基于机器学习的医学影像分析在药物研发和精准医疗方面的应用

doi:10.13523/j.cb.20190211

中国生物工程杂志

2019, Vol. 39

Issue (2): 90-100 DOI: 10.13523/j.cb.20190211

精准医疗与伴随诊断专刊

基于机器学习的医学影像分析在药物研发和精准医疗方面的应用

谢志勇¹(

),周翔²

1 辉瑞研发中心波士顿 02139
2 联影智能医疗科技有限公司上海 200232

Machine Learning in Medical Imaging:the Applications in Drug Discovery and Precision Medicine

Zhi-yong XIE¹(

),Xiang ZHOU²

1 Pfizer Worldwide Research & Development, Cambridge 02139, USA ;
2 United Imaging Intelligence, Shanghai 200232, China

全文: PDF(525 KB) HTML

摘要：

MRI,PET,和CT等医学影像在新药研发和精准医疗中起着越来越重要的作用。影像技术可以被用来诊断疾病,评估药效,选择适应患者,或者确定用药剂量。随着人工智能技术的发展,特别是机器学习以及深度学习技术在医学影像中的应用,使得我们可以用更短的时间,更少的放射剂量获取更高质量的影像。这些技术还可以帮助放射科医生缩短读片时间,提高诊断准确率。除此之外,机器学习技术还可以提高量化分析的可行性和精度,帮助建立影像与基因以及疾病的临床表现之间的关系。首先根据不同形态的医学影像,简单介绍他们在药物研发和精准医疗中的应用。并对机器学习在医学影像中的功能作一概括总结。最后讨论这个领域的挑战和机遇。

关键词： 医学影像; 药物研发; 精准医疗; 人工智能; 机器学习

Abstract:

Medical imaging, such as MRI, PET, and CT, is playing a more and more important role in drug development and precision medicine. It can be used to diagnose disease, evaluate drug effect, select the right patient, or determine the most appropriate drug dose. With the advances in artificial intelligence, especially the extensive applications of machine learning and deep learning in medical imaging, it is possible to use shorter time or less radiation dose to acquire high quality images. AI also help radiologists improve the performance of diagnosis. Moreover, machine learning methods are very useful in quantitative analysis, and gaining insights about the relationship between images, genotypes, and clinical phenotypes. This paper gives an overview of applications of medical imaging in drug development and precision medicine based on the modality of the technologies, as well as how machine learning methods were used in these applications. Challenges and opportunities are discussed in the end.

Key words: Medical imaging Drug development Precision medicine Artificial intelligence Machine learning

收稿日期: 2019-01-10 出版日期: 2019-03-26

ZTFLH:

Q819

	服务
	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	谢志勇
	周翔

引用本文:

谢志勇,周翔. 基于机器学习的医学影像分析在药物研发和精准医疗方面的应用[J]. 中国生物工程杂志, 2019, 39(2): 90-100.

Zhi-yong XIE,Xiang ZHOU. Machine Learning in Medical Imaging:the Applications in Drug Discovery and Precision Medicine. China Biotechnology, 2019, 39(2): 90-100.

链接本文:

https://manu60.magtech.com.cn/biotech/CN/10.13523/j.cb.20190211 或 https://manu60.magtech.com.cn/biotech/CN/Y2019/V39/I2/90

