A Deep Convolutional Neural Network for the Detection of Polyps in Colonoscopy Images

TL;DR

This paper introduces a novel deep convolutional neural network model with unique convolutional kernels and data augmentation techniques for improved automatic detection of colonic polyps in colonoscopy images, addressing variability in appearance and shape.

Contribution

The study presents a new CNN architecture with multiple convolutional kernels and advanced data augmentation, enhancing polyp detection accuracy over existing methods.

Findings

Achieved higher precision and sensitivity in polyp detection.

Outperformed existing models in F1, F2 scores, and dice-coefficient.

Demonstrated robustness to scale, rotation, and shape variations.

Abstract

Computerized detection of colonic polyps remains an unsolved issue because of the wide variation in the appearance, texture, color, size, and presence of the multiple polyp-like imitators during colonoscopy. In this paper, we propose a deep convolutional neural network based model for the computerized detection of polyps within colonoscopy images. The proposed model comprises 16 convolutional layers with 2 fully connected layers, and a Softmax layer, where we implement a unique approach using different convolutional kernels within the same hidden layer for deeper feature extraction. We applied two different activation functions, MISH and rectified linear unit activation functions for deeper propagation of information and self regularized smooth non-monotonicity. Furthermore, we used a generalized intersection of union, thus overcoming issues such as scale invariance, rotation, and shape. Data augmentation techniques such as photometric and geometric distortions are adapted to overcome the obstacles faced in polyp detection. Detailed benchmarked results are provided, showing better performance in terms of precision, sensitivity, F1- score, F2- score, and dice-coefficient, thus proving the efficacy of the proposed model.