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

Abstract

Deep learning approaches applied to medical imaging have reached near-human or betterthan-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 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. Data and Code AvailabilityThis paper uses CheXpert Dataset Irvin et al. (2019), which is a publicly available dataset of 224,316 chest radiographs from 65,240 patients.The code used for experimentation processes described in this paper -which include triplet dataset creation, training and validation of the Few-Shot Learning and Incremental Few-Shot Learning Models were anonymized and included in the supplemental material section.