Search for: All records

Lung cancer claims over 130,000 lives per year in the USA. For those with malignant tumors requiring resection, minimally invasive thoracic surgery via a video assisted or robotic approach is an alternative to highly invasive open thoracotomy (in which the chest is “cracked” open). This involves the insertion of 3-5 ports through the chest wall and the use of a camera and instruments mounted to rigid shafts, which are used to resect tissue in a deflated lung. One of these tools is typically a stapler which is able to simultaneously cut and seal the lung tissue. Tendon-driven continuum robots (TDCRs) are capable of curvilinear motions, which can add useful dexterity in constrained anatomical regions like the chest. However, the inherent flexibility of TDCRs presents challenges for integrating stapler-type end effectors. Lung staplers today are typically rigid tools because they require large axial forces to be transmitted along the tool shaft to fire staples. Such forces would apply large loads to curved continuum devices, changing their shapes and moving the end effector undesirably during staple firing. Low melting point alloys (LMPA) have been explored to stiffen substantially soft robots and compliant surgical devices. Here, we propose their use in a TDCR stapler to stiffen the tool shaft before staples are fired. Prior to stiffening, tendon actuation can provide enhanced maneuverability by curving the backbone compared to rigid staplers to position the stapler at the desired location. 

Devices enabled by artificial intelligence (AI) and machine learning (ML) are being introduced for clinical use at an accelerating pace. In a dynamic clinical environment, these devices may encounter conditions different from those they were developed for. The statistical data mismatch between training/initial testing and production is often referred to as data drift. Detecting and quantifying data drift is significant for ensuring that AI model performs as expected in clinical environments. A drift detector signals when a corrective action is needed if the performance changes. In this study, we investigate how a change in the performance of an AI model due to data drift can be detected and quantified using a cumulative sum (CUSUM) control chart. To study the properties of CUSUM, we first simulate different scenarios that change the performance of an AI model. We simulate a sudden change in the mean of the performance metric at a change-point (change day) in time. The task is to quickly detect the change while providing few false-alarms before the change-point, which may be caused by the statistical variation of the performance metric over time. Subsequently, we simulate data drift by denoising the Emory Breast Imaging Dataset (EMBED) after a pre-defined change-point. We detect the change-point by studying the pre- and post-change specificity of a mammographic CAD algorithm. Our results indicate that with the appropriate choice of parameters, CUSUM is able to quickly detect relatively small drifts with a small number of false-positive alarms. 

A medical robot can autonomously steer a needle to targets in vivo. 

Bronchoscopic diagnosis and intervention in the lung is a new frontier for steerable needles, where they have the potential to enable minimally invasive, accurate access to small nodules that cannot be reliably accessed today. However, the curved, flexible bronchoscope requires a much longer needle than prior work has considered, with complex interactions between the needle and bronchoscope channel, introducing new challenges in steerable needle control. In particular, friction between the working channel and needle causes torsional windup along the bronchoscope, the effects of which cannot be directly measured at the tip of thin needles embedded with 5 degree-of-freedom magnetic tracking coils. To compensate for these effects, we propose a new torsional deadband-aware Extended Kalman Filter to estimate the full needle tip pose including the axial angle, which defines its steering direction. We use the Kalman Filter estimates with an established sliding mode controller to steer along desired trajectories in lung tissue. We demonstrate that this simple torsional deadband model is sufficient to account for the complex interactions between the needle and endoscope channel for control purposes. We measure mean final targeting error of 1.36 mm in phantom tissue and 1.84 mm in ex-vivo porcine lung, with mean trajectory following error of 1.28 mm and 1.10 mm, respectively.