中国癌症杂志 ›› 2021, Vol. 31 ›› Issue (2): 151-155.doi: 10.19401/j.cnki.1007-3639.2021.02.010

• 综述 • 上一篇    下一篇

基于深度学习的人工智能在数字病理学中的进展

杨 鑫  综述 ,章 真  审校   

  1. 复旦大学附属肿瘤医院放射治疗中心,复旦大学上海医学院肿瘤学系,上海 200032
  • 出版日期:2021-02-28 发布日期:2021-03-02
  • 通信作者: 章 真 E-mail:zhen_zhang6@gmail.com

Research progress of artificial intelligence based on deep learning in digital pathology

YANG Xin, ZHANG Zhen#br#   

  1. Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Department of Oncology, Shanghai Medical College, Fudan University, Shanghai 200032, China
  • Published:2021-02-28 Online:2021-03-02
  • Contact: ZHANG Zhen E-mail:zhen_zhang6@gmail.com

摘要: 全切片数字化图像扫描技术的进步促成了数字病理学的诞生。随着存储技术的提高和互联网技术与计算机技术的迅速发展,深度学习的方法被广泛应用于病理学图像的分析中,其目标是化解病理学图像冗余复杂的信息导致病理学医师诊断和分析困难的问题,减轻病理学医师日常繁琐的分析工作,并提高分析结果的准确度。回顾分析常用于病理学分析的深度学习方法,介绍深度学习在病理学分析中各领域的应用,并讨论深度学习在病理学分析中的挑战和机遇。

关键词: 深度学习, 人工智能, 数字病理学, 全切片数字化图像扫描技术

Abstract: Emergence of whole-slide imaging initiates the digital pathology. With the improvement of storage technology and the rapid development of internet and computer technologies, deep learning methods are widely used in the analysis of pathological images. The goal is to solve the problem of redundant and complicated information of pathological images that causes difficulty in diagnosis and analysis, alleviate the tedious analysis work of pathologists, and improve the accuracy of results. This paper reviewed the commonly used deep learning methods for pathological analysis and the application of deep learning in various fields of pathological analysis, and briefly discussed some challenges and opportunities of deep learning in pathological analysis.

Key words: Deep learning, Artificial intelligence, Digital pathology, Whole-slide imaging