Multi-level semantic adaptation for few-shot segmentation on cardiac image sequences
•We provide the multi-level semantic adaptation to improve few-shot segmentation on cardiac image sequence.•We propose the dual-level alignment regularization to improve the model adaptation on diverse modalities.•We propose the hierarchical attention metric to enhance the model discrimination on th...
Gespeichert in:
Veröffentlicht in: | Medical image analysis 2021-10, Vol.73, p.102170-102170, Article 102170 |
---|---|
Hauptverfasser: | , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | •We provide the multi-level semantic adaptation to improve few-shot segmentation on cardiac image sequence.•We propose the dual-level alignment regularization to improve the model adaptation on diverse modalities.•We propose the hierarchical attention metric to enhance the model discrimination on the border features.•We present the first work to leverage few-shot segmentation in cardiac image sequence.
[Display omitted]
Obtaining manual labels is time-consuming and labor-intensive on cardiac image sequences. Few-shot segmentation can utilize limited labels to learn new tasks. However, it suffers from two challenges: spatial-temporal distribution bias and long-term information bias. These challenges derive from the impact of the time dimension on cardiac image sequences, resulting in serious over-adaptation. In this paper, we propose the multi-level semantic adaptation (MSA) for few-shot segmentation on cardiac image sequences. The MSA addresses the two biases by exploring the domain adaptation and the weight adaptation on the semantic features in multiple levels, including sequence-level, frame-level, and pixel-level. First, the MSA proposes the dual-level feature adjustment for domain adaptation in spatial and temporal directions. This adjustment explicitly aligns the frame-level feature and the sequence-level feature to improve the model adaptation on diverse modalities. Second, the MSA explores the hierarchical attention metric for weight adaptation in the frame-level feature and the pixel-level feature. This metric focuses on the similar frame and the target region to promote the model discrimination on the border features. The extensive experiments demonstrate that our MSA is effective in few-shot segmentation on cardiac image sequences with three modalities, i.e. MR, CT, and Echo (e.g. the average Dice is 0.9243), as well as superior to the ten state-of-the-art methods. |
---|---|
ISSN: | 1361-8415 1361-8423 |
DOI: | 10.1016/j.media.2021.102170 |