Abstract:
In this paper, we present a robust method to improve the accuracy of phases segmentation problem in a specified surgical workflow (SW) by learning a topic model from the ...Show MoreMetadata
Abstract:
In this paper, we present a robust method to improve the accuracy of phases segmentation problem in a specified surgical workflow (SW) by learning a topic model from the optical flow (OF) motion features of general working contexts, such as the medical staffs, equipments and materials. We have an awareness of such working contexts by capturing the SW with multiple synchronized cameras. The main problems of the previous method, which are the limitation of topics number, susceptibility to noise, and losing easily important features, were solved by using a foreground detection method, conducting new robust OF extraction method, and adopting k-means clustering to normalize the features. The robustness of our method is validated by conducting experiments of up to 12 phases SW with the average length of each SW is longer than 12 minutes. The max average accuracy achieved after applying leave-one-out cross-validation, is 91.5%, which is a very promising result.
Date of Conference: 13-15 December 2016
Date Added to IEEE Xplore: 09 February 2017
ISBN Information:
Electronic ISSN: 2474-2325