Unsupervised Trajectory Segmentation and Promoting of Multi-Modal Surgical Demonstrations

TL;DR

This paper introduces a fast unsupervised method combining video and kinematic data for surgical trajectory segmentation, employing deep learning and a promoting procedure to enhance accuracy and reduce over-segmentation in robot-assisted surgery.

Contribution

The paper proposes a novel unsupervised deep learning approach with a promoting step to improve surgical trajectory segmentation accuracy and efficiency.

Findings

Achieves higher segmentation accuracy than state-of-the-art methods.

Operates faster with reduced over-segmentation.

Effective noise filtering with wavelet transform.

Abstract

To improve the efficiency of surgical trajectory segmentation for robot learning in robot-assisted minimally invasive surgery, this paper presents a fast unsupervised method using video and kinematic data, followed by a promoting procedure to address the over-segmentation issue. Unsupervised deep learning network, stacking convolutional auto-encoder, is employed to extract more discriminative features from videos in an effective way. To further improve the accuracy of segmentation, on one hand, wavelet transform is used to filter out the noises existed in the features from video and kinematic data. On the other hand, the segmentation result is promoted by identifying the adjacent segments with no state transition based on the predefined similarity measurements. Extensive experiments on a public dataset JIGSAWS show that our method achieves much higher accuracy of segmentation than state-of-the-art methods in the shorter time.