Shiho Yagasaki
Papers
1
Total Citations
2
H-Index
1
About
Shiho Yagasaki is a researcher whose work sits at the intersection of ultrasound physics, deep learning, and therapeutic medical imaging. Her primary research focus is on overcoming fundamental limitations in ultrasound-guided therapy, particularly the problem of acoustic shadowing—a common artifact that obscures critical anatomical structures during procedures. Yagasaki’s most notable contribution is the development of a novel complementation method that employs a convolutional neural network (CNN) to reconstruct and fill in acoustic shadow regions in real-time ultrasound images. This innovation, detailed in her 2021 paper, offers a practical, data-driven solution to enhance image quality and procedural accuracy in therapeutic contexts, such as focused ultrasound ablation or needle guidance. While her citation count is currently modest, the work represents a forward-looking approach to integrating AI with medical acoustics, addressing a persistent challenge in the field. Yagasaki’s research is particularly relevant for students and engineers interested in applying machine learning to improve the safety and efficacy of non-invasive therapies, and it signals a promising trajectory for future contributions in computational ultrasound.
Research Focus
Key Achievements
Top Papers
- 1