# Attention-driven Tree-structured Convolutional LSTM for High Dimensional Data Understanding

## TL;DR

This paper introduces a novel tree-structured ConvLSTM model with attention mechanisms for analyzing hierarchical image data, outperforming traditional sequential models in biomedical image segmentation tasks.

## Contribution

The paper proposes a new end-to-end trainable tree-structured ConvLSTM model with attention for hierarchical data analysis, addressing limitations of sequential ConvLSTM in tree-structured data.

## Key findings

- Effective in coronary artery segmentation
- Validated on four large-scale datasets
- Outperforms existing methods in accuracy and efficiency

## Abstract

Modeling the sequential information of image sequences has been a vital step of various vision tasks and convolutional long short-term memory (ConvLSTM) has demonstrated its superb performance in such spatiotemporal problems. Nevertheless, the hierarchical data structures in a significant amount of tasks (e.g., human body parts and vessel/airway tree in biomedical images) cannot be properly modeled by sequential models. Thus, ConvLSTM is not suitable for tree-structured image data analysis. In order to address these limitations, we present tree-structured ConvLSTM models for tree-structured image analysis tasks which can be trained end-to-end. To demonstrate the effectiveness of the proposed tree-structured ConvLSTM model, we present a tree-structured segmentation framework which consists of a tree-structured ConvLSTM and an attention fully convolutional network (FCN) model. The proposed framework is extensively validated on four large-scale coronary artery datasets. The results demonstrate the effectiveness and efficiency of the proposed method.