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

Guardat en:
Dades bibliogràfiques
Publicat a:Bioengineering vol. 12, no. 8 (2025), p. 855-889
Autor principal: Blake, VanBerlo
Altres autors: Hoey, Jesse, Wong, Alexander, Arntfield, Robert
Publicat:
MDPI AG
Matèries:
Accés en línia:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetes: Afegir etiqueta
Sense etiquetes, Sigues el primer a etiquetar aquest registre!

MARC

LEADER 00000nab a2200000uu 4500
001 3243983881
003 UK-CbPIL
022 |a 2306-5354 
024 7 |a 10.3390/bioengineering12080855  |2 doi 
035 |a 3243983881 
045 2 |b d20250101  |b d20251231 
100 1 |a Blake, VanBerlo  |u David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON N2L 3G1, Canada 
245 1 |a The Efficacy of Semantics-Preserving Transformations in Self-Supervised Learning for Medical Ultrasound 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a 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 developers working with SSL in ultrasound. 
651 4 |a United States--US 
653 |a Datasets 
653 |a Classification 
653 |a Pattern recognition 
653 |a Medical imaging 
653 |a COVID-19 
653 |a Machine learning 
653 |a Pleural effusion 
653 |a Data augmentation 
653 |a Self-supervised learning 
653 |a Preprocessing 
653 |a Semantics 
653 |a Pneumonia 
653 |a Pipelines 
653 |a Medical research 
653 |a Effectiveness 
653 |a Ultrasound 
653 |a Object recognition 
653 |a Ultrasonic imaging 
653 |a Embedding 
700 1 |a Hoey, Jesse  |u David R. Cheriton School of Computer Science, University of Waterloo, Waterloo, ON N2L 3G1, Canada 
700 1 |a Wong, Alexander  |u Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada 
700 1 |a Arntfield, Robert  |u Schulich School of Medicine and Dentistry, Western University, London, ON N6A 3K7, Canada 
773 0 |t Bioengineering  |g vol. 12, no. 8 (2025), p. 855-889 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3243983881/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3243983881/fulltextwithgraphics/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3243983881/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch