医学影像人工智能产业化的现状及面临的挑战
|
摘要
人工智能(artificial intelligence,AI)技术的探索及应用受到全球各国的高度关注,该文旨在对AI在医学影像领域的发展做一分析和展望。文章总结了医学影像AI产业化在政策层面、技术层面、需求层面及经济环境等多个方面的优势,并分析了其产业化之后可能对医疗模式带来的种种变化。同时该文也理性地指出了AI产业化在技术落地、盈利模式的突破及市场竞争等多个方面存在挑战。希望各界人士能够共同积极拥抱新技术,共同推动医学影像AI产业良性、快速地发展。
Arti?cial intelligence(AI) technology has gained attention from most countries all around the world. This article is written to summarize the current development of AI technology used for medical imaging applications. The article has listed several advantages of medical imaging AI products, including related government policies, technology framework, clinical needs and the economic environment. It also shows the possible changes of clinical working style after the complete commercialization of medical imaging AI products. On the other side, it also points out challenges for AI, such as application details in the product research and development process, the pro?ting problem and competition between AI companies. All over, people from different professional?elds are all welcome to try the new technology and give a fast and healthy promotion of the development of medical imaging AI products.
Arti?cial intelligence(AI) technology has gained attention from most countries all around the world. This article is written to summarize the current development of AI technology used for medical imaging applications. The article has listed several advantages of medical imaging AI products, including related government policies, technology framework, clinical needs and the economic environment. It also shows the possible changes of clinical working style after the complete commercialization of medical imaging AI products. On the other side, it also points out challenges for AI, such as application details in the product research and development process, the pro?ting problem and competition between AI companies. All over, people from different professional?elds are all welcome to try the new technology and give a fast and healthy promotion of the development of medical imaging AI products.
引文
[1]MCCARTHY J, MINSKY M L, ROCHESTER N, et al. A proposal for the dartmouth summer research project on articial intelligence[J]. J Mol Biol, 2006, 278(1):279-289.
[2]SUN R, LIMKIN E J, VAKALOPOULOU M, et al. A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1 immunotherapy:an imaging biomarker, retrospective multicohort study[J]. Lancet Oncol,2018, 19(9):1180-1191.
[3]HOOFNAGLE C J, SLOOT B V D, BORGESIUS F Z. The European Union General Data Protection Regulation:what it is and what it means[J]. ICT Law, 2019, 28(1):65-98.
[4]CHEN X, LIU Z, WEI L. A comparative quantitative study of utilizing artificial intelligence on electronic health records in the USA and China during 2008—2017[J]. BMC Med Inform Decis Mak, 2018, 18(Supply 5):117.
[5]WAHL B, COSSY-GANTNER A, GERMANN S, et al. Artificial intelligence (AI) and global health:how can AI contribute to health in resource-poor settings?[J]. BMJ Global Health,2018, 3(4):e000798.
[6]刘凯,张荣国,涂文婷,等.深度学习技术对胸部X线平片亚实性结节的检测效能初探[J].中华放射学杂志, 2017,51(12):918-921.
[7]张惠茅,萧毅,洪楠,等.医学影像人工智能产业现状和发展需求调研报告[J].中华放射学杂志, 2019, 53(6):507-511.
[8]GILLIES R J, KINAHAN P E, HRICAK H. Radiomics:images are more than pictures, they are data.[J]. Radiology, 2016,278(2):563-577.
[9]HOSNYA,PARMARC,QUACKENBUSHJ.Artificial intelligence in radiology[J]. Nat Rev Cancer, 2018, 18(8):500-510.
[10]CAO C, LIU F, TAN H, et al. Deep Learning and its applications in biomedicine[J]. Genomics Proteomics Bioinformatics,2018, 16(1):17-32.
[11]CIOMPI F, CHUNG K, VAN RIEL S J, et al. Towards automatic pulmonary nodule management in lung cancer screening with deep learning[J]. Sci Rep, 2017, 7:46479.
[12]JHA S, TOPOL E J. Adapting to artificial intelligence:radiologists and pathologists as information specialists[J].JAMA, 2016, 316(22):2353-2354.
