Automatic Myocardial Strain Imaging in Echocardiography Using Deep Learning

Abstract

Recent studies in the field of deep learning suggest that motion estimation can be treated as a learnable problem. In this paper we propose a pipeline for functional imaging in echocardiography consisting of four central components, (i) classification of cardiac view, (ii) semantic partitioning of the left ventricle (LV) myocardium, (iii) regional motion estimates and (iv) fusion of measurements. A U-Net type of convolutional neural network (CNN) was developed to classify muscle tissue, and partitioned into a semantic measurement kernel based on LV length and ventricular orientation. Dense tissue motion was predicted using stacked U-Net architectures with image warping of intermediate flow, designed to tackle variable displacements. Training was performed on a mixture of real and synthetic data. The resulting segmentation and motion estimates was fused in a Kalman filter and used as basis for measuring global longitudinal strain. For reference, 2D ultrasound images from 21 subjects were acquired using a GE Vivid system. Data was analyzed by two specialists using a semi-automatic tool for longitudinal function estimates in a commercial system, and further compared to output of the proposed method. Qualitative assessment showed comparable deformation trends as the clinical analysis software. The average deviation for the global longitudinal strain was (−0.6 ± 1.6)% for apical four-chamber view. The system was implemented with Tensorflow, and working in an end-to-end fashion without any ad-hoc tuning. Using a modern graphics processing unit, the average inference time is estimated to (115 ± 3) ms per frame.

DeepStrain: A Deep Learning Workflow for the Automated Characterization of Cardiac Mechanics

“…Thus, incorporating our method within a strain analysis framework could potentially enable accurate, user-independent, and quantitative characterization of cardiac mechanics at a both global and regional level. While this framework could be based on echocardiography images (30), these data remain limited for strain mapping tasks by their low reproducibility of acquisition planes (4) and temporal stability of tracking patterns (31). In contrast, cine-MRI offers the most accurate and reproducible assessment of cardiac anatomy and function, thus providing a more thorough set of data for learning-based motion models.…”

Deep Learning in Ultrasound Imaging

“…The authors in [105] effectively leverage deep learning to drastically simplify this procedure, enabling real-time detection and localization of standard fetal scan planes in freehand ultrasound. Similarly, in [106], [107], deep learning was used to accelerate echocardiographic exams by automatically recognizing the relevant standard views for further analysis, even permitting automated myocardial strain imaging [108]. In [109], a CNN was trained to perform thyroid nodule detection and recognition.…”

Machine Learning for Clinical Decision-Making: Challenges and Opportunities

“…The output was used to quantify chamber volumes, left ventricular mass and ejection fraction, and automatically determine longitudinal strain through speckle tracking. Segmentation was also used to compute tissue motion and estimate global longitudinal strain from 2D echocardiographic images, using CNNs (Østvik, Smistad, Espeland, Berg, & Lovstakken, 2018). More DL solutions in cardiovascular applications can be found in (Bernard et al, 2018;Litjens et al, 2019).…”