Ham Da Yeon, Jang Hyun Joo, Kae Sea Hyub, Oh Chang Kyo, Hong Sungjin, Lee Jae Gon
Division of Gastroenterology, Department of Internal Medicine, Hallym University Dongtan Sacred Heart Hospital, Hallym University College of Medicine, Hwaseong, Republic of Korea.
Division of Gastroenterology, Department of Internal Medicine, Hallym University Kangnam Sacred Heart Hospital, Hallym University College of Medicine, Hwaseong, Republic of Korea.
J Dig Dis. 2025 Jan-Feb;26(1-2):80-87. doi: 10.1111/1751-2980.13340. Epub 2025 Apr 2.
This study aimed to develop a computer-aided diagnosis (CADx) model using an automated deep learning (DL) program to classify low- and high-risk adenomas among colorectal polyps ≤ 10 mm with standard white-light endoscopy.
Still images of colorectal adenomas ≤ 10 mm were extracted. High-risk adenomas were defined as high-grade dysplasia or adenomas with villous histology. Neuro-T version 3.2.1 (Neurocle Inc., Seoul, Republic of Korea), an automated DL software, was used for DL. Accuracy, precision, recall, and F1 score of the DL model were calculated. Endoscopy experts and trainees were invited to diagnose endoscopic images to compare their diagnostic accuracy with that of the DL model.
A total of 2696 endoscopic images (2460 images of low-grade and 236 of high-grade adenomas) were used for training the DL model. In classifying high- and low-risk adenomas in the external validation dataset (398 images of low-grade and 41 images of high-grade adenomas), the model demonstrated 93.8% accuracy, 81.0% precision, 85.7% recall, and 83.3% F1 score overall. The area under the receiver operating characteristic curve for classifying high- and low-risk adenomas was 0.910 and 0.914, respectively. The expert endoscopists and trainees showed an overall accuracy of 95.1% and 79.7%, respectively, for discriminating high- and low-risk adenomas in the external validation dataset.
The CADx model established by the automated DL program showed high diagnostic performance in differentiating high- and low-risk adenomas among colorectal polyps ≤ 10 mm. The performance of the model was comparable to the experts and superior to the trainees.
本研究旨在开发一种计算机辅助诊断（CADx）模型，该模型使用自动化深度学习（DL）程序，通过标准白光内镜对直径≤10mm的大肠息肉中的低风险和高风险腺瘤进行分类。
提取直径≤10mm的大肠腺瘤的静态图像。高风险腺瘤定义为高级别异型增生或具有绒毛组织学特征的腺瘤。使用自动化DL软件Neuro-T版本3.2.1（韩国首尔Neurocle公司）进行深度学习。计算DL模型的准确率、精确率、召回率和F1分数。邀请内镜专家和实习生对内镜图像进行诊断，以将他们的诊断准确性与DL模型的诊断准确性进行比较。
总共2696张内镜图像（2460张低级别腺瘤图像和236张高级别腺瘤图像）用于训练DL模型。在对外部验证数据集（398张低级别腺瘤图像和41张高级别腺瘤图像）中的高风险和低风险腺瘤进行分类时，该模型总体上表现出93.8%的准确率、81.0%的精确率、85.7%的召回率和83.3%的F1分数。用于区分高风险和低风险腺瘤的受试者工作特征曲线下面积分别为0.910和0.914。在外部验证数据集中，专家内镜医师和实习生区分高风险和低风险腺瘤的总体准确率分别为95.1%和79.7%。
由自动化DL程序建立的CADx模型在区分直径≤10mm的大肠息肉中的高风险和低风险腺瘤方面显示出较高的诊断性能。该模型的性能与专家相当，优于实习生。
