Friday, June 23, 2017 - 16:45 to 18:00
Real-Time Instrument Scene Detection in Screening GI Endoscopic Procedures
Here we describe a new and effective real-time solution for detecting video segments showing an instrument used during diagnostic or therapeutic operations in endoscopic procedures. In addition, we present a new method to create training data: similarity-based data augmentation. This method automates most of the creation of a large training dataset and prevents extensive manual effort to collect and annotate training data by domain experts. Convolutional Neural Network (CNN) analysis using the training data collected with similarity-based data augmentation yields an average F1 score very close to that of the CNN analysis using a large manually collected training dataset.
Chuanhai Zhang's picture
Chuanhai Zhang
Iowa State University (USA)
Wallapak Tavanapong's picture
Wallapak Tavanapong
Johnny Wong's picture
Johnny Wong
Piet C. de Groen's picture
Piet C. de Groen
Junghwan Oh's picture
Junghwan Oh