ◽  
Valve Implantation

Three-dimensional alignment of the aggregated myocytes in the normal and hypertrophic murine heart

2009 ◽  
Vol 107 (3) ◽  
pp. 921-927 ◽  
Author(s):  
Boris Schmitt ◽  
Katsiaryna Fedarava ◽  
Jan Falkenberg ◽  
Kai Rothaus ◽  
Narendra K. Bodhey ◽  
...  
Keyword(s):  
Ventricular Hypertrophy ◽  
Diffusion Tensor ◽  
Three Dimensional ◽  
Spatial Arrangement ◽  
Left Ventricular ◽  
Outer Radius ◽  
Myocardial Mass ◽  
3.0 Tesla ◽  
Left Ventricular Chamber ◽  
Hypertrophied Myocardium

Several observations suggest that the transmission of myocardial forces is influenced in part by the spatial arrangement of the myocytes aggregated together within ventricular mass. Our aim was to assess, using diffusion tensor magnetic resonance imaging (DT-MRI), any differences in the three-dimensional arrangement of these myocytes in the normal heart compared with the hypertrophic murine myocardium. We induced ventricular hypertrophy in seven mice by infusion of angiotensin II through a subcutaneous pump, with seven other mice serving as controls. DT-MRI of explanted hearts was performed at 3.0 Tesla. We used the primary eigenvector in each voxel to determine the three-dimensional orientation of aggregated myocytes in respect to their helical angles and their transmural courses (intruding angles). Compared with controls, the hypertrophic hearts showed significant increases in myocardial mass and the outer radius of the left ventricular chamber ( P < 0.05). In both groups, a significant change was noted from positive intruding angles at the base to negative angles at the ventricular apex ( P < 0.01). Compared with controls, the hypertrophied hearts had significantly larger intruding angles of the aggregated myocytes, notably in the apical and basal slices ( P < 0.001). In both groups, the helical angles were greatest in midventricular sections, albeit with significantly smaller angles in the mice with hypertrophied myocardium ( P < 0.01). The use of DT-MRI revealed significant differences in helix and intruding angles of the myocytes in the mice with hypertrophied myocardium.

Sign in / Sign up

Export Citation Format

Share Document