Self-supervised Learning for Chest CT - Training Strategies and Effect on Downstream Applications

Abstract

Self-supervised pretraining can reduce the amount of labeled training data needed by pre-learning fundamental visual characteristics of the medical imaging data. In this study, we investigate several self-supervised training strategies for chest computed tomography exams and their effects of downstream applications. we benchmark five well-known self-supervision strategies (masked image region prediction, next slice prediction, rotation prediction, flip prediction and denoising) on 15M chest CT slices collected from four sites of Mayo Clinic enterprise. These models were evaluated for two downstream tasks on public datasets; pulmonary embolism (PE) detection (classification) and lung nodule segmentation. Image embeddings generated by these models were also evaluated for prediction of patient age, race, and gender to study inherent biases in understanding of chest CT exams by models. Use of pretraining weights, especially masked regions prediction based weights, improved performance and reduced computational effort needed for downstream tasks compared to task-specific state-of-the-art (SOTA) models. Performance improvement for PE detection was observed for training dataset sizes as large as 380K with maximum gain of 5% over SOTA. Segmentation model initialized with pretraining weights learned twice as fast as randomly initialized model. While gender and age predictors built using self-supervised training weights showed no performance improvement over randomly initialized predictors, the race predictor experienced a 10% performance boost when using self-supervised training weights. We released models and weights under open-source academic license. These models can then be finetuned with limited task-specific annotated data for a variety of downstream imaging tasks thus accelerating research in biomedical imaging informatics.