Chest X-ray Pneumothorax Segmentation Using EfficientNet-B4 Transfer Learning in a U-Net Architecture
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911138270150656 |
|---|---|
| author | Roque, Alvaro Aranibar Sebastian, Helga |
| author_facet | Roque, Alvaro Aranibar Sebastian, Helga |
| contents | Pneumothorax, the abnormal accumulation of air in the pleural space, can be life-threatening if undetected. Chest X-rays are the first-line diagnostic tool, but small cases may be subtle. We propose an automated deep-learning pipeline using a U-Net with an EfficientNet-B4 encoder to segment pneumothorax regions. Trained on the SIIM-ACR dataset with data augmentation and a combined binary cross-entropy plus Dice loss, the model achieved an IoU of 0.7008 and Dice score of 0.8241 on the independent PTX-498 dataset. These results demonstrate that the model can accurately localize pneumothoraces and support radiologists. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03950 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Chest X-ray Pneumothorax Segmentation Using EfficientNet-B4 Transfer Learning in a U-Net Architecture Roque, Alvaro Aranibar Sebastian, Helga Computer Vision and Pattern Recognition Artificial Intelligence Pneumothorax, the abnormal accumulation of air in the pleural space, can be life-threatening if undetected. Chest X-rays are the first-line diagnostic tool, but small cases may be subtle. We propose an automated deep-learning pipeline using a U-Net with an EfficientNet-B4 encoder to segment pneumothorax regions. Trained on the SIIM-ACR dataset with data augmentation and a combined binary cross-entropy plus Dice loss, the model achieved an IoU of 0.7008 and Dice score of 0.8241 on the independent PTX-498 dataset. These results demonstrate that the model can accurately localize pneumothoraces and support radiologists. |
| title | Chest X-ray Pneumothorax Segmentation Using EfficientNet-B4 Transfer Learning in a U-Net Architecture |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.03950 |