Publications by authors named "Takumi Fujibayashi"
Study on method of organ section retention and tracking through deep learning in automated diagnostic and therapeutic robotics.
Int J Comput Assist Radiol Surg
November 2023
Article Synopsis
- This study addresses the challenges of tracking kidney and liver organs during high-intensity focused ultrasound (HIFU) treatment, as respiratory movements can hinder precise cauterization and risk damage to surrounding tissues.
- The researchers developed and tested three methods (AEMA, AEMAD, AEMAD++) for estimating organ angles in ultrasound images, using a phantom model to create a dataset by capturing various images of the kidney.
- AEMAD++ was found to have the best performance in terms of accuracy (29.5%) and processing speed (3.20 FPS), indicating its potential for effective organ tracking in medical applications.
A VS ultrasound diagnostic system with kidney image evaluation functions.
Int J Comput Assist Radiol Surg
February 2023
Purpose: An inevitable feature of ultrasound-based diagnoses is that the quality of the ultrasound images produced depends directly on the skill of the physician operating the probe. This is because physicians have to constantly adjust the probe position to obtain a cross section of the target organ, which is constantly shifting due to patient respiratory motions. Therefore, we developed an ultrasound diagnostic robot that works in cooperation with a visual servo system based on deep learning that will help alleviate the burdens imposed on physicians.
View Article and Find Full Text PDF