Multi-Modal Classification of Polyp Malignancy using CNN Features with Balanced Class Augmentation

Colorectal polyps are an indicator of colorectal cancer (CRC). Classification of polyps during colonoscopy is still a challenge for which many medical experts have come up with visual models albeit with limited success. In this paper, a classification approach is proposed to differentiate between po...

Full description

Saved in:
Bibliographic Details
Main Authors: Fonolla, Roger, Sommen, Fons van der, Schreuder, Ramon M., Schoon, Erik J., de With, Peter H.N.
Format: Conference Proceeding
Language:English
Subjects:
Biomedical imaging
BLI
Blue Laser Imaging
CNN
Data Augmentation
Feature extraction
LCI
Linked Color Imaging
Polyp classification
Sensitivity
Support vector machines
SVM
Training
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Colorectal polyps are an indicator of colorectal cancer (CRC). Classification of polyps during colonoscopy is still a challenge for which many medical experts have come up with visual models albeit with limited success. In this paper, a classification approach is proposed to differentiate between polyp malignancy, using features extracted from the Global Average Pooling (GAP) layer of a Convolutional Neural Network (CNNs). Two recent endoscopic modalities are used to improve the algorithm prediction: Blue Laser Imaging (BLI) and Linked Color Imaging (LCI). Furthermore, a new strategy of per-class data augmentation is adopted to tackle an unbalanced class distribution and to improve the decision of the classifiers. As a result, we increase the performance compared to state-of-the-art methods (0.97 vs 0.90 AUC). Our method for automatic polyp malignancy classification facilitates future advances towards patient safety and may avoid time-consuming and costly histopathological assessment.
ISSN:1945-8452
DOI:10.1109/ISBI.2019.8759320