March 3, 2026Open Access

Semi-supervised learning in prostate MRI tumor detection approaches fully supervised performance on external validation

Puntos clave

Performance metrics show semi-supervised learning matches fully supervised methods for detecting prostate tumors.
Incorporating pseudo-labeling and consistency regularization enhances diagnostic tool efficiency with fewer annotations.
The approach utilizes diverse data to achieve detection accuracy comparable to traditional practices in prostate MRI.
This method highlights the potential for scalable automated tools, addressing clinical workflow demands effectively.

Resumen

Question The need for extensive expert voxel-level annotations delays the development of AI-based prostate cancer diagnostic tools and their implementation in clinical practice. Findings The combination of pseudo-labeling with consistency regularization achieved performance comparable to that of fully supervised methods, demonstrating that data diversity matches the impact of expert annotation volume. Clinical relevance Semi-supervised learning reduces dependence on expert annotations while maintaining detection accuracy, enabling the development of scalable, automated diagnostic tools for prostate cancer amid growing clinical workflow demands.

Me gusta

Guardar

Ver artículo completo