What question did this study set out to answer?

This review aims to explore the methodologies and challenges of using machine learning for synthetic ultrasound generation in radiology.

Approaches and Limitations of Machine Learning for Synthetic Ultrasound Generation

View Full Paper

Ask AI

Bookmark

This review aims to explore the methodologies and challenges of using machine learning for synthetic ultrasound generation in radiology.
Analyzed nineteen studies on synthetic ultrasound generation methods.
Identified three primary strategies: unconditional generation, conditional generation, and domain translation.
Evaluated models using expert assessment and Fréchet Inception Distance.
Synthetic ultrasound generation shows potential for augmenting training datasets.
Current limitations include the need for extensive training datasets and manual annotations.
Insufficient exploration of incorporating new domain knowledge hampers clinical implementation.

No takes yet. Share an insight, caveat, or question.

Scoping review analyzes synthetic ultrasound generation methods in radiology, highlighting their limitations.

Mendez et al. (2023) studied this question.

View Full Paper

Ask AI

Bookmark