University of Twente Student Theses
Deep Learning-Based Interpretation And Analysis Of Ultrasound Raw Data
Lan, B. (2024) Deep Learning-Based Interpretation And Analysis Of Ultrasound Raw Data.
|
PDF
39MB |
| Abstract: | This thesis has demonstrated that the A-mode ultrasound, when combined with the proposed deep learning techniques, holds significant potential for the high accuracy bone measurement and various types of robotic applications. With the accurate interpretation of the A-mode US raw signals, the methods have been successfully developed that it not only increase the precision of bone tracking in orthopedic surgery, but also enable the real-time anatomical region classification and dynamic muscle monitoring. Each chapter has contributed to a comprehensive understanding of how the enhanced capabilities be integrated into the practical, non-invasive tools for the clinical use. The CasAtt-UNet and SIRC-UNet models have shown high accuracy in the bone tracking, while the dual-attention framework for the muscle contraction prediction lead to an accurate muscle health monitoring. In the end, these findings not only pave the way for its broader application in healthcare settings, but also inspire the construction of an intelligent robotics that can perceive the surrounding environment. |
| Item Type: | Essay (Master) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 50 technical science in general, 54 computer science |
| Programme: | Electrical Engineering MSc (60353) |
| Link to this item: | https://purl.utwente.nl/essays/98976 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page