[1]	Paul S M, Mytelka D S, Dunwiddie C T , et al. How to improve RD productivity: The pharmaceutical industry’s grand challenge. Nat Rev Drug Discov, 2010; 9(3):203-214. doi: 10.1038/nrd3078
[2]	DiMasi J A, Grabowski H G, Hansen R W . Innovation in the pharmaceutical industry: New estimates of R&D costs. J Health Econ, 2016; 47:20-33. doi: 10.1016/j.jhealeco.2016.01.012 pmid: 26928437
[3]	Wong C H, Siah K W, Lo A W . Estimation of clinical trial success rates and related parameters. Biostatistics. 2018,DOI: 10.1093/biostatistics/kxx069. doi: 10.1093/biostatistics/kxx069 pmid: 29394327
[4]	Rudin M, Weissleder R . Molecular imaging in drug discovery and development. Nat Rev Drug Discov, 2003; 2(2):123-131. doi: 10.1038/nrd1007 pmid: 12563303
[5]	Ching T, Himmelstein D S , Beaulieu-Jones B K, et al. Opportunities and Obstacles for Deep Learning in Biology and Medicine. J R Soc Interface, 2018,15(141):1-47.
[6]	Shen D, Wu G, Suk H , Deep learning in medical image analysis. Annu Rev Biomed Eng, 2017,19:221-248. doi: 10.1146/annurev-bioeng-071516-044442 pmid: 28301734
[7]	European Society of Radiology . Medical imaging in personalised medicine: a white paper of the research committee of the European Society of Radiology (ESR). Insights Imaging, 2011; 2(6):621-630. doi: 10.1007/s13244-011-0125-0
[8]	Albanese C V, Diessel E, Genant H K . Clinical applications of body composition measurements using DXA. J Clin Densitom, 2003; 6(2):75-85. doi: 10.1385/JCD:6:2:75 pmid: 12794229
[9]	Deodhar A, Strand V, Kay J , et al. The term “non-radiographic axial spondyloarthritis” is much more important to classify than to diagnose patients with axial spondyloarthritis. Ann Rheum Dis, 2016,75(5):791-794. doi: 10.1136/annrheumdis-2015-208852 pmid: 26768406
[10]	Landewé R , Van Der Heijde D. Presentation and analysis of radiographic data in clinical trials and observational studies. Ann Rheum Dis, 2005,64(Suppl 4):48-51. doi: 10.1136/ard.2004.031831 pmid: 15647421
[11]	Blake G M, Fogelman I . The role of DXA bone density scans in the diagnosis and treatment of osteoporosis. Postgrad Med J, 2007,83(982):509-517. doi: 10.1136/pgmj.2007.057505 pmid: 2600106
[12]	Wintermark M, Jawadi S S, Rapp J H , et al. High-resolution ct imaging of carotid artery atherosclerotic plaques. Am J Neuroradiol, 2008,29(5):875-882. doi: 10.3174/ajnr.A0950 pmid: 18272562
[13]	Hecht H S, Cronin P, Blaha M J , et al. 2016 SCCT/STR guidelines for coronary artery calcium scoring of noncontrast noncardiac chest CT scans: A report of the Society of Cardiovascular Computed Tomography and Society of Thoracic Radiology. Journal of Cardiovascular Computed Tomography, 2017,11(1):74-84. doi: 10.1016/j.jcct.2016.11.003 pmid: 27916431
[14]	Thaiss W M, Sauter A W, Bongers M , et al. Clinical applications for dual energy CT versus dynamic contrast enhanced CT in oncology. Eur J Radiol, 2015,84(12):2368-2379. doi: 10.1016/j.ejrad.2015.06.001 pmid: 26116077
[15]	Park M-S, Klotz E, Kim M-J , et al. Perfusion ct: noninvasive surrogate marker for stratification of pancreatic cancer response to concurrent chemo- and radiation therapy. Radiology, 2009,250(1):110-117. doi: 10.1148/radiol.2493080226 pmid: 18984781
[16]	Bhatt S P, Han M K . Developing and implementing biomarkers and novel imaging in COPD. Chronic Obstr Pulm Dis (Miami, Fla). 2016; 3(1):485-490. doi: 10.15326/jcopdf.3.1.2015.0170 pmid: 5559131
[17]	van der Veldt A A M, Hendrikse N H, Smit E F , et al. Biodistribution and radiation dosimetry of 11C-labelled docetaxel in cancer patients. Eur J Nucl Med Mol Imaging, 2010,37(10):1950-1958. doi: 10.1007/s00259-010-1489-y pmid: 20508935
[18]	Zhang Y, Fox G B . PET imaging for receptor occupancy: meditations on calculation and simplification. J Biomed Res, 2012,26(2):69-76. doi: 10.1016/S1674-8301(12)60014-1 pmid: 3597321
[19]	González Trotter D E, Meng X, McQuade P , et al. In vivo imaging of the programmed death ligand 1 by 18F PET. J Nucl Med, 2017,58(11):1852-1857. doi: 10.2967/jnumed.117.191718
