中国组织工程研究 ›› 2024, Vol. 28 ›› Issue (17): 2766-2773.doi: 10.12307/2024.406

• 生物材料综述 biomaterial review • 上一篇    下一篇

机器学习在医用金属材料特性研究中的应用

史  榴1,梁鹏晨1,常  庆2,宋二红3   

  1. 1上海大学微电子学院,上海市  201800;2上海交通大学医学院附属瑞金医院消化外科研究所,上海市胃肿瘤重点实验室,上海市  200020;3中国科学院上海硅酸盐研究所高性能陶瓷和超微结构国家重点实验室,上海市  200050
  • 收稿日期:2023-07-14 接受日期:2023-07-29 出版日期:2024-06-18 发布日期:2023-12-16
  • 通讯作者: 常庆,博士,研究员,上海交通大学医学院附属瑞金医院消化外科研究所,上海市胃肿瘤重点实验室,上海市 200020 宋二红,博士,副研究员,中国科学院上海硅酸盐研究所高性能陶瓷和超微结构国家重点实验室,上海市 200050
  • 作者简介:史榴,女,1999年生,陕西省西安市人,汉族,上海大学在读硕士,主要从事深度学习算法在医用材料研发中的应用研究。
  • 基金资助:
    国家自然科学基金资助项目(81670968),项目负责人:常庆

Application of machine learning in key properties of medical metal materials

Shi Liu1, Liang Pengchen1, Chang Qing2, Song Erhong3   

  1. 1College of Microelectronics, Shanghai University, Shanghai 201800, China; 2Shanghai Key Laboratory of Gastric Neoplasms, Shanghai Institute of Digestive Surgery, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200020, China; 3State Key Laboratory of High-Performance Ceramics and Ultrastructure, Shanghai Institute of Ceramics, Chinese Academy of Sciences, Shanghai 200050, China
  • Received:2023-07-14 Accepted:2023-07-29 Online:2024-06-18 Published:2023-12-16
  • Contact: Chang Qing, PhD, Researcher, Shanghai Key Laboratory of Gastric Neoplasms, Shanghai Institute of Digestive Surgery, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200020, China Song Erhong, PhD, Associate researcher, State Key Laboratory of High-Performance Ceramics and Ultrastructure, Shanghai Institute of Ceramics, Chinese Academy of Sciences, Shanghai 200050, China
  • About author:Shi Liu, Master candidate, College of Microelectronics, Shanghai University, Shanghai 201800, China
  • Supported by:
    National Natural Science Foundation of China, No. 81670968 (to CQ)

摘要:


文题释义:

医用金属材料:是在医学领域中广泛应用的特殊金属材料。这些金属材料通常具有优异的生物相容性、耐腐蚀性和力学性能。常见的医用金属包括不锈钢、钛合金和钴铬合金等,由于其良好的特性,医用金属材料在植入物制造、手术器械、牙科修复和骨科手术等领域得到广泛应用。
机器学习:是人工智能领域的一个分支,它是通过构建和训练算法来使计算机系统从数据中学习,并根据学习的知识做出决策或预测。机器学习的核心思想是通过分析大量数据,找出其中的模式和规律,并用这些规律来做出预测或分类。


背景:机器学习与医用金属材料的结合,弥补传统实验和计算模拟的低效性和高成本的不足,通过分析大量数据快速准确地预测金属材料特性,优化材料设计和性能,提高医学应用的安全性和效率。

目的:总结并归纳机器学习在医用材料特性中的研究进展及不足。
方法:由第一作者通过计算机检索中国知网、PubMed、X-MOL和Web of Science数据库2013年1月至2023年4月的相关文章。中文检索词为“医用金属材料机器学习,医用钛合金,医用镁合金,医用金属材料性能”,英文检索词为“machine learning medical metal materials,medical stainless steel alloy,medical cobalt-chromium alloy,medical titanium alloy,medical magnesium alloy”,最终纳入70篇相关文献进行归纳总结。

