人工智能时代超声医学新发展
|
摘要
人工智能(AI)技术发展至今已在许多研究领域和产业取得引人瞩目的成就,大大推动了高度依赖机器操控和海量信息数据分析的医学超声影像学的发展。目前AI在超声医学领域的发展是医工结合交叉研究的新热点,越来越多的超声医学专家和数学家、计算机科学家共同致力于推动超声医学研究与AI的融合实践,旨在提高超声诊断的准确率、降低误诊率、缩短报告时间,满足日益增长的临床需求。本文主要就超声医学在AI领域的研究进展、AI时代我国超声医学发展的机遇与挑战等作一综述。
Since the advent of artificial intelligence(AI), remarkable achievements have been made in many research fields and industries, which greatly promote the development of medical ultrasound imaging, which is highly dependent on machine manipulation and massive data analysis. At present, the development of AI in the field of ultrasound medicine is a new focus of the cross-research of medical-industrial integration. More and more medical ultrasound experts, mathematicians and computer scientists are working together to promote the integration of ultrasound medicine and AI, so as to improve the accuracy of ultrasound diagnosis, reduce misdiagnosis rate, shorten reporting time and meet the growing clinical needs. In this review, we summarized the advances on ultrasound medicine in the field of AI, and the opportunities and challenges in the development of ultrasound medicine in China in the era of AI.
Since the advent of artificial intelligence(AI), remarkable achievements have been made in many research fields and industries, which greatly promote the development of medical ultrasound imaging, which is highly dependent on machine manipulation and massive data analysis. At present, the development of AI in the field of ultrasound medicine is a new focus of the cross-research of medical-industrial integration. More and more medical ultrasound experts, mathematicians and computer scientists are working together to promote the integration of ultrasound medicine and AI, so as to improve the accuracy of ultrasound diagnosis, reduce misdiagnosis rate, shorten reporting time and meet the growing clinical needs. In this review, we summarized the advances on ultrasound medicine in the field of AI, and the opportunities and challenges in the development of ultrasound medicine in China in the era of AI.
引文
[1]孔祥溢,王任直.人工智能及在医疗领域的应用[J].医学信息学杂志,2016,37:1-5.
[2]PEEK N,COMBI C,MARIN R,BELLAZZI R.Thirty years of artificial intelligence in medicine(AIME)conferences:a review of research theme[J].Artif Intell Med,2015,65:61-73.
[3]杨海峰,田增民,孙跃春,崔刚,李宾,张智波,等.Remebot第六代神经外科机器人的临床应用[J].中国临床医生杂志,2017,45:86-88.
[4]徐大华,刘东斌.高科技推动微创外科发展[J/CD].中华腔镜外科杂志(电子版),2017,10:193-195.
[5]SPECTOR L.Evolution of artificial intelligence[J].Artif Intell,2006,170:1251-1253.
[6]金征宇.前景与挑战:当医学影像遇见人工智能[J].协和医学杂志,2018,9:2-4.
[7]ESTEVA A,KUPREL B,NOVOA R A,KO J,SWETTER S M,BLAU H M,et al.Dermatologist-level classification of skin cancer with deep neural networks[J].Nature,2017,542:115-118.
[8]蔡航.基于神经网络的医疗诊断专家系统[J].数理医药学杂志,2002,15:294-295.
[9]STOITSIS J,VALAVANIS I,MOUGIAKAKOU S G,GOLEMATI S,NIKITA A,NIKITA K S.Computer aided diagnosis based on medical image processing and artificial intelligence methods[J].Nucl Instrum Methods Phys Res A,2006,569:591-595.
[10]温朝阳,王金锐,刘吉斌,姜玉新,华扬,詹维伟,等.中国血管超声规范化及其继续教育探索[J/CD].中华医学超声杂志(电子版),2010,7:2016-2024.
[11]周嫱,李炜,智明春,李贞爱.产科超声工作站的应用[J].中国医疗设备,2016,31:121-122.
[12]唐守信,张家君,卢川.甲状腺影像报告和数据系统临床应用进展[J].医学影像学杂志,2017,27:1573-1575.
[13]何献忠,许仲兴,陈欣,龚连生.人机大战引发智能医疗的探讨[J].中国医学工程,2016,24:35-37.
[14]施俊,王锐玲,周世崇,常才.结合乳腺影像报告和数据体系的乳腺超声CAD研究进展[J].生物医学工程学杂志,2010,27:1169-1172.
[15]林方才,孙欣,矫健,刘娜,查笑丹.自动全容积乳腺超声成像和超声光散射对乳腺结节诊断的对比研究[J/CD].中华临床医师杂志(电子版),2012,6:7898-7899.
[16]谭艳娟,包凌云,黄安茜,朱罗茜,阚光娟,刘坚.乳腺恶性肿瘤冠状面汇聚征与临床病理学相关因素分析[J].中国超声医学杂志,2015,31:587-589.
