Key result
The Recurrent Aggregation Learning method achieved superior left ventricle segmentation on multi-view echocardiographic sequences with an accuracy of 0.987 and Dice score of 0.919, outperforming U-Net.
Why the study?
Multi-view echocardiographic sequence segmentation is crucial for clinical diagnosis but remains challenging due to limited labeled data, huge noise, and large gaps across views.
Does the Recurrent Aggregation Learning method improve segmentation and classification accuracy in multi-view echocardiographic sequences compared to standard deep learning models?
Does the Recurrent Aggregation Learning method improve segmentation and classification accuracy in multi-view echocardiographic sequences compared to standard deep learning models?
The Recurrent Aggregation Learning method achieves superior segmentation accuracy and temporal stability for multi-view echocardiographic sequences, demonstrating strong potential for automated clinical assessment of left ventricular function.
Recurrent aggregation learning may aid multi-view echo segmentation; leaves open clinical validation before practice adoption.
Multi-view echocardiographic sequences segmentation is crucial for clinical diagnosis. However, this task is challenging due to limited labeled data, huge noise, and large gaps across views. Here we propose a recurrent aggregation learning method to tackle this challenging task. By pyramid ConvBlocks, multi-level and multi-scale features are extracted efficiently. Hierarchical ConvLSTMs next fuse these features and capture spatial-temporal information in multi-level and multi-scale space. We further introduce a double-branch aggregation mechanism for segmentation and classification which are mutually promoted by deep aggregation of multi-level and multi-scale features. The segmentation branch provides information to guide the classification while the classification branch affords multi-view regularization to refine segmentations and further lessen gaps across views. Our method is built as an end-to-end framework for segmentation and classification. Adequate experiments on our multi-view dataset (9000 labeled images) and the CAMUS dataset (1800 labeled images) corroborate that our method achieves not only superior segmentation and classification accuracy but also prominent temporal stability.
No takes yet. Share an insight, caveat, or question.
Li et al. (2019) studied Left ventricle segmentation in echocardiography (n=300). Recurrent Aggregation Learning (RAL) vs. U-Net, ACNN, and U-Net++ was evaluated on Segmentation Accuracy. The Recurrent Aggregation Learning method achieved superior left ventricle segmentation on multi-view echocardiographic sequences with an accuracy of 0.987 and Dice score of 0.919, outperforming U-Net.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: