Weakly-Supervised Self-Training for Breast Cancer Localization.
Annu Int Conf IEEE Eng Med Biol Soc
; 2020: 1124-1127, 2020 07.
Article
en En
| MEDLINE
| ID: mdl-33018184
ABSTRACT
The use of deep learning methods has dramatically increased the state-of-the-art performance in image object localization. However, commonly used supervised learning methods require large training datasets with pixel-level or bounding box annotations. Obtaining such fine-grained annotations is extremely costly, especially in the medical imaging domain. In this work, we propose a novel weakly supervised method for breast cancer localization. The essential advantage of our approach is that the model only requires image-level labels and uses a self-training strategy to refine the predicted localization in a step-wise manner. We evaluated our approach on a large, clinically relevant mammogram dataset. The results show that our model significantly improves performance compared to other methods trained similarly.
Texto completo:
1
Colección:
01-internacional
Banco de datos:
MEDLINE
Asunto principal:
Neoplasias de la Mama
Tipo de estudio:
Prognostic_studies
Límite:
Humans
Idioma:
En
Revista:
Annu Int Conf IEEE Eng Med Biol Soc
Año:
2020
Tipo del documento:
Article