Tool and Phase recognition using contextual CNN features
This work addresses surgical workflow analysis for medical applications, but it is incremental as it builds on existing transfer learning and contextual feature methods.
The authors tackled surgical tool and phase recognition by proposing a transfer learning method using ImageNet features, contextual features, and time series analysis with random forest classification, achieving encouraging results on the M2CAI16 challenge datasets through leave-one-out cross-validation.
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.