Multi-Task Pre-Training of Deep Neural Networks for Digital Pathology.
IEEE J Biomed Health Inform
; 25(2): 412-421, 2021 02.
Article
em En
| MEDLINE
| ID: mdl-32386169
ABSTRACT
In this work, we investigate multi-task learning as a way of pre-training models for classification tasks in digital pathology. It is motivated by the fact that many small and medium-size datasets have been released by the community over the years whereas there is no large scale dataset similar to ImageNet in the domain. We first assemble and transform many digital pathology datasets into a pool of 22 classification tasks and almost 900k images. Then, we propose a simple architecture and training scheme for creating a transferable model and a robust evaluation and selection protocol in order to evaluate our method. Depending on the target task, we show that our models used as feature extractors either improve significantly over ImageNet pre-trained models or provide comparable performance. Fine-tuning improves performance over feature extraction and is able to recover the lack of specificity of ImageNet features, as both pre-training sources yield comparable performance.
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Redes Neurais de Computação
Limite:
Humans
Idioma:
En
Revista:
IEEE J Biomed Health Inform
Ano de publicação:
2021
Tipo de documento:
Article