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. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/ISBI45749.2020.9098470 | 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI) |
Keywords | DocType | ISSN |
meta-training,unsupervised learning,unsupervised task design,breast image analysis,magnetic resonance imaging,few-shot classification,pre-training,clustering | Conference | 1945-7928 |
ISBN | Citations | PageRank |
978-1-5386-9331-5 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Maicas Gabriel | 1 | 0 | 0.34 |
Cuong Nguyen | 2 | 207 | 35.89 |
Motlagh Farbod | 3 | 0 | 0.34 |
Jacinto C. Nascimento | 4 | 396 | 40.94 |
Gustavo Carneiro | 5 | 292 | 27.63 |