Evaluating task-specific augmentations in self-supervised pre-training for 3D medical image analysis

C. H. B. Claessens; J. J. M. Hamm; C. G. A. Viviers; J. Nederend; D. J. Grünhagen; P. J. Tanis; P. H. N. de With; F. van der Sommen

doi:10.1117/12.3000850

2 April 2024 Evaluating task-specific augmentations in self-supervised pre-training for 3D medical image analysis

C. H. B. Claessens, J. J. M. Hamm, C. G. A. Viviers, J. Nederend, D. J. Grünhagen, P. J. Tanis, P. H. N. de With, F. van der Sommen

Author Affiliations +

Proceedings Volume 12926, Medical Imaging 2024: Image Processing; 129261L (2024) https://doi.org/10.1117/12.3000850
Event: SPIE Medical Imaging, 2024, San Diego, California, United States

Conference Poster

Abstract

Self-supervised learning (SSL) has become a crucial approach for pre-training deep learning models in natural and medical image analysis. However, applying transformations designed for natural images to three-dimensional (3D) medical data poses challenges. This study explores the efficacy of specific augmentations in the context of self-supervised pre-training for volumetric medical images. A 3D non-contrastive framework is proposed for in-domain self-supervised pre-training on 3D gray-scale thorax CT data, incorporating four spatial and two intensity augmentations commonly used in 3D medical image analysis. The pre-trained models, adapted versions of ResNet-50 and Vision Transformer (ViT)-S, are evaluated on lung nodule classification and lung tumor segmentation tasks. The results indicate a significant impact of SSL, with a remarkable increase in AUC and DSC as compared to training from scratch. For classification, random scalings and random rotations play a fundamental role in achieving higher downstream performance, while intensity augmentations show limited contribution and may even degrade performance. For segmentation, random intensity histogram shifting enhances robustness, while other augmentations have marginal or negative impacts. These findings underscore the necessity of tailored data augmentations within SSL for medical imaging, emphasizing the importance of task-specific transformations for optimal model performance in complex 3D medical datasets.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

C. H. B. Claessens, J. J. M. Hamm, C. G. A. Viviers, J. Nederend, D. J. Grünhagen, P. J. Tanis, P. H. N. de With, and F. van der Sommen "Evaluating task-specific augmentations in self-supervised pre-training for 3D medical image analysis", Proc. SPIE 12926, Medical Imaging 2024: Image Processing, 129261L (2 April 2024); https://doi.org/10.1117/12.3000850

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available