Contrast-Invariant Self-supervised Segmentation for Quantitative Placental MRI
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909720256708608 |
|---|---|
| author | Zhong, Xinliu Liu, Ruiying Nichols, Emily S. Zhang, Xuzhe Laine, Andrew F. Duerden, Emma G. Wang, Yun |
| author_facet | Zhong, Xinliu Liu, Ruiying Nichols, Emily S. Zhang, Xuzhe Laine, Andrew F. Duerden, Emma G. Wang, Yun |
| contents | Accurate placental segmentation is essential for quantitative analysis of the placenta. However, this task is particularly challenging in T2*-weighted placental imaging due to: (1) weak and inconsistent boundary contrast across individual echoes; (2) the absence of manual ground truth annotations for all echo times; and (3) motion artifacts across echoes caused by fetal and maternal movement. In this work, we propose a contrast-augmented segmentation framework that leverages complementary information across multi-echo T2*-weighted MRI to learn robust, contrast-invariant representations. Our method integrates: (i) masked autoencoding (MAE) for self-supervised pretraining on unlabeled multi-echo slices; (ii) masked pseudo-labeling (MPL) for unsupervised domain adaptation across echo times; and (iii) global-local collaboration to align fine-grained features with global anatomical context. We further introduce a semantic matching loss to encourage representation consistency across echoes of the same subject. Experiments on a clinical multi-echo placental MRI dataset demonstrate that our approach generalizes effectively across echo times and outperforms both single-echo and naive fusion baselines. To our knowledge, this is the first work to systematically exploit multi-echo T2*-weighted MRI for placental segmentation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_24739 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Contrast-Invariant Self-supervised Segmentation for Quantitative Placental MRI Zhong, Xinliu Liu, Ruiying Nichols, Emily S. Zhang, Xuzhe Laine, Andrew F. Duerden, Emma G. Wang, Yun Image and Video Processing Computer Vision and Pattern Recognition Accurate placental segmentation is essential for quantitative analysis of the placenta. However, this task is particularly challenging in T2*-weighted placental imaging due to: (1) weak and inconsistent boundary contrast across individual echoes; (2) the absence of manual ground truth annotations for all echo times; and (3) motion artifacts across echoes caused by fetal and maternal movement. In this work, we propose a contrast-augmented segmentation framework that leverages complementary information across multi-echo T2*-weighted MRI to learn robust, contrast-invariant representations. Our method integrates: (i) masked autoencoding (MAE) for self-supervised pretraining on unlabeled multi-echo slices; (ii) masked pseudo-labeling (MPL) for unsupervised domain adaptation across echo times; and (iii) global-local collaboration to align fine-grained features with global anatomical context. We further introduce a semantic matching loss to encourage representation consistency across echoes of the same subject. Experiments on a clinical multi-echo placental MRI dataset demonstrate that our approach generalizes effectively across echo times and outperforms both single-echo and naive fusion baselines. To our knowledge, this is the first work to systematically exploit multi-echo T2*-weighted MRI for placental segmentation. |
| title | Contrast-Invariant Self-supervised Segmentation for Quantitative Placental MRI |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.24739 |