[20]	Villemagne V L, Doré V, Bourgeat P , et al. Aβ-amyloid and tau imaging in dementia. Semin Nucl Med, 2017,47(1):75-88. doi: 10.1053/j.semnuclmed.2016.09.006
[21]	Crandall J P, Tahari A K, Juergens R A , et al. A comparison of FLT to FDG PET/CT in the early assessment of chemotherapy response in stages IB-IIIA resectable NSCLC. EJNMMI Res, 2017,7(1):8. doi: 10.1186/s13550-017-0258-3 pmid: 5247390
[22]	Kreisl W C, Fujita M, Fujimura Y , et al. Comparison of [(11)C]-(R)-PK 11195 and [(11)C]PBR28, two radioligands for translocator protein (18 kDa) in human and monkey: Implications for positron emission tomographic imaging of this inflammation biomarker. Neuroimage, 2010,49(4):2924-2932. doi: 10.1016/j.neuroimage.2009.11.056
[23]	Kupsch A R, Bajaj N, Weiland F , et al. Impact of DaTscan SPECT imaging on clinical management, diagnosis, confidence of diagnosis, quality of life, health resource use and safety in patients with clinically uncertain parkinsonian syndromes: a prospective 1-year follow-up of an open-label controlled study. J Neurol Neurosurg Psychiatry, 2012,83(6):620-628. doi: 10.1136/jnnp-2011-301695 pmid: 22492213
[24]	Wang J, Maurer L . Positron emission tomography: applications in drug discovery and drug development. Curr Top Med Chem, 2005,5(11):1053-1075. doi: 10.2174/156802605774297056 pmid: 16181131
[25]	Gomes C M, Abrunhosa A J, Ramos P , et al. Molecular imaging with SPECT as a tool for drug development. Advanced Drug Delivery Reviews, 2011,63(7):547-554. doi: 10.1016/j.addr.2010.09.015 pmid: 20933557
[26]	Huang Q, Zeng Z . A review on real-time 3d ultrasound imaging technology. Biomed Res Int, 2017,2017:1-20. doi: 10.1155/2017/6027029 pmid: 28459067
[27]	Unnikrishnan S , Klibanov A L. microbubbles as ultrasound contrast agents for molecular imaging: preparation and application. Am J Roentgenol, 2012,199(2):292-299. doi: 10.2214/AJR.12.8826 pmid: 22826389
[28]	Sigrist R M S, Liau J, Kaffas A El , et al. Ultrasound elastography: review of techniques and clinical applications. Theranostics, 2017,7(5):1303-1329. doi: 10.7150/thno.18650 pmid: 28435467
[29]	Sbardella E, Tona F, Petsas N , et al. DTI measurements in multiple sclerosis: evaluation of brain damage and clinical implications. Mult Scler Int, 2013,2013:671730. doi: 10.1155/2013/671730 pmid: 23606965
[30]	Liu Z, Pardini M, Yaldizli ? , et al. Magnetization transfer ratio measures in normal-appearing white matter show periventricular gradient abnormalities in multiple sclerosis. Brain, 2015,138(5):1239-1246. doi: 10.1093/brain/awv065 pmid: 25823475
[31]	Chenevert T L, Stegman L D , Taylor J M G, et al. Diffusion magnetic resonance imaging: an early surrogate marker of therapeutic efficacy in brain tumors. J Natl Cancer Inst, 2000,92(24):2029-2036. doi: 10.1093/jnci/92.24.2029 pmid: 11121466
[32]	Evelhoch J L . In vivo MR in the drug pipeline. J Magn Reson, 2018,292:117-128. doi: 10.1016/j.jmr.2018.04.012
[33]	Dulai P S, Sirlin C B, Loomba R . MRI and MRE for non-invasive quantitative assessment of hepatic steatosis and fibrosis in NAFLD and NASH: Clinical trials to clinical practice. J Hepatol, 2016,65(5):1006-1016. doi: 10.1016/j.jhep.2016.06.005 pmid: 27312947
[34]	Roemer F W, Crema M D, Trattnig S , et al. Advances in imaging of osteoarthritis and cartilage. Radiology, 2011,260(2):332-354. doi: 10.1148/radiol.11101359 pmid: 21778451
[35]	Dumas A, Dierksen G A, Gurol M E , et al. Functional magnetic resonance imaging detection of vascular reactivity in cerebral amyloid angiopathy. Ann Neurol, 2012,72(1):76-81. doi: 10.1002/ana.23566 pmid: 22829269
[36]	Yang X, De Andrade V, Scullin W , et al. Low-dose x-ray tomography through a deep convolutional neural network. Sci Rep, 2018,8(1):2575. doi: 10.1038/s41598-018-19426-7
[37]	Xu J, Gong E, Pauly J , et al. 200x low-dose pet reconstruction using deep learning.[ 2017-12-12]. 200x low-dose pet reconstruction using deep learning. [2017-12-12]. .
