Building large mosaics of confocal endomicroscopic images using visual servoing
This paper presents an endomicroscopy-based visual servoing control scheme in order to perform very large field of view optical biopsies on soft tissues.
Probe-based Confocal Laser Endomicroscopy (pCLE) is a recent technology that allows to take optical biopsies in vivo and in situ in a minimally invasive way. Microscopic images are acquired in real-time using a small optical probe that contacts the tissue. Enhancing the field of view would help improving clinical analysis of pCLE data. It can be realized by sweeping the probe in contact with the tissue while collecting the video stream, and using a mosaicking algorithm to reconstruct a large mosaic. While most of the literature in this field has focused on image processing, little attention has been paid so far to the way the probe motion can be controlled. This is a crucial issue since the precision of the probe trajectory control drastically influences the quality of the final mosaic. Robotically controlled motion has the potential of providing enough precision to perform very large mosaicking.
Several challenges are associated with implementing such an approach. Firstly, probe-tissue contacts generate deformations that prevent from properly controlling the image trajectory. Secondly, minimally invasive robotic devices are likely to exhibit limited quality of the distal probe motion control at the microscopic scale. To cope with these problems visual servoing from real-time endomicroscopy images is proposed in this paper. It is implemented on two different devices (a high-accuracy industrial robot and a prototype minimally invasive device). Experiments on different kinds of environments (printed paper and ex vivo tissues) show that quality of the visually servoed probe motion is sufficient to build mosaics with minimal distortion in spite of disturbances. The high quality of probe motion control allows to robustly compute much larger mosaics than the state of the art. Read More…