Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China; Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China; Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China.
Department of Gastroenterology, Shenzhen Hospital of Southern Medical University, Shenzhen, China.
Gastrointest Endosc. 2022 Jun;95(6):1186-1194.e3. doi: 10.1016/j.gie.2021.11.049. Epub 2021 Dec 14.
The optical diagnosis of colorectal cancer (CRC) invasion depth with white light (WL) and image-enhanced endoscopy (IEE) remains challenging. We aimed to construct and validate a 2-modal deep learning-based system, incorporated with both WL and IEE images (named Endo-CRC) in estimating the invasion depth of CRC.
Samples were retrospectively obtained from 3 hospitals in China. We combined WL and IEE images into image pairs. Altogether, 337,278 image pairs from 268 noninvasive and superficial CRC and 181,934 image pairs from 82 deep CRC were used for training. A total of 296,644 and 4528 image pairs were used for internal and external tests and for comparison with endoscopists. Thirty-five videos were used for evaluating the real-time performance of the Endo-CRC system. Two deep learning models, solely using either WL (model W) or IEE images (model I), were constructed to compare with Endo-CRC.
The accuracies of Endo-CRC in internal image tests with and without advanced CRC were 91.61% and 93.78%, respectively, and 88.65% in the external test, which did not include advanced CRC. In an endoscopist-machine competition, Endo-CRC achieved an expert comparable accuracy of 88.11% and the highest sensitivity compared with all endoscopists. In a video test, Endo-CRC achieved an accuracy of 100.00%. Compared with model W and model I, Endo-CRC had a higher accuracy (per image pair: 91.61% vs 88.27% compared with model I and 91.61% vs 81.32% compared with model W).
The Endo-CRC system has great potential for assisting in CRC invasion depth diagnosis and may be well applied in clinical practice.
白光（WL）和图像增强内镜（IEE）下结直肠癌（CRC）侵袭深度的光学诊断仍然具有挑战性。我们旨在构建和验证一种基于 2 种模式的深度学习系统，该系统结合了 WL 和 IEE 图像（命名为 Endo-CRC），用于估计 CRC 的侵袭深度。
本研究回顾性地从中国的 3 家医院获取样本。我们将 WL 和 IEE 图像组合成图像对。总共使用了 268 例非侵袭性和表浅 CRC 的 337278 对图像和 82 例深部 CRC 的 181934 对图像进行训练。总共使用了 296644 对和 4528 对图像进行内部和外部测试，并与内镜医生进行比较。还使用了 35 个视频来评估 Endo-CRC 系统的实时性能。构建了仅使用 WL（模型 W）或 IEE 图像（模型 I）的 2 种深度学习模型，并与 Endo-CRC 进行比较。
Endo-CRC 在内部图像测试中对有和无高级 CRC 的准确率分别为 91.61%和 93.78%，外部测试（不包括高级 CRC）的准确率为 88.65%。在内镜医生与机器的竞争中，Endo-CRC 达到了与专家相当的准确率 88.11%，并且与所有内镜医生相比具有最高的敏感性。在视频测试中，Endo-CRC 的准确率达到了 100.00%。与模型 W 和模型 I 相比，Endo-CRC 的准确率更高（每对图像：与模型 I 相比为 91.61%，与模型 W 相比为 91.61%）。
Endo-CRC 系统在 CRC 侵袭深度诊断方面具有很大的潜力，可能在临床实践中得到很好的应用。
