mlsanityData to 14 Oct 2026

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

arXiv 2504.07904 ↗First posted 10 Apr 2025eess.IV cs.CV cs.LGcited by 0

Not on the map. Why?

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.

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

23 of 54 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  4. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  5. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  6. 2019Searching for MobileNetV3cited by 1,994
  7. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,838
  8. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,057
  9. 2019Large Batch Optimization for Deep Learning: Training BERT in 76 minutescited by 674
  10. 2021Big Self-Supervised Models Advance Medical Image Classificationcited by 320
  11. 2022Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methodscited by 149
  12. 2023The SSL Interplay: Augmentations, Inductive Bias, and Generalizationcited by 40
11 more
  1. 2020USCL: Pretraining Deep Ultrasound Image Diagnosis Model through Video Contrastive Representation Learningcited by 34
  2. 2020Longitudinal Self-Supervised Learningcited by 30
  3. 2021COVIDx-US -- An open-access benchmark dataset of ultrasound imaging data for AI-driven COVID-19 analyticscited by 17
  4. 2024You Don't Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learningcited by 16
  5. 2022Unsupervised Contrastive Learning of Image Representations from Ultrasound Videos with Hard Negative Miningcited by 14
  6. 2022Contrastive Pretraining for Echocardiography Segmentation with Limited Datacited by 13
  7. 2022HiCo: Hierarchical Contrastive Learning for Ultrasound Video Model Pretrainingcited by 7
  8. 2022Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive Learningcited by 5
  9. 2023Contrastive Self-Supervised Learning for Spatio-Temporal Analysis of Lung Ultrasound Videoscited by 4
  10. 2023Self-Supervised Pretraining Improves Performance and Inference Efficiency in Multiple Lung Ultrasound Interpretation Taskscited by 3
  11. 2024Intra-video Positive Pairs in Self-Supervised Learning for Ultrasoundcited by 2

Built on by

Not cited yet.