Lei Changda, Kan Xiuji, Ouyang Yifan, Mei Yutong, Guo Yunbo, Hong Kaicheng, Li Junbo, Wang Bilin, Li Rui
Department of Gastroenterology, The First Affiliated Hospital of Soochow University, Suzhou, China.
Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Science, Suzhou, China.
Ann Med. 2025 Dec;57(1):2523565. doi: 10.1080/07853890.2025.2523565. Epub 2025 Jun 28.
Narrow band imaging (NBI) can assist endoscopists in detecting early gastric cancer (EGC) more easily, but its widespread use is hindered by economic cost and technical property rights. We aim to realize the conversion of white light endoscopy (WLE) images into virtual narrow band imaging (Vir-NBI) images using stable diffusion.
Endoscopic images were retrospectively collected from 325 patients who underwent endoscopic submucosal dissection (ESD). A total of 273 NBI images from 218 patients were used to fine-tune stable diffusion, which then converted 111 WLE images from 107 patients into Vir-NBI images. Endoscopists assessed the images and evaluated their effectiveness in diagnosing EGC and depicting lesion margins in the form of WLE, NBI, and Vir-NBI image pairs.
Compared with WLE images, Vir-NBI images have better quality. The accuracy of junior endoscopists in diagnosing EGC by observing WLE images alone, simultaneous WLE and NBI images, and simultaneous WLE and Vir-NBI images were 61.26%, 79.28% and 81.08%, respectively. For intermediate endoscopists, the diagnostic accuracy was 72.07%, 86.79% and 84.68%, respectively. For senior endoscopists, the diagnostic accuracy was 80.18%, 95.50% and 92.79%, respectively. In addition,Vir-NBI images had higher area concordance rate andsuccessful whole-lesion diagnosis than WLE images (43.85% vs 39.32%, < 0.001) (45.33% vs 32.87%, < 0.001).
Vir-NBI images has similar observation effect with real NBI image, which helps endoscopists better visualize the lesion structure, thus improving the accuracy of EGC diagnosis.
窄带成像（NBI）可帮助内镜医师更轻松地检测早期胃癌（EGC），但其广泛应用受到经济成本和技术产权的阻碍。我们旨在利用稳定扩散实现白光内镜（WLE）图像向虚拟窄带成像（Vir-NBI）图像的转换。
回顾性收集325例行内镜黏膜下剥离术（ESD）患者的内镜图像。使用来自218例患者的273张NBI图像对稳定扩散进行微调，然后将来自107例患者的111张WLE图像转换为Vir-NBI图像。内镜医师以WLE、NBI和Vir-NBI图像对的形式评估图像，并评价其在诊断EGC和描绘病变边界方面的有效性。
与WLE图像相比，Vir-NBI图像质量更好。初级内镜医师仅观察WLE图像、同时观察WLE和NBI图像以及同时观察WLE和Vir-NBI图像诊断EGC的准确率分别为61.26%、79.28%和81.08%。中级内镜医师的诊断准确率分别为72.07%、86.79%和84.68%。高级内镜医师的诊断准确率分别为80.18%、95.50%和92.79%。此外，Vir-NBI图像在病变面积一致性率和全病变成功诊断方面均高于WLE图像（43.85%对39.32%，P<0.001）（45.33%对32.87%，P<0.001）。
Vir-NBI图像与真实NBI图像具有相似的观察效果，有助于内镜医师更好地观察病变结构，从而提高EGC诊断的准确性。
