Page 153 - 南京医科大学自然版
P. 153

第45卷第10期                           南京医科大学学报(自然科学版)
                 2025年10月                   Journal of Nanjing Medical University(Natural Sciences)     ·1521 ·


               ·综     述·

                人工智能在消化道早癌诊疗中的应用进展



                阙煜轩,周晓颖      *
                南京医科大学第一附属医院消化内科,江苏 南京                  210029




               [摘   要] 消化道早癌(early gastrointestinal cancer,EGC)的早期症状不明显且筛查率低,导致多数患者确诊时已为中晚期,预
                后较差。因此,早期诊断和及时治疗对改善患者预后至关重要。近年来,人工智能(artificial intelligence,AI)技术能够通过高
                精度的图像分析和数据处理,提高早期病变的检出率和诊断准确性,从而实现早发现、早诊断、早治疗,改善患者预后。但同
                时,AI也面临训练数据不足、算法偏差、各地区发展不均衡等问题,需要进一步发展改进。文章全面回顾了AI在EGC诊疗中的
                应用现状,探讨其优势、挑战及未来发展方向,以期为相关领域的研究者和临床医生提供有价值的参考。
               [关键词] 人工智能;消化道早癌;内镜检查;诊断;治疗
               [中图分类号] R735                    [文献标志码] A                       [文章编号] 1007⁃4368(2025)10⁃1521⁃08
                doi:10.7655/NYDXBNSN250672


                Application progress of artificial intelligence in the diagnosis and treatment of early

                gastrointestinal cancers
                QUE Yuxuan,ZHOU Xiaoying  *
                Department of Gastroenterology,the First Affiliated Hospital of Nanjing Medical University,Nanjing 210029,China


               [Abstract] Early gastrointestinal cancer(EGC)has subtle early symptoms and low screening rates,which leads to most patients
                being diagnosed at the middle or advanced stages,resulting in poor prognoses. Therefore,early diagnosis and timely treatment are
                crucial for improving patient outcomes. In recent years,artificial intelligence(AI)technology has been able to enhance the detection
                rate and diagnostic accuracy of early lesions through high ⁃ precision image analysis and data processing,thereby achieving early
                detection,early diagnosis,and early treatment to improve patient prognoses. However,AI also faces challenges such as insufficient
                training data,algorithm bias,and uneven development across regions,which need to be addressed in future advancements. This review
                aims to provide a comprehensive overview of the current applications of AI in the diagnosis and treatment of EGC,exploring its
                advantages,challenges,and future directions to offer valuable references for researchers and clinicians in related fields.
               [Key words] artificial intelligence;early gastrointestinal cancer;endoscopy;diagnosis;treatment
                                                                        [J Nanjing Med Univ,2025,45(10):1521⁃1527,1536]




                    消化道早癌(early gastrointestinal cancer,EGC)      中晚期,错过最佳治疗时机 。在我国,部分消化道
                                                                                          [1]
                主要包括食管癌、胃癌和结直肠癌(colorectal cancer,                肿瘤如食管癌、胃癌的发病率很高,约占全球的一
                CRC)的早期病变,其患病率逐年上升,且起病隐匿、                         半。EGC 若未及时发现和治疗,往往进展迅速,导
                早期症状通常不明显,或仅表现出一些非特异性症                            致患者医疗负担沉重,生活质量下降且死亡率升
                状,如腹胀、嗳气等,待出现显著症状时多已发展为                           高。早期筛查和诊断对于提高患者的生存率至关
                                                                  重要。
                                                                      近年来,人工智能(artificial intelligence,AI)技
               [基金项目] 国家自然科学基金青年项目(82100594);江苏
                                                                  术广泛应用于病理学、影像学等医学领域,已成为
                省大学生创新训练项目(国家级,202410312046Z)
                                                                  临床工作的重要辅助          [2-3] 。AI 能够从大量的医学影
                ∗
                 通 信 作 者(Corresponding author),E ⁃ mail:zhouxiaoy⁃
                ing0926@njmu.edu.cn(ORCID:0000⁃0002⁃6529⁃0243)    像和病理数据中学习早期癌症的特征,识别出微小
   148   149   150   151   152   153   154   155   156   157   158