Abstract
Background: Classification of colorectal neoplasms during colonoscopic examination is important to avoid unnecessary endoscopic biopsy or resection. This study aimed to develop and validate deep learning models that automatically classify colorectal lesions histologically on white-light colonoscopy images. Methods: White-light colonoscopy images of colorectal lesions exhibiting pathological results were collected and classified into seven categories: stages T1-4 colorectal cancer (CRC), high-grade dysplasia (HGD), tubular adenoma (TA), and non-neoplasms. The images were then re-classified into four categories including advanced CRC, early CRC/HGD, TA, and non-neoplasms. Two convolutional neural network models were trained, and the performances were evaluated in an internal test dataset and an external validation dataset. Results: In total, 3828 images were collected from 1339 patients. The mean accuracies of ResNet-152 model for the seven-category and four-category classification were 60.2% and 67.3% in the internal test dataset, and 74.7% and 79.2% in the external validation dataset, respectively, including 240 images. In the external validation, ResNet-152 outperformed two endoscopists for four-category classification, and showed a higher mean area under the curve (AUC) for detecting TA+ lesions (0.818) compared to the worst-performing endoscopist. The mean AUC for detecting HGD+ lesions reached 0.876 by Inception-ResNet-v2. Conclusions: A deep learning model presented promising performance in classifying colorectal lesions on white-light colonoscopy images; this model could help endoscopists build optimal treatment strategies.
Highlights
Colorectal cancer (CRC) is one of the leading causes of death in the world, and the third most common malignancy in Korea [1,2]
This study aimed to develop and assess convolutional neural network (CNN) models which automatically categorize colorectal lesions into several stages ranging from non-neoplastic lesions to advanced colorectal cancer (CRC) with conventional white-light colonoscopy images
Static white-light colonoscopy images for any colorectal lesion of the patients were collected from the picture archiving and communication system (PACS) of the involved hospitals in a resolution of 640 × 480 pixels
Summary
Colorectal cancer (CRC) is one of the leading causes of death in the world, and the third most common malignancy in Korea [1,2]. Superfluous endoscopic resection or biopsy of diminutive non-neoplastic lesions increases unnecessary colorectal mucosal injury and medical economic burden [6,7,8]. For the optical diagnosis of colorectal lesions, several advanced endoscopic imaging technologies, including narrow-band imaging (NBI) with or without magnifying techniques, flexible spectral imaging color enhancement, or i-Scan digital contrast have been introduced and validated for efficacy [9,10,11]. Most studies focused on the differentiation of neoplastic lesions from non-neoplastic lesions using specific images from magnifying NBI or endocytoscopy [21,22,24], which has limited the application in real-world practice. This study aimed to develop and assess convolutional neural network (CNN) models which automatically categorize colorectal lesions into several stages ranging from non-neoplastic lesions to advanced CRC with conventional white-light colonoscopy images
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