[38]	Yang G, Yu S, Dong H , et al. DAGAN: deep de-aliasing generative adversarial networks for fast compressed sensing mri reconstruction. IEEE Trans Med Imaging, 2018,37(6):1310-1321. doi: 10.1109/TMI.2017.2785879
[39]	Schlemper J, Caballero J, Hajnal J V , et al. A deep cascade of convolutional neural networks for dynamic mr image reconstruction. IEEE Trans Med Imaging, 2018,37(2):491-503. doi: 10.1109/TMI.2017.2760978 pmid: 29035212
[40]	Cohen O, Zhu B, Rosen M S . MR fingerprinting Deep RecOnstruction NEtwork (DRONE). Magn Reson Med, 2018,80(3):885-894. doi: 10.1002/mrm.27198 pmid: 29624736
[41]	Zhu J-Y, Park T, Isola P , et al. Unpaired image-to-image translation using cycle-consistent adversarial networks.[ 2017-03-30]. Unpaired image-to-image translation using cycle-consistent adversarial networks. [2017-03-30]. .
[42]	Armanious K, Yang C, Fischer M , et al. MedGAN: Medical image translation using GANs.[ 2018-06-17]. MedGAN: Medical image translation using GANs. [2018-06-17]. .
[43]	Maintz J B A, Viergever M A . An Overview of Medical Image Registration Methods.[ 2018-09-19]. . An Overview of Medical Image Registration Methods. [2018-09-19]. .
[44]	Cao X, Yang J, Zhang J , et al. Deformable image registration based on similarity-steered cnn regression//Medical Image Computing and Computer Assisted Intervention ? MICCAI 2017. Springer, 2017: 300-308.
[45]	Li H, Fan Y. Non-rigid image registration using fully convolutional networks with deep self-supervision.[ 2017-09-04]. Non-rigid image registration using fully convolutional networks with deep self-supervision. [2017-09-04]. .
[46]	Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation.[ 2015-05-18]. U-Net: convolutional networks for biomedical image segmentation. [2015-05-18]. .
[47]	Milletari F, Navab N, Ahmadi S-A. V-Net: fully convolutional neural networks for volumetric medical image segmentation.[ 2016-06-15]. V-Net: fully convolutional neural networks for volumetric medical image segmentation. [2016-06-15]. .
[48]	Pelt D M, Sethian J A . A mixed-scale dense convolutional neural network for image analysis. Proc Natl Acad Sci USA, 2018,115(2):254-259. doi: 10.1073/pnas.1715832114 pmid: 29279403
[49]	Conaghan PG , ?stergaard M, Bowes MA, et al. Comparing the effects of tofacitinib, methotrexate and the combination, on bone marrow oedema, synovitis and bone erosion in methotrexate-naive, early active rheumatoid arthritis: results of an exploratory randomised MRI study incorporating semiquantitative and quantitative techniques. Ann Rheum Dis, 2016,75(6):1024-1033. doi: 10.1136/annrheumdis-2015-208267
[50]	Ribli D, Horváth A, Unger Z , et al. Detecting and classifying lesions in mammograms with deep learning. Sci Rep, 2018,8(1):4165. doi: 10.1038/s41598-018-22437-z
[51]	Rajpurkar P, Irvin J, Zhu K , et al. CheXNet: radiologist-level pneumonia detection on chest x-rays with deep learning.[ 2017-11-14]. CheXNet: radiologist-level pneumonia detection on chest x-rays with deep learning. [2017-11-14]. .
[52]	Causey JL, Zhang J, Ma S , et al. Highly accurate model for prediction of lung nodule malignancy with CT scans. Sci Rep, 2018,8(1):9286. doi: 10.1038/s41598-018-27569-w pmid: 29915334
[53]	Gulshan V, Peng L, Coram M , et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 2016,316(22):2402. doi: 10.1001/jama.2016.17216 pmid: 27898976
[54]	Esteva A, Kuprel B, Novoa R A , et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature, 2017,542(7639):115-118. doi: 10.1038/nature21056 pmid: 28117445
[55]	Janowczyk A, Madabhushi A . Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases. J Pathol Inform, 2016,7(1):29. doi: 10.4103/2153-3539.186902 pmid: 27563488
[56]	Tiulpin A, Thevenot J, Rahtu E , et al. Automatic knee osteoarthritis diagnosis from plain radiographs: a deep learning-based approach. Sci Rep, 2018;, 8(1):1727. doi: 10.1038/s41598-018-20132-7 pmid: 29379060