[13]KERMANY D S, GOLDBAUM M, CAI W, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning[J]. Cell, 2018, 172(5):1122-1131.
[14]GOLDEN J A. Deep learning algorithms for detection of lymph node metastases from breast cancer:helping artificial intelligence be seen[J]. JAMA, 2017, 318(22):2184-2186.
[15]萧毅,刘士远.医学影像人工智能进入深水区后的思考[J].中华放射学杂志, 2019, 53(1):2-5.
[16]中国食品药品检定研究院,中华医学会放射学分会心胸学组,任海萍,等.胸部CT肺结节数据标注与质量控制专家共识(2018)[J].中华放射学杂志, 2019, 53(1):9-15.
[17]NICHOLS J A, HERBERT CHAN H W, BAKER M A B.Machine learning:applications of artificial intelligence to imaging and diagnosis[J]. Biophys Rev, 2019, 11(1):111-118.
[2]SUN R, LIMKIN E J, VAKALOPOULOU M, et al. A radiomics approach to assess tumour-infiltrating CD8 cells and response to anti-PD-1 or anti-PD-L1 immunotherapy:an imaging biomarker, retrospective multicohort study[J]. Lancet Oncol,2018, 19(9):1180-1191.
[3]HOOFNAGLE C J, SLOOT B V D, BORGESIUS F Z. The European Union General Data Protection Regulation:what it is and what it means[J]. ICT Law, 2019, 28(1):65-98.
[4]CHEN X, LIU Z, WEI L. A comparative quantitative study of utilizing artificial intelligence on electronic health records in the USA and China during 2008—2017[J]. BMC Med Inform Decis Mak, 2018, 18(Supply 5):117.
[5]WAHL B, COSSY-GANTNER A, GERMANN S, et al. Artificial intelligence (AI) and global health:how can AI contribute to health in resource-poor settings?[J]. BMJ Global Health,2018, 3(4):e000798.
[6]刘凯,张荣国,涂文婷,等.深度学习技术对胸部X线平片亚实性结节的检测效能初探[J].中华放射学杂志, 2017,51(12):918-921.
[7]张惠茅,萧毅,洪楠,等.医学影像人工智能产业现状和发展需求调研报告[J].中华放射学杂志, 2019, 53(6):507-511.
[8]GILLIES R J, KINAHAN P E, HRICAK H. Radiomics:images are more than pictures, they are data.[J]. Radiology, 2016,278(2):563-577.
[9]HOSNYA,PARMARC,QUACKENBUSHJ.Artificial intelligence in radiology[J]. Nat Rev Cancer, 2018, 18(8):500-510.
[10]CAO C, LIU F, TAN H, et al. Deep Learning and its applications in biomedicine[J]. Genomics Proteomics Bioinformatics,2018, 16(1):17-32.
[11]CIOMPI F, CHUNG K, VAN RIEL S J, et al. Towards automatic pulmonary nodule management in lung cancer screening with deep learning[J]. Sci Rep, 2017, 7:46479.
[12]JHA S, TOPOL E J. Adapting to artificial intelligence:radiologists and pathologists as information specialists[J].JAMA, 2016, 316(22):2353-2354.
[13]KERMANY D S, GOLDBAUM M, CAI W, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning[J]. Cell, 2018, 172(5):1122-1131.
[14]GOLDEN J A. Deep learning algorithms for detection of lymph node metastases from breast cancer:helping artificial intelligence be seen[J]. JAMA, 2017, 318(22):2184-2186.
[15]萧毅,刘士远.医学影像人工智能进入深水区后的思考[J].中华放射学杂志, 2019, 53(1):2-5.
[16]中国食品药品检定研究院,中华医学会放射学分会心胸学组,任海萍,等.胸部CT肺结节数据标注与质量控制专家共识(2018)[J].中华放射学杂志, 2019, 53(1):9-15.
[17]NICHOLS J A, HERBERT CHAN H W, BAKER M A B.Machine learning:applications of artificial intelligence to imaging and diagnosis[J]. Biophys Rev, 2019, 11(1):111-118.