Deep Learning Based Multi-Label Classification for Surgical Tool Presence Detection in Laparoscopic Videos

Abstract

Laparoscopic surgery, Modern surgery, where the surgery is performed far away from the patient by inserting small incisions on the patient's body and the surgery is performed with a help of a video recorder and through which the doctor performs the surgery. The computer assisted intervention are increasing exponentially and the need for accurate and reliable intervention is very important because of the domain which is very critical. Efforts have made to develop a system that is both fast and accurate approach but it is still an active area of research due its importance. Some applications which involve identifying the location of surgical tool at the given frame, identifying what tools are present in the given frame and many more applications. With the advance of deep learning models, the computer Assisted intervention are getting its reward and many papers have been published in this domain recently. In this thesis, a Deep learning based multi-label classification method for identifying surgical tools in a given frame was developed and it was able to beat other methods that participated in the competition. The pipeline consists of Video to image frame conversion, Model training with real-time data augmentation, ensemble methods for combining the models. The model mainly consists of Convolutional neural network with many layers. The key concept for performing a best state of the art method was to combine the two state of the art method and evaluate the test set. We use Inception architecture and the standard feed-forward architecture for performing the prediction. This method was able to beat other results and was able to get the first place in MICCAI challenge. The results was evaluated by MICCAI conference and the data was provided by them as well.