Robust guidewire tracking under large deformations combining segment-like features (SEGlets).

Robust tracking of interventional tools, such as guidewires and catheters, in X-ray fluoroscopic video sequences has a wide range of clinical applications for endovascular procedures. Thus far, the tracking is usually achieved by finding the optimal displacement of the control points of a spline, which models the guidewire, between consecutive frames. The displacement of the control points is typically driven by a data term and smoothed by a regularization term. In the presence of large deformation and changes in length of the tool, the current tracking methods may fail to recover the guidewire motion. This can occur because of the limitation of the data and regularization terms, and the absence of an explicit solution for coping with elongations of the guidewire. The purpose of this paper is to present an algorithm that can robustly track guidewires under these challenging conditions. The algorithm is based on two main contributions: (a) new robust features termed SEGlets for segment-like features are introduced to overcome the limitations of the current data terms; (b) a tracking formulation based on the generation of tracking hypotheses by organizing the SEGlets in plausible guidewire shapes. The proposed method allows high flexibility of the guidewire between consecutive frames in contrast to the spline model, which can suffer from the limitations of the regularization terms. Furthermore, the technique models elongations of the guidewire which makes it possible for robust tracking under motion. A tool model which is recursively updated by employing a Kalman filter, is also proposed for modelling the regularization term. A detailed evaluation and a comparative study with three state-of-the-art guidewire tracking methods have been performed to demonstrate the potential clinical value of the technique. The proposed method achieves an overall guidewire tracking precision of 2.40 pixels, tip precision of 25.55 pixels, false tracking rate of 5.73%, missing tracking rate of 9.69%, and F1 score of 0.92. The implementation of the proposed technique and the three tracking methods will be made publicly available as software libraries.