End-to-end autoencoding architecture for the simultaneous generation of medical images and corresponding segmentation masks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909219492462592 |
|---|---|
| author | Kebaili, Aghiles Lapuyade-Lahorgue, Jérôme Vera, Pierre Ruan, Su |
| author_facet | Kebaili, Aghiles Lapuyade-Lahorgue, Jérôme Vera, Pierre Ruan, Su |
| contents | Despite the increasing use of deep learning in medical image segmentation, acquiring sufficient training data remains a challenge in the medical field. In response, data augmentation techniques have been proposed; however, the generation of diverse and realistic medical images and their corresponding masks remains a difficult task, especially when working with insufficient training sets. To address these limitations, we present an end-to-end architecture based on the Hamiltonian Variational Autoencoder (HVAE). This approach yields an improved posterior distribution approximation compared to traditional Variational Autoencoders (VAE), resulting in higher image generation quality. Our method outperforms generative adversarial architectures under data-scarce conditions, showcasing enhancements in image quality and precise tumor mask synthesis. We conduct experiments on two publicly available datasets, MICCAI's Brain Tumor Segmentation Challenge (BRATS), and Head and Neck Tumor Segmentation Challenge (HECKTOR), demonstrating the effectiveness of our method on different medical imaging modalities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_10472 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | End-to-end autoencoding architecture for the simultaneous generation of medical images and corresponding segmentation masks Kebaili, Aghiles Lapuyade-Lahorgue, Jérôme Vera, Pierre Ruan, Su Image and Video Processing Computer Vision and Pattern Recognition Despite the increasing use of deep learning in medical image segmentation, acquiring sufficient training data remains a challenge in the medical field. In response, data augmentation techniques have been proposed; however, the generation of diverse and realistic medical images and their corresponding masks remains a difficult task, especially when working with insufficient training sets. To address these limitations, we present an end-to-end architecture based on the Hamiltonian Variational Autoencoder (HVAE). This approach yields an improved posterior distribution approximation compared to traditional Variational Autoencoders (VAE), resulting in higher image generation quality. Our method outperforms generative adversarial architectures under data-scarce conditions, showcasing enhancements in image quality and precise tumor mask synthesis. We conduct experiments on two publicly available datasets, MICCAI's Brain Tumor Segmentation Challenge (BRATS), and Head and Neck Tumor Segmentation Challenge (HECKTOR), demonstrating the effectiveness of our method on different medical imaging modalities. |
| title | End-to-end autoencoding architecture for the simultaneous generation of medical images and corresponding segmentation masks |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2311.10472 |