Abstract
Soft tissue deformation and ruptures complicate needle placement. However, ruptures at tissue interfaces also contain information which helps physicians to navigate through different layers. This navigation task can be challenging, whenever ultrasound (US) image guidance is hard to align and externally sensed forces are superimposed by friction. We propose an experimental setup for reproducible needle insertions, applying optical coherence tomography (OCT) directly at the needle tip as well as external US and force measurements. Processing the complex OCT data is challenging as the penetration depth is limited and the data can be difficult to interpret. Using a machine learning approach, we show that ruptures can be detected in the complex OCT data without additional external guidance or measurements after training with multi-modal ground-truth from US and force. We can detect ruptures with accuracies of 0.94 and 0.91 on homogeneous and inhomogeneous phantoms, respectively, and 0.71 for ex-situ tissues. We propose an experimental setup and deep learning based rupture detection for the complex OCT data in front of the needle tip, even in deeper tissue structures without the need for US or force sensor guiding. This study promises a suitable approach to complement a robust robotic needle placement.
Highlights
N EEDLE placement is a challenging task in different medical applications
For combining intensity and phase of the complex optical coherence tomography (OCT) data, we introduce a method based on using a support vector machine (SVM) [31]
We evaluate the receiver operating characteristics (ROC) for different combinations of the rupture extraction scaling factors p for all modalities using an interval of pi ∈ [0.2, 0.8]
Summary
Another example is the placement of needles to administer epidural anesthesia, where the physician penetrates a number of tissue structures and needs to stop directly behind the ligamentum flavum to reach the small epidural space of a few millimeters length. Several tissue structures with varying elasticities are punctured during needle insertions. Experienced physicians typically rely on the haptic impression at the needle shaft to navigate. Sometimes they can identify tissue structures, as ruptures of tissue layers can be felt at the shaft, e.g., during liver biopsies [3]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call