Abstract
Purpose
To develop and evaluate an approach to estimate the respiratory-induced motion of hepatic lesions.
Materials and methods
In this study, a correlation between the collected surrogate signals and the liver tumor respiratory motion is obtained using learning-based algorithms. A robotic phantom is developed which simulates the respiratory motion of the liver, the diaphragm, and the abdomen skin in two directions as superior-inferior (SI) and anterior-posterior (AP). The surrogate signals are collected by means of optical markers attached to the abdomen skin and tracked by a digital camera, in addition to an inertial measurement unit (IMU) fixed to the hub of a needle that is inserted into the tissue. A finite element model (FEM) is developed to study the effect of tissue and tumor location parameters on target motion.
Results
The estimation error of linear regression for the SI and AP directions has been respectively 1.37% and 2.87%, and for quadratic polynomial regression have been 0.76% and 2.41% on the data from the experiments.
Conclusion
Using more than one surrogate signals resulted in a about 0.5-6.5% decrease of the motion estimation error compared to using only one of the surrogates.
Keywords: hepatic tumor, motion estimation, respiratory motion, machine learning, robotic phantom, finite element analysis
To develop and evaluate an approach to estimate the respiratory-induced motion of hepatic lesions.
Materials and methods
In this study, a correlation between the collected surrogate signals and the liver tumor respiratory motion is obtained using learning-based algorithms. A robotic phantom is developed which simulates the respiratory motion of the liver, the diaphragm, and the abdomen skin in two directions as superior-inferior (SI) and anterior-posterior (AP). The surrogate signals are collected by means of optical markers attached to the abdomen skin and tracked by a digital camera, in addition to an inertial measurement unit (IMU) fixed to the hub of a needle that is inserted into the tissue. A finite element model (FEM) is developed to study the effect of tissue and tumor location parameters on target motion.
Results
The estimation error of linear regression for the SI and AP directions has been respectively 1.37% and 2.87%, and for quadratic polynomial regression have been 0.76% and 2.41% on the data from the experiments.
Conclusion
Using more than one surrogate signals resulted in a about 0.5-6.5% decrease of the motion estimation error compared to using only one of the surrogates.
Keywords: hepatic tumor, motion estimation, respiratory motion, machine learning, robotic phantom, finite element analysis
| Original language | English |
|---|---|
| Publication status | Published - 2019 |
| Event | 33rd International Conference on Computer Assisted Radiology and Surgery 2019 - Rennes Conference Center, Rennes, France Duration: 17 Jun 2019 → 21 Jun 2019 Conference number: 33 https://www.cars2019.org/ |
Conference
| Conference | 33rd International Conference on Computer Assisted Radiology and Surgery 2019 |
|---|---|
| Abbreviated title | CARS 2019 |
| Country/Territory | France |
| City | Rennes |
| Period | 17/06/19 → 21/06/19 |
| Internet address |