The Efficacy of Semantics-Preserving Transformations in Self-Supervised Learning for Medical Ultrasound
This work provides practical guidance for medical imaging practitioners using SSL in ultrasound, though it is incremental as it adapts existing methods to a specific domain.
The study investigated data augmentation and preprocessing strategies in self-supervised learning for lung ultrasound, finding that semantics-preserving transformations improved COVID-19 classification, while cropping-based methods enhanced B-line and pleural effusion detection.
Data augmentation is a central component of joint embedding self-supervised learning (SSL). Approaches that work for natural images may not always be effective in medical imaging tasks. This study systematically investigated the impact of data augmentation and preprocessing strategies in SSL for lung ultrasound. Three data augmentation pipelines were assessed: (1) a baseline pipeline commonly used across imaging domains, (2) a novel semantic-preserving pipeline designed for ultrasound, and (3) a distilled set of the most effective transformations from both pipelines. Pretrained models were evaluated on multiple classification tasks: B-line detection, pleural effusion detection, and COVID-19 classification. Experiments revealed that semantics-preserving data augmentation resulted in the greatest performance for COVID-19 classification - a diagnostic task requiring global image context. Cropping-based methods yielded the greatest performance on the B-line and pleural effusion object classification tasks, which require strong local pattern recognition. Lastly, semantics-preserving ultrasound image preprocessing resulted in increased downstream performance for multiple tasks. Guidance regarding data augmentation and preprocessing strategies was synthesized for practitioners working with SSL in ultrasound.