Comparison of Mechanistic and Learning-based Tip Force Estimation on Tendon-driven Soft Robotic Catheters.

Researchers have adopted mechanistic and learning-based approaches for tip force estimation on soft robotic catheters. Typically the literature attributes the mech-anistic methods with more accuracy while indicating the learning-based methods outpace in computational time. In this study, a previously validated mechanistic tip force estimation method was compared with four learning-based methods, i.e. support-vector-regression (SVR), random-forest (RF), Ad-aBoost (Ada), and deep neural network (DNN). The learning-based methods were trained on experimental data acquired from a robotic catheter, developed in-house. The accuracy of force estimation using the five methods were compared with the ground truth forces in a teleoperated catheter manipulation test. Moreover, the capability of the learning-based models in contact detection, i.e., detection of the onset of tip contact, were compared with the ground truth. The results showed that the mechanical model had a mean-absolute error (MAE) of 8.8 mN while the MAE of SVR, RF, Ada, and DNN were 5.6, 5.2, 5.3, and 5.1 mN, respectively. Moreover, the accuracy and precision of the mechanistic model for contact detection was 89.2% and 91.7%, respectively, while these were 97.0%, 97.7%, 97.6%,and 97% and 97.9%, 98.3%, 97.8%, and 98.8% for the SVR, RF, Ada, and DNN, respectively. The comparison showed that with hyper-parameter optimization the learning-based models surpassed the mechanistic model in accuracy and precision, while both method approaches revealed acceptable performance for the proposed application.

Optical Fiber Array Sensor for Force Estimation and Localization in TAVI Procedure: Design, Modeling, Analysis and Validation.

Transcatheter aortic valve implantation has shown superior clinical outcomes compared to open aortic valve replacement surgery. The loss of the natural sense of touch, inherited from its minimally invasive nature, could lead to misplacement of the valve in the aortic annulus. In this study, a cylindrical optical fiber sensor is proposed to be integrated with valve delivery catheters. The proposed sensor works based on intensity modulation principle and is capable of measuring and localizing lateral force. The proposed sensor was constituted of an array of optical fibers embedded on a rigid substrate and covered by a flexible shell. The optical fibers were modeled as Euler-Bernoulli beams with both-end fixed boundary conditions. To study the sensing principle, a parametric finite element model of the sensor with lateral point loads was developed and the deflection of the optical fibers, as the determinant of light intensity modulation was analyzed. Moreover, the sensor was fabricated, and a set of experiments were performed to study the performance of the sensor in lateral force measurement and localization. The results showed that the transmitted light intensity decreased up to 24% for an external force of 1 N. Additionally, the results showed the same trend between the simulation predictions and experimental results. The proposed sensor was sensitive to the magnitude and position of the external force which shows its capability for lateral force measurement and localization.

Hybrid piezoresistive-optical tactile sensor for simultaneous measurement of tissue stiffness and detection of tissue discontinuity in robot-assisted minimally invasive surgery.

To compensate for the lack of touch during minimally invasive and robotic surgeries, tactile sensors are integrated with surgical instruments. Surgical tools with tactile sensors have been used mainly for distinguishing among different tissues and detecting malignant tissues or tumors. Studies have revealed that malignant tissue is most likely stiffer than normal. This would lead to the formation of a sharp discontinuity in tissue mechanical properties. A hybrid piezoresistive-optical-fiber sensor is proposed. This sensor is investigated for its capabilities in tissue distinction and detection of a sharp discontinuity. The dynamic interaction of the sensor and tissue is studied using finite element method. The tissue is modeled as a two-term Mooney­Rivlin hyperelastic material. For experimental verification, the sensor was microfabricated and tested under the same conditions as of the simulations. The simulation and experimental results are in a fair agreement. The sensor exhibits an acceptable linearity, repeatability, and sensitivity in characterizing the stiffness of different tissue phantoms. Also, it is capable of locating the position of a sharp discontinuity in the tissue. Due to the simplicity of its sensing principle, the proposed hybrid sensor could also be used for industrial applications.