English

Recurrent Aggregation Learning for Multi-View Echocardiographic Sequences Segmentation

Image and Video Processing 2019-07-29 v1 Computer Vision and Pattern Recognition

Abstract

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.

Keywords

Cite

@article{arxiv.1907.11292,
  title  = {Recurrent Aggregation Learning for Multi-View Echocardiographic Sequences Segmentation},
  author = {Ming Li and Weiwei Zhang and Guang Yang and Chengjia Wang and Heye Zhang and Huafeng Liu and Wei Zheng and Shuo Li},
  journal= {arXiv preprint arXiv:1907.11292},
  year   = {2019}
}

Comments

MICCAI 2019

R2 v1 2026-06-23T10:31:23.397Z