M2CAI Workflow Challenge: Convolutional Neural Networks with Time Smoothing and Hidden Markov Model for Video Frames Classification

TL;DR

This paper presents a method for classifying endoscopic video frames by combining a fine-tuned Residual Network-200 with temporal smoothing techniques, including averaging and Hidden Markov Models, achieving top performance in the M2CAI Workflow challenge.

Contribution

It introduces a novel combination of deep learning with temporal smoothing and HMMs for improved video frame classification in medical procedures.

Findings

Achieved top three performance in the M2CAI challenge

Demonstrated effectiveness of temporal smoothing methods

Validated the use of fine-tuned Residual Networks for medical video analysis

Abstract

Our approach is among the three best to tackle the M2CAI Workflow challenge. The latter consists in recognizing the operation phase for each frames of endoscopic videos. In this technical report, we compare several classification models and temporal smoothing methods. Our submitted solution is a fine tuned Residual Network-200 on 80% of the training set with temporal smoothing using simple temporal averaging of the predictions and a Hidden Markov Model modeling the sequence.