[17]宋家琳,刘翔,章建全,陈雁秋,刁宗平,盛建国,等.高频超声影像肝脏包膜几何特征定量评价患者肝硬化程度[J].中国医学影像技术,2015,31:1907-1910.
[18]PAVLOPOULOS S,KYRIACOU E,KOUTSOURISD,BLEKAS K,STAFYLOPATIS A,ZOUMPOULIS P.Fuzzy neural network-based texture analysis of ultrasonic images[J].IEEE Eng Med Biol Mag,2000,19:39-47.
[19]赵佳琦,徐琪,章建全,黄禾菁,刁宗平.骨骼肌超声诊断迈向人工智能新领域:计算机辅助骨骼肌损伤超声定量诊断[J].第二军医大学学报,2017,38:1217-1224.ZHAO J Q,XU Q,ZHANG J Q,HUANG H J,DIAO ZP.Ultrasound diagnosis of skeletal muscle promoted by artificial intelligence:a quantitative evaluation of injured skeletal muscle by computer-aided ultrasonographic texture analysis[J].Acad J Sec Mil Med Univ,2017,38:1217-1224.
[20]赵佳琦,章建全,徐琪,陈雁秋,盛建国,卢峰,等.超声图像纹理分析技术对离体猪横纹肌理化损伤模型的定量研究[J/CD].中华医学超声杂志(电子版),2013,10:674-680.
[21]ZHAO J,ZHANG J,XU Q,SHENG J,DIAO Z,LIUS.Quantitative evaluation of striated muscle injury by multiscale blob features method[J].J Med Ultrason(2001),2016,43:337-345.
[22]赵佳琦,章建全,赵璐璐,宋家琳,潘倩,盛建国,等.不同消融功率致兔骨骼肌急性微波热损伤修复的超声影像演变特征[J/CD].中华医学超声杂志(电子版),2016,13:780-789.
[23]XU Q,WU H S,CHEN Y Q.Statistical multiscale blob features for classifying and retrieving image texture from large-scale databases[J].J Electron Imaging,2010,19:1-7.
[24]陈东太郎,徐琪,曾卫明.一种基于结构化信息极大分解的肌肉损伤超声造影图像分割方法:201510019412.4[P].2017-10-03.
[25]宋芫,赵博文,王蓓,彭晓慧,许立龙,郭河清,等.超声心动图自动心肌运动定量技术评测左心室收缩功能的相关性研究[J].中华超声影像学杂志,2017,26:7-11.
[26]佟彤,熊奕.智能三维超声成像在胎儿领域的应用进展[J].中国介入影像与治疗学,2016,13:188-191.
[27]STOITSIS J,GOLEMATI S,NIKITA K S.A modular software system to assist interpretation of medical images-application to vascular ultrasound images[J].IEEE Trans Instrum Meas,2006,55:1944-1952.
[28]季兴.盆底超声中基于回归模型的膀胱脱垂自动分级[D].深圳:深圳大学,2017.
[29]胡晨明,徐静,梁萍,鲁通,任贺,王旸,等.用于超声引导介入治疗的三维超声系统[J].中国医疗器械信息,2007,13:68-71.
[30]王弈,李传富.人工智能方法在医学图像处理中的研究新进展[J].中国医学物理学杂志,2013,30:4138-4143.
[31]MURAD A,PYUN J Y.Deep recurrent neural networks for human activity recognition[J/OL].Sensors(Basel)2017,17.pii:E2556.doi:10.3390/s17112556.
[2]PEEK N,COMBI C,MARIN R,BELLAZZI R.Thirty years of artificial intelligence in medicine(AIME)conferences:a review of research theme[J].Artif Intell Med,2015,65:61-73.
[3]杨海峰,田增民,孙跃春,崔刚,李宾,张智波,等.Remebot第六代神经外科机器人的临床应用[J].中国临床医生杂志,2017,45:86-88.
[4]徐大华,刘东斌.高科技推动微创外科发展[J/CD].中华腔镜外科杂志(电子版),2017,10:193-195.
[5]SPECTOR L.Evolution of artificial intelligence[J].Artif Intell,2006,170:1251-1253.
[6]金征宇.前景与挑战:当医学影像遇见人工智能[J].协和医学杂志,2018,9:2-4.
[7]ESTEVA A,KUPREL B,NOVOA R A,KO J,SWETTER S M,BLAU H M,et al.Dermatologist-level classification of skin cancer with deep neural networks[J].Nature,2017,542:115-118.
[8]蔡航.基于神经网络的医疗诊断专家系统[J].数理医药学杂志,2002,15:294-295.
[9]STOITSIS J,VALAVANIS I,MOUGIAKAKOU S G,GOLEMATI S,NIKITA A,NIKITA K S.Computer aided diagnosis based on medical image processing and artificial intelligence methods[J].Nucl Instrum Methods Phys Res A,2006,569:591-595.