[57]	Duff E P, Vennart W, Wise R G , et al. Learning to identify CNS drug action and efficacy using multistudy fMRI data. Sci Transl Med, 2015, 7(274):274ra16-274ra16. doi: 10.1126/scitranslmed.3008438 pmid: 25673761
[58]	Park J-Y, Na HK, Kim S , et al. Robust identification of alzheimer’s disease subtypes based on cortical atrophy patterns. Sci Rep, 2017,7(1):43270. doi: 10.1038/srep43270 pmid: 28276464
[59]	ten Kate M, Redolfi A, Peira E , et al. MRI predictors of amyloid pathology: results from the EMIF-AD Multimodal Biomarker Discovery study. Alzheimers Res Ther, 2018,10(1):100. doi: 10.1186/s13195-018-0428-1
[60]	Thung K-H, Yap P-T, Adeli E , et al. Conversion and time-to-conversion predictions of mild cognitive impairment using low-rank affinity pursuit denoising and matrix completion. Med Image Anal, 2018,45:68-82. doi: 10.1016/j.media.2018.01.002
[61]	Whitfield-Gabrieli S, Ghosh S S, Nieto-Castanon A , et al. Brain connectomics predict response to treatment in social anxiety disorder. Mol Psychiatry, 2016,21(5):680-685. doi: 10.1038/mp.2015.109 pmid: 26260493
[62]	Lambin P , Leijenaar R T H, Deist T M, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol, 2017,14(12):749-762. doi: 10.1038/nrclinonc.2017.141
[63]	Lao J, Chen Y, Li Z-C , et al. A deep learning-based radiomics model for prediction of survival in glioblastoma multiforme. Sci Rep, 2017,7(1):10353. doi: 10.1038/s41598-017-10649-8 pmid: 28871110
[64]	Grossmann P, Stringfield O, El-Hachem N , et al. Defining the biological basis of radiomic phenotypes in lung cancer. Elife, 2017,6:e23421. doi: 10.7554/elife.23421 pmid: 28731408
[65]	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. Lancet Oncol, 2018,19(9):1180-1191. doi: 10.1016/S1470-2045(18)30413-3
[66]	Wang K, Lu X, Zhou H , et al. Deep learning radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B: a prospective multicentre study. Gut, 2018, 5:gutjnl-2018-316204.
[67]	Harari JH , Díaz-Caneja C M, Janssen J, et al. The association between gene variants and longitudinal structural brain changes in psychosis: a systematic review of longitudinal neuroimaging genetics studies. NPJ Schizophr, 2017,3(1):40. doi: 10.1038/s41537-017-0036-2 pmid: 5665946
[68]	Liu J, Calhoun V D . A review of multivariate analyses in imaging genetics. Front Neuroinform, 2014,8:29. doi: 10.3389/fninf.2014.00029 pmid: 3972473
[69]	Vieira S , Pinaya W H L, Mechelli A. Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: methods and applications. Neurosci Biobehav Rev, 2017,74:58-75. doi: 10.1016/j.neubiorev.2017.01.002 pmid: 28087243
[70]	Sun C, Shrivastava A, Singh S , et al. Revisiting unreasonable effectiveness of data in deep learning era.[ 2017-07-10]. Revisiting unreasonable effectiveness of data in deep learning era. [2017-07-10]. .
[71]	Yan Z, Zhou X S . How intelligent are convolutional neural networks? [2017-09-18]. https://arxiv. org/abs/1709. 06126.
[72]	Zhou Z H . Special topic: machine learning a brief introduction to weakly supervised learning. Natl Sci Rev, 2018,5:44-53. doi: 10.1093/nsr/nwx106
[73]	Jia Z, Huang X, Chang EI-C , et al. Constrained deep weak supervision for histopathology image segmentation. IEEE Transactions on Medical Imaging, 2017,36(11):2376-2388. doi: 10.1109/TMI.2017.2724070 pmid: 28692971
[74]	Tzeng E, Hoffman J, Saenko K , et al. Adversarial discriminative domain adaptation.[ 2017-02-17]. Adversarial discriminative domain adaptation. [2017-02-17]. .
[75]	Zhang Q, Wu Y N, Zhu S-C. Interpretable convolutional neural networks.[ 2017-10-02]. Interpretable convolutional neural networks. [2017-10-02]. .
[76]	Wang X, Peng Y, Lu L , et al. ChestX-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases.[ 2017-05-05]. ChestX-ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. [2017-05-05]. .
[77]	Yan K, Wang X, Lu L , et al. DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. J Med Imaging, 2018,5(03):1.

