# The Efficacy of Semantics-Preserving Transformations in Self-Supervised Learning for Medical Ultrasound

arXiv: https://arxiv.org/abs/2504.07904 · HTML: https://mlsanity.com/paper/2504.07904/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 54 references that are in the map.
- First posted on arXiv 10 Apr 2025.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Large Batch Optimization for Deep Learning: Training BERT in 76 minutes](https://mlsanity.com/paper/1904.00962/) (2019)
- [Big Self-Supervised Models Advance Medical Image Classification](https://mlsanity.com/paper/2101.05224/) (2021)
- [Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods](https://mlsanity.com/paper/2205.11508/) (2022)
- [The SSL Interplay: Augmentations, Inductive Bias, and Generalization](https://mlsanity.com/paper/2302.02774/) (2023)
- [USCL: Pretraining Deep Ultrasound Image Diagnosis Model through Video Contrastive Representation Learning](https://mlsanity.com/paper/2011.13066/) (2020)
- [Longitudinal Self-Supervised Learning](https://mlsanity.com/paper/2006.06930/) (2020)
- [COVIDx-US -- An open-access benchmark dataset of ultrasound imaging data for AI-driven COVID-19 analytics](https://mlsanity.com/paper/2103.10003/) (2021)
- [You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning](https://mlsanity.com/paper/2406.09294/) (2024)
- [Unsupervised Contrastive Learning of Image Representations from Ultrasound Videos with Hard Negative Mining](https://mlsanity.com/paper/2207.13148/) (2022)
- [Contrastive Pretraining for Echocardiography Segmentation with Limited Data](https://mlsanity.com/paper/2201.07219/) (2022)
- [HiCo: Hierarchical Contrastive Learning for Ultrasound Video Model Pretraining](https://mlsanity.com/paper/2210.04477/) (2022)
- [Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive Learning](https://mlsanity.com/paper/2212.04097/) (2022)
- [Contrastive Self-Supervised Learning for Spatio-Temporal Analysis of Lung Ultrasound Videos](https://mlsanity.com/paper/2310.10689/) (2023)
- [Self-Supervised Pretraining Improves Performance and Inference Efficiency in Multiple Lung Ultrasound Interpretation Tasks](https://mlsanity.com/paper/2309.02596/) (2023)
- [Intra-video Positive Pairs in Self-Supervised Learning for Ultrasound](https://mlsanity.com/paper/2403.07715/) (2024)

## Abstract (arXiv)

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.