基于人工智能技术的产学研深度融合在胃肠外科诊疗中的科技创新和成果转化经验分享  被引量:13

Integration of production-university-research based on artificial intelligence for technological innovation and transformation in gastrointestinal surgery

在线阅读下载全文

作  者:刘广伟[1,2,3] 李帅 陈永健[2,3,6] 卢云 Liu Guangwei;Li Shuai;Chen Yongjian;Lu Yun(Department of Gastrointestinal Surgery,The Affiliated Hospital,Qingdao University,Qingdao,Shandong 266003,China;Shandong Key Laboratory of Digital Medicine and Computer Assisted Surgery,Qingdao,Shandong 266003,China;Institute for Digital Medicine and Computer-Assisted Surgery of Qingdao University,Qingdao,Shandong 266000,China;State Key Laboratory of Virtual Reality Technology and System of Beijing University of Aeronautics and Astronautics,Beijing 100000,China;Qingdao Research Institute of Beijing University of Aeronautics and Astronautics,Qingdao,Shandong 266100,China;Qingdao Hisense Medical Equipment Co.LTD,Qingdao,Shandong 266100,China)

机构地区:[1]青岛大学附属医院胃肠外科,266003 [2]山东省数字医学与计算机辅助手术重点实验室,青岛266003 [3]青岛大学数字医学与计算机辅助手术研究院,青岛266071 [4]北京航空航天大学虚拟现实技术与系统国家重点实验室,北京100000 [5]北京航空航天大学青岛研究院,青岛266100 [6]青岛海信医疗设备股份有限公司,青岛266100

出  处:《中华胃肠外科杂志》2020年第6期557-561,共5页Chinese Journal of Gastrointestinal Surgery

基  金:国家自然科学基金(81802473);山东省自然科学基金(ZR2019PF017);山东省重点研发计划(2018GSF118206)。

摘  要:医学人工智能是一个"产学研"深度融合的领域。"产学研"协同创新体系打破了各学科之间的壁垒,在科技创新及成果转化方面展现了巨大的推动力。笔者所在的青岛大学附属医院,依托山东省数字医学与计算机辅助手术重点实验室、青岛大学数字医学与计算机辅助手术研究院,与北京航空航天大学虚拟现实技术与系统国家重点实验室以及青岛海信医疗设备股份有限公司,共同建立了紧密的"产学研"合作机制,历时10年,在人工智能胃肠外科领域开展了一系列科技创新和成果转化的有益探索,成果丰硕。主要包括:(1)研发海信计算机辅助手术系统(CAS),对于以周围血管为指引的腹腔镜胃肠手术,全局把握血管的走行和变异以准确选择手术策略,具有重要的临床意义。(2)研发胃肠道病变自动识别系统(人工智能影像辅助诊断系统),首次将人工智能深度神经网络应用于直肠癌淋巴结转移的鉴别,实现了精准的临床诊断。(3)成功开发出胃肠道虚拟内镜平台,能够提供全新的肠壁外翻的虚拟内镜视图,实现单向导航肠壁全览的功能。(4)构建具有完全自主知识产权的国产化腹腔镜手术模拟训练平台。我们体会到,临床需求是研发之源,临床实践是创新之源,临床医生是成果转化的实践者。人工智能模型的建立往往需要海量的、高质量的临床医疗数据的支持,故只有采用多中心研究的方式进行,才能保证其推广及应用的有效性。在科技创新和成果转化的整个过程中,不能忽视医学伦理和知识产权归属问题。Medical artificial intelligence is a deeply integrated field of production-university-research.The collaborative innovation system of"industry,education and research"has broken down the barriers between various disciplines and has shown great impetus in scientific and technological innovation and achievement transformation.The Affiliated Hospital of Qingdao University where the authors work,relying on Shandong Key Laboratory of Digital Medicine and Computer-Assisted Surgery and Institute of Digital Medicine and Computer-Assisted Surgery of Qingdao University,has jointly established a close"industry-university-research"cooperation mechanism with the State Key Laboratory of Virtual Reality Technology and Systems of Beijing University of Aeronautics and Astronautics and Qingdao Hisense Medical Equipment Co.,Ltd.,which lasted for 10 years and carried out a series of useful explorations in scientific and technological innovation and achievement transformation in the field of gastrointestinal surgery of artificial intelligence with fruitful results.It mainly comprises of the following:(1)The research and development(R&D)of Hisense computer-assisted surgery(CAS)system has important clinical significance for laparoscopic gastrointestinal surgery guided by surrounding blood vessels that grasps globally the movement and variation of blood vessels in order to accurately select surgical strategies.(2)R&D of an automatic identification system for gastrointestinal diseases(namely image-assisted diagnosis system of artificial intelligence)initially applies deep neural network of artificial intelligence to the identification of lymph node metastases in rectal cancer,which has achieved accurate clinical diagnosis.(3)The virtual endoscopy platform for the gastrointestinal tract developed can successfully provide a new virtual endoscopy view of the intestinal wall eversion and realize the one-way navigation of the intestinal wall.(4)A localized platform of laparoscopic surgery simulation training is established with completely inde

关 键 词:胃肠外科 人工智能 产学研 

分 类 号:R656[医药卫生—外科学] TP18[医药卫生—临床医学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象