[1]	武瑞君,李治非,张鑫,濮润,敖翼,孙燕荣. 新冠病毒抗体药物研发进展及展望分析[J]. 中国生物工程杂志, 2020, 40(5): 1-6.
[2]	朱小丽,黄翠,马丽丽,张超,巩玥,赵婉雨,赵秀芳,郭文姣,彭皓,张吉,梁慧刚. 新型冠状病毒病(COVID-19)研究进展[J]. 中国生物工程杂志, 2020, 40(1-2): 38-50.
[3]	彭贤贵,杨武晨,李佳,苟阳,王平,刘思恒,张云,李艺,张曦. 细胞形态相关技术在血液系统肿瘤中的应用 ^*[J]. 中国生物工程杂志, 2019, 39(9): 84-90.
[4]	武奥申,刘小娜,刘昀赫,刘刚,刘雷. 二代基因测序数据管理和大数据平台在精准医学中的应用[J]. 中国生物工程杂志, 2019, 39(2): 101-111.
[5]	蒋析文,董子维,刘悦,朱小亚. 生物标记物与精准医疗研究进展[J]. 中国生物工程杂志, 2019, 39(2): 74-81.
[6]	吴升星, 李艳, 张海燕, 刘洋, 赖琼, 杨明. 诱导多能干细胞技术在药物研发领域中的前景[J]. 中国生物工程杂志, 2017, 37(11): 116-122.

Viewed

Full text

Abstract

Cited

Shared

Discussed