引用本文
  • 于观贞,魏培莲,陈颖,朱明华.人工智能在肿瘤病理诊断和评估中的应用与思考[J].第二军医大学学报,2017,38(11):1349-1354    [点击复制]
  • YU Guan-zhen,WEI Pei-lian,CHEN Ying,ZHU Ming-hua.Artificial intelligence in pathological diagnosis and assessment of human solid tumor:application and thinking[J].Acad J Sec Mil Med Univ,2017,38(11):1349-1354   [点击复制]
【打印本页】 【下载PDF全文】 【HTML】 查看/发表评论下载PDF阅读器关闭

←前一篇|后一篇→

过刊浏览    高级检索

本文已被:浏览 1340次   下载 1906 本文二维码信息
码上扫一扫!
人工智能在肿瘤病理诊断和评估中的应用与思考
于观贞1*,魏培莲1,陈颖2,朱明华2
0
(1. 上海中医药大学附属龙华医院肿瘤科, 上海 200032;
2. 第二军医大学长海医院病理科, 上海 200433
*通信作者)
摘要:
人工智能在多个医学场景如疾病诊断、药物筛选、影像医学和护理医学等领域中取得了革命性的进步。病理切片属于二维图像,是人工智能的首要突破点。我国的医疗资源和病理资源丰富,而病理切片的标准化和数字化为人工智能的深度学习提供了大数据背景。我们在乳腺癌、胃癌和胆管癌病理人工智能方面进行了一系列研究,建立了标准的肿瘤细胞标注流程和深度学习流程,研发了肝门部胆管癌人工智能模型,但也发现了存在的问题,提出了解决方案。随着精准性的提高,病理人工智能有望很快进入临床实践。
关键词:  人工智能  病理诊断  胃肿瘤  乳腺肿瘤  胆管肿瘤
DOI:10.16781/j.0258-879x.2017.11.1349
投稿时间:2017-10-27修订日期:2017-11-05
基金项目:国家自然科学基金(30901794,81572856),上海市浦江人才计划项目(13PJD002),上海中医药大学附属龙华医院高层次人才引进项目(LH02.51.002).
Artificial intelligence in pathological diagnosis and assessment of human solid tumor:application and thinking
YU Guan-zhen1*,WEI Pei-lian1,CHEN Ying2,ZHU Ming-hua2
(1. Department of Oncology, Longhua Hospital Affiliated to Shanghai University of Traditional Chinese Medicine, Shanghai 200032, China;
2. Department of Pathology, Changhai Hospital, Second Military Medical University, Shanghai 200433, China
*Corresponding author)
Abstract:
Application of artificial intelligence has made revolutionary advances in many medical scenarios such as diagnosis, drug screening, medical imaging and nursing. Images of pathological sections (2D) are a preliminary breakthrough of artificial intelligence. Abundant medical and pathological resources, and standardization, digitization of pathological section images provide big data for the in-depth study of artificial intelligence. Through a series of research on artificial intelligence in pathologies of breast cancer, gastric cancer, and cholangiocarcinoma, we established a labeling standard of tumor cells and an in-depth learning process, and we also developed an artificial intelligence algorithm for hilar cholangiocarcinoma. However, there are still many problems and we tried to search for the solutions. With the improvement in precision of artificial intelligence diagnosis, pathology of artificial intelligence may be soon applied in future clinical practice.
Key words:  artificial intelligence  pathological diagnosis  stomach neoplasms  breast neoplasms  bile duct neoplasms