Learning Semi-Supervised Medical Image Segmentation from Spatial Registration
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914950122831872 |
|---|---|
| author | Liu, Qianying Henderson, Paul Gu, Xiao Dai, Hang Deligianni, Fani |
| author_facet | Liu, Qianying Henderson, Paul Gu, Xiao Dai, Hang Deligianni, Fani |
| contents | Semi-supervised medical image segmentation has shown promise in training models with limited labeled data and abundant unlabeled data. However, state-of-the-art methods ignore a potentially valuable source of unsupervised semantic information -- spatial registration transforms between image volumes. To address this, we propose CCT-R, a contrastive cross-teaching framework incorporating registration information. To leverage the semantic information available in registrations between volume pairs, CCT-R incorporates two proposed modules: Registration Supervision Loss (RSL) and Registration-Enhanced Positive Sampling (REPS). The RSL leverages segmentation knowledge derived from transforms between labeled and unlabeled volume pairs, providing an additional source of pseudo-labels. REPS enhances contrastive learning by identifying anatomically-corresponding positives across volumes using registration transforms. Experimental results on two challenging medical segmentation benchmarks demonstrate the effectiveness and superiority of CCT-R across various semi-supervised settings, with as few as one labeled case. Our code is available at https://github.com/kathyliu579/ContrastiveCross-teachingWithRegistration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10422 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Semi-Supervised Medical Image Segmentation from Spatial Registration Liu, Qianying Henderson, Paul Gu, Xiao Dai, Hang Deligianni, Fani Computer Vision and Pattern Recognition Semi-supervised medical image segmentation has shown promise in training models with limited labeled data and abundant unlabeled data. However, state-of-the-art methods ignore a potentially valuable source of unsupervised semantic information -- spatial registration transforms between image volumes. To address this, we propose CCT-R, a contrastive cross-teaching framework incorporating registration information. To leverage the semantic information available in registrations between volume pairs, CCT-R incorporates two proposed modules: Registration Supervision Loss (RSL) and Registration-Enhanced Positive Sampling (REPS). The RSL leverages segmentation knowledge derived from transforms between labeled and unlabeled volume pairs, providing an additional source of pseudo-labels. REPS enhances contrastive learning by identifying anatomically-corresponding positives across volumes using registration transforms. Experimental results on two challenging medical segmentation benchmarks demonstrate the effectiveness and superiority of CCT-R across various semi-supervised settings, with as few as one labeled case. Our code is available at https://github.com/kathyliu579/ContrastiveCross-teachingWithRegistration. |
| title | Learning Semi-Supervised Medical Image Segmentation from Spatial Registration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.10422 |