Medical needle tip tracking based on Optical Imaging and AI

Voices Powered byElevenlabs logo


summarize it

AI: The paper discusses the development and evaluation of a technology that combines optical imaging and AI-based algorithms for precise and efficient needle tip tracking during deep subsurface needle insertions. The proposed system demonstrates accurate and real-time tracking of the needle tip in experiments using rubber and porcine tissue phantoms. The paper also discusses the consistency of results across different phantoms, processing time, and the effect of exposure time on positional error. The architecture and training process of a CNN model for needle tip position and orientation estimation are described, and the results show promising accuracy. The paper introduces a new technology that has the potential to enhance the safety and efficiency of femoral artery insertion procedures and can be applied in various medical fields. The method for acquiring data for training and validating the system is explained, as well as different methods for needle tip tracking and the proposed novel method using an optical fiber embedded in the needle. The system setup and calibration procedure are also described.


Zhuoqi Cheng, Simon Lyck Bjært Sørensen, Mikkel Werge Olsen, René Lynge Eriksen, Thiusius Rajeeth Savarimuthu


Deep needle insertion to a target often poses a huge challenge, requiring a combination of specialized skills, assistive technology, and extensive training. One of the frequently encountered medical scenarios demanding such expertise includes the needle insertion into a femoral vessel in the groin. After the access to the femoral vessel, various medical procedures, such as cardiac catheterization and extracorporeal membrane oxygenation (ECMO) can be performed. However, even with the aid of Ultrasound imaging, achieving successful insertion can necessitate multiple attempts due to the complexities of anatomy and tissue deformation. To address this challenge, this paper presents an innovative technology for needle tip real-time tracking, aiming for enhanced needle insertion guidance. Specifically, our approach revolves around the creation of scattering imaging using an optical fiber-equipped needle, and uses Convolutional Neural Network (CNN) based algorithms to enable real-time estimation of the needle tip's position and orientation during insertion procedures. The efficacy of the proposed technology was rigorously evaluated through three experiments. The first two experiments involved rubber and bacon phantoms to simulate groin anatomy. The positional errors averaging 2.3+1.5mm and 2.0+1.2mm, and the orientation errors averaging 0.2+0.11rad and 0.16+0.1rad. Furthermore, the system's capabilities were validated through experiments conducted on fresh porcine phantom mimicking more complex anatomical structures, yielding positional accuracy results of 3.2+3.1mm and orientational accuracy of 0.19+0.1rad. Given the average femoral arterial radius of 4 to 5mm, the proposed system is demonstrated with a great potential for precise needle guidance in femoral artery insertion procedures. In addition, the findings highlight the broader potential applications of the system in the medical field.

Follow Us on


Add comment
Recommended SciCasts
Attention Is Not All You Need Anymore