Key result
PLANet outperforms traditional and deep learning methods in real-time cardiac structure segmentation.
Why the study?
Automatic 2D echocardiography segmentation has lacked an effective feature enhancement approach for contextual feature capture and label coherence in category prediction for individual pixels.
Does the deep pyramid local attention neural network (PLANet) improve cardiac structure segmentation performance in 2D echocardiography compared to traditional and deep learning methods?
Does the deep pyramid local attention neural network (PLANet) improve cardiac structure segmentation performance in 2D echocardiography compared to traditional and deep learning methods?
The proposed PLANet deep learning model improves automatic cardiac structure segmentation in 2D echocardiography, offering real-time performance with potential clinical utility.
PLANet may enhance real-time echocardiography segmentation; leaves open translation to clinical outcomes or workflow.
Automatic semantic segmentation in 2D echocardiography is vital in clinical practice for assessing various cardiac functions and improving the diagnosis of cardiac diseases. However, two distinct problems have persisted in automatic segmentation in 2D echocardiography, namely the lack of an effective feature enhancement approach for contextual feature capture and lack of label coherence in category prediction for individual pixels. Therefore, in this study, we propose a deep learning model, called deep pyramid local attention neural network (PLANet), to improve the segmentation performance of automatic methods in 2D echocardiography. Specifically, we propose a pyramid local attention module to enhance features by capturing supporting information within compact and sparse neighboring contexts. We also propose a label coherence learning mechanism to promote prediction consistency for pixels and their neighbors by guiding the learning with explicit supervision signals. The proposed PLANet was extensively evaluated on the dataset of cardiac acquisitions for multi-structure ultrasound segmentation (CAMUS) and sub-EchoNet-Dynamic, which are two large-scale and public 2D echocardiography datasets. The experimental results show that PLANet performs better than traditional and deep learning-based segmentation methods on geometrical and clinical metrics. Moreover, PLANet can complete the segmentation of heart structures in 2D echocardiography in real time, indicating a potential to assist cardiologists accurately and efficiently.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2020) studied Cardiac structure segmentation. Deep pyramid local attention neural network (PLANet) vs. Traditional and deep learning-based segmentation methods was evaluated on Geometrical and clinical metrics for segmentation performance. The deep pyramid local attention neural network (PLANet) outperformed traditional and deep learning-based methods on geometrical and clinical metrics for real-time cardiac structure segmentation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: