中国癌症杂志 ›› 2017, Vol. 27 ›› Issue (12): 992-995.doi: 10.19401/j.cnki.1007-3639.2017.06.013

• 综述 • 上一篇    下一篇

机器学习在甲状腺肿瘤诊疗中的应用

张婷婷1,渠 宁1,郑 璞2,陈雅玲3,史荣亮1,嵇庆海1,孙国华1   

  1. 1. 复旦大学附属肿瘤医院头颈外科,复旦大学上海医学院肿瘤学系,上海 200032 ;
    2.Nuralogix 公司,多伦多M5C1C3 ;
    3. 复旦大学附属肿瘤医院超声诊断科,复旦大学上海医学院肿瘤学系,上海 200032
  • 出版日期:2017-12-30 发布日期:2018-01-11
  • 通信作者: 孙国华 E-mail:sunghayang@163.com

An overview of the use of machine learning in thyroid tumor

ZHANG Tingting1, QU Ning1, ZHENG Pu2, CHEN Yaling3, SHI Rongliang1, JI Qinghai1, SUN Guohua1   

  1. 1. Department of Head and Neck Surgery, Fudan University Shanghai Cancer Center; Department of Oncology, Shanghai Medical College, Fudan University, Shanghai 200032, China; 2. Nuralogix Corporation, Toronto M5C1C3, Canada; 3. Department of Supersound Diagnosis, Fudan University Shanghai Cancer Center; Department of Oncology, Shanghai Medical College, Fudan University, Shanghai 200032, China
  • Published:2017-12-30 Online:2018-01-11
  • Contact: SUN Guohua E-mail: sunghayang@163.com

摘要: 甲状腺肿瘤是一种常见疾病,其中良性肿瘤占绝大多数。流行病学研究显示,甲状腺恶性肿瘤发病率逐年提高。随着诊断技术的发展,高质量的影像及病理资料获取已不再困难,高效而准确的判读结果才是提高诊断水平的关键。随着患者数量的增多,甲状腺肿瘤患者的治疗决策及随访管理等均存在着巨大的挑战。机器学习因其具备高效率、较高准确率等特点而成为医学领域的研究热点之一。目前已有研究肯定了其在甲状腺肿瘤诊疗中的作用。正确全面地了解机器学习及其在甲状腺肿瘤诊疗中的作用可以为提高诊断准确性,指导治疗决策和改善患者管理提供新思路。

关键词: 甲状腺肿瘤, 机器学习, 人工神经网络, 深度学习

Abstract: Thyroid tumor is a common disease, of which the vast majorities are benign. However, there appears to be a recent increase in the occurrence of thyroid cancer. With the development of diagnostic techniques, acquisition of high-quality imaging and pathological data is no longer difficult. The difficulty of improving diagnosis now lies mainly in efficient and accurate interpretation of results. Given the increasing number of patients, treatment decision-making and follow-up management can be challenging. Machine learning has become a promising solution to the challenges in the field of medicine due to its high efficiency and accuracy. At present, its role in the diagnosis and treatment of thyroid tumors has been confirmed by several studies. A comprehensive understanding of machine learning and its role in the diagnosis and treatment of thyroid tumors can provide new ideas for improving diagnostic accuracy, guiding treatment decisions and improving patient management.

Key words: Thyroid tumor, Machine learning, Artificial neural network, Deep learning