Faculty of Health and Medical Sciences, University of Adelaide, Adelaide, South Australia, Australia; Department of Gastroenterology and Hepatology, Nagoya University Graduate School of Medicine, Nagoya, Aichi, Japan.
Australian Institute for Machine Learning, University of Adelaide, Adelaide, South Australia, Australia.
Gastrointest Endosc. 2020 Oct;92(4):891-899. doi: 10.1016/j.gie.2020.02.042. Epub 2020 Mar 4.
Endoscopy guidelines recommend adhering to policies such as resect and discard only if the optical biopsy is accurate. However, accuracy in predicting histology can vary greatly. Computer-aided diagnosis (CAD) for characterization of colorectal lesions may help with this issue. In this study, CAD software developed at the University of Adelaide (Australia) that includes serrated polyp differentiation was validated with Japanese images on narrow-band imaging (NBI) and blue-laser imaging (BLI).
CAD software developed using machine learning and densely connected convolutional neural networks was modeled with NBI colorectal lesion images (Olympus 190 series - Australia) and validated for NBI (Olympus 290 series) and BLI (Fujifilm 700 series) with Japanese datasets. All images were correlated with histology according to the modified Sano classification. The CAD software was trained with Australian NBI images and tested with separate sets of images from Australia (NBI) and Japan (NBI and BLI).
An Australian dataset of 1235 polyp images was used as training, testing, and internal validation sets. A Japanese dataset of 20 polyp images on NBI and 49 polyp images on BLI was used as external validation sets. The CAD software had a mean area under the curve (AUC) of 94.3% for the internal set and 84.5% and 90.3% for the external sets (NBI and BLI, respectively).
The CAD achieved AUCs comparable with experts and similar results with NBI and BLI. Accurate CAD prediction was achievable, even when the predicted endoscopy imaging technology was not part of the training set.
内镜指南建议遵循“如果光学活检准确，仅切除并丢弃”等政策。然而，预测组织学的准确性可能有很大差异。用于结直肠病变特征描述的计算机辅助诊断 (CAD) 可能有助于解决此问题。在这项研究中，阿德莱德大学（澳大利亚）开发的 CAD 软件包括锯齿状息肉的鉴别，使用窄带成像（NBI）和蓝激光成像（BLI）的日本图像进行了验证。
使用机器学习和密集连接卷积神经网络开发的 CAD 软件使用 NBI 结直肠病变图像（奥林巴斯 190 系列-澳大利亚）建模，并使用日本数据集对 NBI（奥林巴斯 290 系列）和 BLI（富士胶片 700 系列）进行验证。所有图像均根据改良的 Sano 分类与组织学相关联。CAD 软件使用澳大利亚 NBI 图像进行训练，并使用来自澳大利亚（NBI）和日本（NBI 和 BLI）的单独图像集进行测试。
使用 1235 个息肉图像的澳大利亚数据集作为训练、测试和内部验证集。使用 20 个 NBI 息肉图像和 49 个 BLI 息肉图像的日本数据集作为外部验证集。CAD 软件在内部集的平均曲线下面积（AUC）为 94.3%，在外部集（NBI 和 BLI）的 AUC 分别为 84.5%和 90.3%。
CAD 的 AUC 与专家相当，与 NBI 和 BLI 的结果相似。即使预测的内镜成像技术不是训练集的一部分，也可以实现准确的 CAD 预测。
