Tool and Phase recognition using contextual CNN features

TL;DR

This paper introduces a transfer learning approach that uses contextual CNN features combined with time series analysis and random forests for surgical tool and phase recognition, showing promising results on M2CAI16 datasets.

Contribution

It presents a novel pipeline integrating transfer learning, contextual feature generation, and time series analysis for improved surgical phase and tool recognition.

Findings

Encouraging results with leave-one-out cross validation

Effective combination of CNN features and temporal analysis

Improved accuracy over baseline methods

Abstract

A transfer learning method for generating features suitable for surgical tools and phase recognition from the ImageNet classification features [1] is proposed here. In addition, methods are developed for generating contextual features and combining them with time series analysis for final classification using multi-class random forest. The proposed pipeline is tested over the training and testing datasets of M2CAI16 challenges: tool and phase detection. Encouraging results are obtained by leave-one-out cross validation evaluation on the training dataset.