Robotically Surgical Vessel Localization Using Robust Hybrid Video Motion Magnification

Vessel and neurovascular bundle localization plays an essential role in endoscopic and robotic surgery. It still remains challenging to spare vessels and neurovascular bundles to avoid inadvertent injury due to limited visual and tactile perception of surgeons. This work assumes that surgeons have great difficulty in intuitively perceiving small pulsatile motion of vessels and neurovascular bundles from complex surgical field provided by endoscopic videos, and proposes a new surgical video pulsatile motion magnification method to help surgeons easily and precisely recognize vessels or neurovascular bundles by their visual systems. The new method consists of robust hybrid temporal filtering and deeply learned spatial decomposition. The proposed hybrid temporal filtering can significantly magnify pulsatile motion more consistent with reality and simultaneously keep non-pulsating regions in magnified videos almost identical to original videos, and learning-based spatial decomposition can reduce noise and ring artifacts in magnified videos. We evaluate our method on surgical videos acquired from robotic prostatectomy, with the experimental results showing that our method essentially outperforms current motion magnification approaches. In particular, visual quality and quantitative assessment of our method are certainly better than these methods.