# Unsupervised Task Design to Meta-Train Medical Image Classifiers

arXiv: https://arxiv.org/abs/1907.07816 · HTML: https://mlsanity.com/paper/1907.07816/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2019.

## Built on by (most cited first, 2 of 2)

- [DeepMCAT: Large-Scale Deep Clustering for Medical Image Categorization](https://mlsanity.com/paper/2110.00109/) (2021)
- [Expert-Agnostic Ultrasound Image Quality Assessment using Deep Variational Clustering](https://mlsanity.com/paper/2307.02462/) (2023)

## Abstract (arXiv)

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.