结果与结论:①随着传统实验和计算模拟方法所产生的大量数据的可获取性提高,机器学习作为材料设计方法的引入为材料科学研究开辟了新的范式。②机器学习工作流主要分为4个部分:数据收集及预处理、特征工程、模型选择及训练和模型评估,每个环节不可缺少。③医用金属材料分为:不锈钢共基合金、钴铬合金、钛合金和镁合金。针对不锈钢共基合金,机器学习预测其力学性能,要提高机器学习的泛化能力;针对钴铬合金,机器学习预测其力学性能,可得出钴铬合金为髋关节植入物的最佳材料;针对钛合金,机器学习预测其力学性能,可选择出力学性能最优异的植入物;针对镁合金,机器学习预测其耐腐蚀性和力学性能,集成模型可准确预测镁合金的力学性能,随机森林模型可预测镁合金作为血管支架时的最优元素含量。④机器学习在医用材料领域存在一定局限性,如模型相对滞后、数据未能标准化及泛化性较低;未来研究解决此类问题应充分利用深度学习和分割算法技术,使用统一标准数据,改善模型提高泛化能力。

https://orcid.org/0009-0006-7587-9541(史榴);https://orcid.org/0000-0001-7568-4070(常庆)

中国组织工程研究杂志出版内容重点:生物材料;骨生物材料口腔生物材料纳米材料缓释材料材料相容性组织工程

关键词: 医用金属材料, 机器学习, 材料特性, 腐蚀性能, 力学性能, 不锈钢共基合金, 钴铬合金, 钛合金, 镁合金, 特征参数

Abstract: BACKGROUND: The combination of machine learning and medical metal materials can make up for the inefficiency and high cost of traditional experiments and computational simulations, and quickly and accurately predict the characteristics of metal materials by analyzing large amounts of data, optimize material design and performance, and improve the safety and efficiency of medical applications.
OBJECTIVE: To summarize the research progress and shortcomings of machine learning in the characteristics of medical materials. 
METHODS: The first author searched CNKI, PubMed, X-MOL, and Web of Science databases by computer to search all relevant articles from January 2013 to April 2023. The Chinese search terms were “machine learning of medical metal materials, medical titanium alloy, medical magnesium alloy, medical metal material properties”. The English search terms were “machine learning medical metal materials, medical stainless steel alloy, medical cobalt-chromium alloy, medical titanium alloy, medical magnesium alloy”. Finally, 70 relevant articles were included for a summary.
RESULTS AND CONCLUSION: (1) The introduction of machine learning as a material design methodology has opened up new paradigms for material science research as the accessibility of large amounts of data generated by traditional experimental and computational simulation methods increases. (2) The machine learning workflow is divided into four main parts: data collection and preprocessing, feature engineering, model selection and training, and model evaluation, each of which is indispensable. (3) Medical metal materials are categorized into: stainless steel co-base alloys, cobalt-chromium alloys, titanium alloys, and magnesium alloys. For stainless steel co-base alloy, machine learning predicts its mechanical properties, to improve the generalization ability of machine learning. For cobalt-chromium alloy, machine learning predicts its mechanical properties, and it can conclude that cobalt-chromium alloy is the optimal material for hip implants. For titanium alloy, machine learning predicts its mechanical properties, and it can select the implant with the best mechanical properties. For magnesium alloy, machine learning predicts its corrosion resistance and mechanical properties; the ensemble model can accurately predict the mechanical properties of magnesium alloys, and the random forest model can predict the optimal elemental contents of magnesium alloys as vascular stents. (4) Machine learning has deficiencies in the field of medical materials. For example, the model is relatively lagging; the data failed to be standardized, and the generalization is low. To solve such problems, we should make full use of deep learning and segmentation algorithm technology, use unified standard data, and improve the model to increase the generalization ability.

Key words: medical metal material, machine learning, material characteristics, corrosion performance, mechanical property, stainless steel co-base alloy, cobalt-chromium alloy, titanium alloy, magnesium alloy, characteristic parameter

中图分类号: