Few-Shot Transfer Learning to improve Chest X-Ray pathology detection using limited triplets

TL;DR

This paper presents a few-shot transfer learning method that enhances chest X-ray pathology detection by retraining pre-trained models with a small set of image triplets, significantly improving accuracy with minimal data.

Contribution

It introduces a novel FSL approach using image triplets for rapid model retraining in medical imaging, enabling quick performance boosts with limited data.

Findings

FSL with image triplets improves detection accuracy

Rapid retraining with few images is effective

Outperforms existing FSL methods in medical imaging

Abstract

Deep learning approaches applied to medical imaging have reached near-human or better-than-human performance on many diagnostic tasks. For instance, the CheXpert competition on detecting pathologies in chest x-rays has shown excellent multi-class classification performance. However, training and validating deep learning models require extensive collections of images and still produce false inferences, as identified by a human-in-the-loop. In this paper, we introduce a practical approach to improve the predictions of a pre-trained model through Few-Shot Learning (FSL). After training and validating a model, a small number of false inference images are collected to retrain the model using \textbf{\textit{Image Triplets}} - a false positive or false negative, a true positive, and a true negative. The retrained FSL model produces considerable gains in performance with only a few epochs and few images. In addition, FSL opens rapid retraining opportunities for human-in-the-loop systems, where a radiologist can relabel false inferences, and the model can be quickly retrained. We compare our retrained model performance with existing FSL approaches in medical imaging that train and evaluate models at once.