Dense Self-Supervised Learning for Medical Image Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929441508163584 |
|---|---|
| author | Seince, Maxime Folgoc, Loic Le de Souza, Luiz Augusto Facury Angelini, Elsa |
| author_facet | Seince, Maxime Folgoc, Loic Le de Souza, Luiz Augusto Facury Angelini, Elsa |
| contents | Deep learning has revolutionized medical image segmentation, but it relies heavily on high-quality annotations. The time, cost and expertise required to label images at the pixel-level for each new task has slowed down widespread adoption of the paradigm. We propose Pix2Rep, a self-supervised learning (SSL) approach for few-shot segmentation, that reduces the manual annotation burden by learning powerful pixel-level representations directly from unlabeled images. Pix2Rep is a novel pixel-level loss and pre-training paradigm for contrastive SSL on whole images. It is applied to generic encoder-decoder deep learning backbones (e.g., U-Net). Whereas most SSL methods enforce invariance of the learned image-level representations under intensity and spatial image augmentations, Pix2Rep enforces equivariance of the pixel-level representations. We demonstrate the framework on a task of cardiac MRI segmentation. Results show improved performance compared to existing semi- and self-supervised approaches; and a 5-fold reduction in the annotation burden for equivalent performance versus a fully supervised U-Net baseline. This includes a 30% (resp. 31%) DICE improvement for one-shot segmentation under linear-probing (resp. fine-tuning). Finally, we also integrate the novel Pix2Rep concept with the Barlow Twins non-contrastive SSL, which leads to even better segmentation performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20395 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dense Self-Supervised Learning for Medical Image Segmentation Seince, Maxime Folgoc, Loic Le de Souza, Luiz Augusto Facury Angelini, Elsa Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning I.4.6; I.4.10 Deep learning has revolutionized medical image segmentation, but it relies heavily on high-quality annotations. The time, cost and expertise required to label images at the pixel-level for each new task has slowed down widespread adoption of the paradigm. We propose Pix2Rep, a self-supervised learning (SSL) approach for few-shot segmentation, that reduces the manual annotation burden by learning powerful pixel-level representations directly from unlabeled images. Pix2Rep is a novel pixel-level loss and pre-training paradigm for contrastive SSL on whole images. It is applied to generic encoder-decoder deep learning backbones (e.g., U-Net). Whereas most SSL methods enforce invariance of the learned image-level representations under intensity and spatial image augmentations, Pix2Rep enforces equivariance of the pixel-level representations. We demonstrate the framework on a task of cardiac MRI segmentation. Results show improved performance compared to existing semi- and self-supervised approaches; and a 5-fold reduction in the annotation burden for equivalent performance versus a fully supervised U-Net baseline. This includes a 30% (resp. 31%) DICE improvement for one-shot segmentation under linear-probing (resp. fine-tuning). Finally, we also integrate the novel Pix2Rep concept with the Barlow Twins non-contrastive SSL, which leads to even better segmentation performance. |
| title | Dense Self-Supervised Learning for Medical Image Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning I.4.6; I.4.10 |
| url | https://arxiv.org/abs/2407.20395 |