[10]温朝阳,王金锐,刘吉斌,姜玉新,华扬,詹维伟,等.中国血管超声规范化及其继续教育探索[J/CD].中华医学超声杂志(电子版),2010,7:2016-2024.
[11]周嫱,李炜,智明春,李贞爱.产科超声工作站的应用[J].中国医疗设备,2016,31:121-122.
[12]唐守信,张家君,卢川.甲状腺影像报告和数据系统临床应用进展[J].医学影像学杂志,2017,27:1573-1575.
[13]何献忠,许仲兴,陈欣,龚连生.人机大战引发智能医疗的探讨[J].中国医学工程,2016,24:35-37.
[14]施俊,王锐玲,周世崇,常才.结合乳腺影像报告和数据体系的乳腺超声CAD研究进展[J].生物医学工程学杂志,2010,27:1169-1172.
[15]林方才,孙欣,矫健,刘娜,查笑丹.自动全容积乳腺超声成像和超声光散射对乳腺结节诊断的对比研究[J/CD].中华临床医师杂志(电子版),2012,6:7898-7899.
[16]谭艳娟,包凌云,黄安茜,朱罗茜,阚光娟,刘坚.乳腺恶性肿瘤冠状面汇聚征与临床病理学相关因素分析[J].中国超声医学杂志,2015,31:587-589.
[17]宋家琳,刘翔,章建全,陈雁秋,刁宗平,盛建国,等.高频超声影像肝脏包膜几何特征定量评价患者肝硬化程度[J].中国医学影像技术,2015,31:1907-1910.
[18]PAVLOPOULOS S,KYRIACOU E,KOUTSOURISD,BLEKAS K,STAFYLOPATIS A,ZOUMPOULIS P.Fuzzy neural network-based texture analysis of ultrasonic images[J].IEEE Eng Med Biol Mag,2000,19:39-47.
[19]赵佳琦,徐琪,章建全,黄禾菁,刁宗平.骨骼肌超声诊断迈向人工智能新领域:计算机辅助骨骼肌损伤超声定量诊断[J].第二军医大学学报,2017,38:1217-1224.ZHAO J Q,XU Q,ZHANG J Q,HUANG H J,DIAO ZP.Ultrasound diagnosis of skeletal muscle promoted by artificial intelligence:a quantitative evaluation of injured skeletal muscle by computer-aided ultrasonographic texture analysis[J].Acad J Sec Mil Med Univ,2017,38:1217-1224.
[20]赵佳琦,章建全,徐琪,陈雁秋,盛建国,卢峰,等.超声图像纹理分析技术对离体猪横纹肌理化损伤模型的定量研究[J/CD].中华医学超声杂志(电子版),2013,10:674-680.
[21]ZHAO J,ZHANG J,XU Q,SHENG J,DIAO Z,LIUS.Quantitative evaluation of striated muscle injury by multiscale blob features method[J].J Med Ultrason(2001),2016,43:337-345.
[22]赵佳琦,章建全,赵璐璐,宋家琳,潘倩,盛建国,等.不同消融功率致兔骨骼肌急性微波热损伤修复的超声影像演变特征[J/CD].中华医学超声杂志(电子版),2016,13:780-789.
[23]XU Q,WU H S,CHEN Y Q.Statistical multiscale blob features for classifying and retrieving image texture from large-scale databases[J].J Electron Imaging,2010,19:1-7.
[24]陈东太郎,徐琪,曾卫明.一种基于结构化信息极大分解的肌肉损伤超声造影图像分割方法:201510019412.4[P].2017-10-03.
[25]宋芫,赵博文,王蓓,彭晓慧,许立龙,郭河清,等.超声心动图自动心肌运动定量技术评测左心室收缩功能的相关性研究[J].中华超声影像学杂志,2017,26:7-11.
[26]佟彤,熊奕.智能三维超声成像在胎儿领域的应用进展[J].中国介入影像与治疗学,2016,13:188-191.
[27]STOITSIS J,GOLEMATI S,NIKITA K S.A modular software system to assist interpretation of medical images-application to vascular ultrasound images[J].IEEE Trans Instrum Meas,2006,55:1944-1952.
[28]季兴.盆底超声中基于回归模型的膀胱脱垂自动分级[D].深圳:深圳大学,2017.
[29]胡晨明,徐静,梁萍,鲁通,任贺,王旸,等.用于超声引导介入治疗的三维超声系统[J].中国医疗器械信息,2007,13:68-71.
[30]王弈,李传富.人工智能方法在医学图像处理中的研究新进展[J].中国医学物理学杂志,2013,30:4138-4143.
[31]MURAD A,PYUN J Y.Deep recurrent neural networks for human activity recognition[J/OL].Sensors(Basel)2017,17.pii:E2556.doi:10.3390/s17112556.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |