A CNN CADx System for Multimodal Classification of Colorectal Polyps Combining WL, BLI, and LCI Modalities

Abstract

Colorectal polyps are critical indicators of colorectal cancer (CRC). Blue Laser Imaging and Linked Color Imaging are two modalities that allow improved visualization of the colon. In conjunction with the Blue Laser Imaging (BLI) Adenoma Serrated International Classification (BASIC) classification, endoscopists are capable of distinguishing benign and pre-malignant polyps. Despite these advancements, this classification still prevails a high misclassification rate for pre-malignant colorectal polyps. This work proposes a computer aided diagnosis (CADx) system that exploits the additional information contained in two novel imaging modalities, enabling more informative decision-making during colonoscopy. We train and benchmark six commonly used CNN architectures and compare the results with 19 endoscopists that employed the standard clinical classification model (BASIC). The proposed CADx system for classifying colorectal polyps achieves an area under the curve (AUC) of 0.97. Furthermore, we incorporate visual explanatory information together with a probability score, jointly computed from White Light, Blue Laser Imaging, and Linked Color Imaging. Our CADx system for automatic polyp malignancy classification facilitates future advances towards patient safety and may reduce time-consuming and costly histology assessment.

Intelligent recognition of colorectal cancer combining application of computer-assisted diagnosis with deep learning approaches

“…While performing the computer aided diagnosis (CAD) it's tend to fuse with the short designate the elements of a CNN. This is jointly which means it will be used to performing the CNN for classification [15], [16]. A CNN looks amazingly close to the usual neural networks among the feeling of being created by neurons with their different weights, biases, and activation functions.…”

Artificial intelligence for the early detection of colorectal cancer: A comprehensive review of its advantages and misconceptions

“…The advantage of the E2E approach is the possibility of designing more complex multitasking systems: Detecting polyps and then identifying whether the detected polyp is hyperplastic or adenomatous[ 50 ]. Information about whether a polyp can be malignant will assist the clinician in making a better clinical decision (to remove or not the polyp)[ 51 ].…”

Colorectal Polyp Classification from White-light Colonoscopy Images via Domain Alignment

“…Colorectal cancer (CRC) is one of the most common malignancies with a high mortality rate around the world [1]. Colorectal polyps are recognized as indicators of CRC, and they are roughly classified into two categories: hyperplastic and adenomatous [2]. Hyperplastic polyps are benign while adenomatous polyps have a high possibility of malignant transformation.…”

“…For example, Usami et al [11] proposed to distinguish benign/malignant polyps using WL, dye, and NBI images. In [2], authors achieved the highest accuracy of 95% by combining WL, BLI, and Linked Color Imaging (LCI) modalities.…”