Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.17317 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929423356264448 |
|---|---|
| author | Ferreira, André Solak, Naida Li, Jianning Dammann, Philipp Kleesiek, Jens Alves, Victor Egger, Jan |
| author_facet | Ferreira, André Solak, Naida Li, Jianning Dammann, Philipp Kleesiek, Jens Alves, Victor Egger, Jan |
| contents | Deep Learning is the state-of-the-art technology for segmenting brain tumours. However, this requires a lot of high-quality data, which is difficult to obtain, especially in the medical field. Therefore, our solutions address this problem by using unconventional mechanisms for data augmentation. Generative adversarial networks and registration are used to massively increase the amount of available samples for training three different deep learning models for brain tumour segmentation, the first task of the BraTS2023 challenge. The first model is the standard nnU-Net, the second is the Swin UNETR and the third is the winning solution of the BraTS 2021 Challenge. The entire pipeline is built on the nnU-Net implementation, except for the generation of the synthetic data. The use of convolutional algorithms and transformers is able to fill each other's knowledge gaps. Using the new metric, our best solution achieves the dice results 0.9005, 0.8673, 0.8509 and HD95 14.940, 14.467, 17.699 (whole tumour, tumour core and enhancing tumour) in the validation set. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_17317 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | How we won BraTS 2023 Adult Glioma challenge? Just faking it! Enhanced Synthetic Data Augmentation and Model Ensemble for brain tumour segmentation Ferreira, André Solak, Naida Li, Jianning Dammann, Philipp Kleesiek, Jens Alves, Victor Egger, Jan Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Deep Learning is the state-of-the-art technology for segmenting brain tumours. However, this requires a lot of high-quality data, which is difficult to obtain, especially in the medical field. Therefore, our solutions address this problem by using unconventional mechanisms for data augmentation. Generative adversarial networks and registration are used to massively increase the amount of available samples for training three different deep learning models for brain tumour segmentation, the first task of the BraTS2023 challenge. The first model is the standard nnU-Net, the second is the Swin UNETR and the third is the winning solution of the BraTS 2021 Challenge. The entire pipeline is built on the nnU-Net implementation, except for the generation of the synthetic data. The use of convolutional algorithms and transformers is able to fill each other's knowledge gaps. Using the new metric, our best solution achieves the dice results 0.9005, 0.8673, 0.8509 and HD95 14.940, 14.467, 17.699 (whole tumour, tumour core and enhancing tumour) in the validation set. |
| title | How we won BraTS 2023 Adult Glioma challenge? Just faking it! Enhanced Synthetic Data Augmentation and Model Ensemble for brain tumour segmentation |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2402.17317 |