Visual Features for Improving Endoscopic Bleeding Detection Using Convolutional Neural Networks

• Published in: Sensors (Basel, Switzerland) Switzerland), 2023-12, Vol.23 (24), p.9717
• Main Authors: Brzeski, Adam, Dziubich, Tomasz, Krawczyk, Henryk
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; artificial intelligence; Classification; computer vision algorithms; convolutional neural networks; Deep learning; Endoscopy; Image processing; Machine learning; medical image analysis; Medical imaging; Medical imaging equipment; Neural networks; Support vector machines; Tumors; Wavelet transforms
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23249717

The presented paper investigates the problem of endoscopic bleeding detection in endoscopic videos in the form of a binary image classification task. A set of definitions of high-level visual features of endoscopic bleeding is introduced, which incorporates domain knowledge from the field. The high-level features are coupled with respective feature descriptors, enabling automatic capture of the features using image processing methods. Each of the proposed feature descriptors outputs a feature activation map in the form of a grayscale image. Acquired feature maps can be appended in a straightforward way to the original color channels of the input image and passed to the input of a convolutional neural network during the training and inference steps. An experimental evaluation is conducted to compare the classification ROC AUC of feature-extended convolutional neural network models with baseline models using regular color image inputs. The advantage of feature-extended models is demonstrated for the Resnet and VGG convolutional neural network architectures.