Uncertainty-Based Ensemble Learning in CMR Semantic Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917400593563648 |
|---|---|
| author | Liu, Yiwei Zhong, Liang Wen, Lingyi Wu, Yuankai |
| author_facet | Liu, Yiwei Zhong, Liang Wen, Lingyi Wu, Yuankai |
| contents | Existing methods derive clinical functional metrics from ventricular semantic segmentation in cardiac cine sequences. While performing well on overall segmentation, they struggle with the end slices. To address this, we extract global uncertainty from segmentation variance and use it in our ensemble learning method, Streaming, for classifier weighting, balancing overall and end-slice performance. We introduce the End Coefficient (EC) to quantify end-slice accuracy. Experiments on ACDC and M\&Ms datasets show that our framework achieves near state-of-the-art Dice Similarity Coefficient (DSC) and outperforms all models on end-slice performance, improving patient-specific segmentation accuracy. We open-sourced our code on https://github.com/LEw1sin/Uncertainty-Ensemble. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09269 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Uncertainty-Based Ensemble Learning in CMR Semantic Segmentation Liu, Yiwei Zhong, Liang Wen, Lingyi Wu, Yuankai Computer Vision and Pattern Recognition Existing methods derive clinical functional metrics from ventricular semantic segmentation in cardiac cine sequences. While performing well on overall segmentation, they struggle with the end slices. To address this, we extract global uncertainty from segmentation variance and use it in our ensemble learning method, Streaming, for classifier weighting, balancing overall and end-slice performance. We introduce the End Coefficient (EC) to quantify end-slice accuracy. Experiments on ACDC and M\&Ms datasets show that our framework achieves near state-of-the-art Dice Similarity Coefficient (DSC) and outperforms all models on end-slice performance, improving patient-specific segmentation accuracy. We open-sourced our code on https://github.com/LEw1sin/Uncertainty-Ensemble. |
| title | Uncertainty-Based Ensemble Learning in CMR Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.09269 |