人工智能在内镜下结直肠肿瘤诊断中的应用

Artificial Intelligence in Endoscopic Diagnosis of Colorectal Neoplasia

结直肠癌是全球第三大常见癌症,良好的内镜下筛查项目有望降低结直肠癌的发病率和死亡率。随着计算机技术的不断提高及大数据时代的到来,人工智能技术辅助内镜下疾病诊断的相关研究蓬勃发展。结肠镜检查中的病变检测和病变定性以及计算机辅助质量改进是人工智能在胃肠病学中的主要临床应用,到目前为止已经发表了较多研究成果。本文介绍了常用的深度学习模型架构,并针对人工智能在结直肠病变检测和诊断中应用的现有临床证据进行总结,探讨未来的发展方向。

Colorectal cancer is the third most common cancer in the world,and a good endoscopic screening programme is expected to reduce the morbidity and mortality of colorectal cancer.With the continuous improvement of computer technology and the advent of the big data era,research related to artificial intelligence technology-assisted endoscopic disease diagnosis has flourished.Lesion detection,lesion characterization and computed aid quality improvement in colonoscopy are the main clinical applications of artificial intelligence in gastroenterology,and more evidences have been published so far.This paper introduced commonly used deep learning model architectures,summarized the available clinical evidence for the application of artificial intelligence in colorectal lesion detection and discussed and discussed future directions.