Authors:
Martin Kryl
;
Pavel Košan
;
Petr Včelák
and
Jana Klečková
Affiliation:
Department of Computer Science and Engineering, University of West Bohemia, Univerzitni 8, Plzen, Czech Republic
Keyword(s):
Medical Imaging, Deep Learning, U-Net, Clinical AI, Image Segmentation, Healthcare Technology.
Abstract:
As AI transforms medical imaging, this paper positions U-Net as a practical and enduring choice for segmentation tasks in constrained clinical environments. Despite rapid advancements in architectures like transformers and hybrid models, U-Net remains highly relevant due to its simplicity, efficiency, and interpretability, particularly in settings with limited computational resources and data availability. By exploring modifications such as residual connections and the Tversky loss function, we argue that incremental refinements to U-Net can bridge the gap between current clinical needs and the potential of more advanced AI tools. This paper advocates for a balanced approach, combining accessible enhancements with hybrid strategies, such as radiologist-informed labeling and advanced preprocessing, to ensure immediate impact while building a foundation for future innovation. U-Net’s adaptability positions it as both a cornerstone of today’s AI integration in healthcare and a stepping
stone toward adopting next-generation models.
(More)