Back to Search Start Over

Unsupervised Task Design to Meta-Train Medical Image Classifiers

Authors :
Cuong C. Nguyen
Gabriel Maicas
Gustavo Carneiro
Jacinto C. Nascimento
Farbod Motlagh
Source :
ISBI
Publication Year :
2020
Publisher :
IEEE, 2020.

Abstract

Meta-training has been empirically demonstrated to be the most effective pre-training method for few-shot learning of medical image classifiers (i.e., classifiers modeled with small training sets). However, the effectiveness of meta-training relies on the availability of a reasonable number of hand-designed classification tasks, which are costly to obtain, and consequently rarely available. In this paper, we propose a new method to unsupervisedly design a large number of classification tasks to meta-train medical image classifiers. We evaluate our method on a breast dynamically contrast enhanced magnetic resonance imaging (DCE-MRI) data set that has been used to benchmark few-shot training methods of medical image classifiers. Our results show that the proposed unsupervised task design to meta-train medical image classifiers builds a pre-trained model that, after fine-tuning, produces better classification results than other unsupervised and supervised pre-training methods, and competitive results with respect to meta-training that relies on hand-designed classification tasks.

Details

Database :
OpenAIRE
Journal :
2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)
Accession number :
edsair.doi.dedup.....2affbfce52ddf15b131a5e153f409adc
Full Text :
https://doi.org/10.1109/isbi45749.2020.9098470