人工智能在功能与分子影像学的研究进展

郑博文; 陈卫国; 秦耿耿

doi:10.12122/j.issn.1674-4500.2020.01.01

人工智能在功能与分子影像学的研究进展

doi: 10.12122/j.issn.1674-4500.2020.01.01

南方医科大学南方医院放射科，广东广州 510515

基金项目: 广东省自然科学基金（2018A0303130215）；广东科技计划项目（2016ZC0058）；广东省医学科学技术研究基金（A2017496）；南方医科大学科研启动计划项目（QD2016N010）

详细信息

作者简介:
郑博文，硕士，E-mail：bowen0762@163.com

通讯作者:
秦耿耿，副主任医师，E-mail：zealotq@smu.edu.cn

计量
- 文章访问数: 1854
- HTML全文浏览量: 885
- PDF下载量: 111
- 被引次数: 0
出版历程
- 收稿日期: 2019-12-06
- 刊出日期: 2020-01-01

Implementation of artificial intelligence in functional and molecular imaging

Department of Radiology, Nanfang Hospital, Southern Medical University, Guangzhou 510515, China

摘要

摘要: 功能与分子影像学能够提供组织器官功能变化及细胞或分子事件的时间和空间分布信息，而人工智能是一门新兴的计算机技术，在医学影像中具有广泛的应用。将人工智能应用到功能影像学，能够使影像科医生更加高效、充分地利用得到的信息，更加深入地挖掘图像的生物学本质，在疾病早期诊断、有效治疗、预后预测、探索发病机制等方面均具有重要意义。本文将重点阐述人工智能在功能与分子影像学中图像处理、图像解释及质量控制的应用与进展。
- 功能与分子影像学 /
- 人工智能 /
- 机器学习 /
- 深度学习
Abstract: Functional and molecular imaging can visualize and quantitatively measure not only the change of tissue and organ but also cellular and molecular processes in vivo. As new emerging computer technology, artificial intelligence(AI) is widely applied in the area of medical imaging. The implementation of AI on functional and molecular imaging enables the radiologists to make more efficient and full use of the information and explore the biological nature of images, which have a profound impact on the early detection, effective treatment, prognostic prediction, and pathogenesis exploration of disease. This review briefly summarized the implementation and progress of AI on functional and molecular imaging in image processing, image interpretation, and quality control.
- functional and molecular imaging /
- artificial intelligence /
- machine learning /
- deep learning

HTML全文

参考文献(30)

[1]	Hinton GE, Osindero S, Teh YW. A fast learning algorithm for deep belief nets[J]. Neural Comput, 2006, 18(7): 1527-54. doi: 10.1162/neco.2006.18.7.1527
[2]	Lambin P, Rios-Velazquez E, Leijenaar R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-6. doi: 10.1016/j.ejca.2011.11.036
[3]	Cui J, Gong K, Guo N, et al. PET image denoising using unsupervised deep learning[J]. Eur J Nucl Med Mol Imaging, 2019, 46(13): 2780-9. doi: 10.1007/s00259-019-04468-4
[4]	Shiri I, Ghafarian P, Geramifar P, et al. Direct attenuation correction of brain PET images using only emission data via a deep convolutional encoder-decoder (Deep-DAC)[J]. Eur Radiol, 2019, 29(12): 6867-79. doi: 10.1007/s00330-019-06229-1
[5]	Arabi H, Zeng G, Zheng G, et al. Novel adversarial semantic structure deep learning for MRI-guided attenuation correction in brain PET/MRI[J]. Eur J Nucl Med Mol Imaging, 2019, 46(13): 2746-59. doi: 10.1007/s00259-019-04380-x
[6]	Tao Q, Yan W, Wang Y, et al. Deep learning-based method for fully automatic quantification of left ventricle function from Cine Mr images: a multivendor, multicenter study[J]. Radiology, 2019, 290(1): 81-8. doi: 10.1148/radiol.2018180513
[7]	Yu M, Lu Z, Shen C, et al. The best predictor of ischemic coronary stenosis: subtended myocardial volume, machine learning-based FFRCT, or high-risk plaque features?[J]. Eur Radiol, 2019, 29(7): 3647-57. doi: 10.1007/s00330-019-06139-2
[8]	Li Y, Yu M, Dai X, et al. Detection of hemodynamically significant coronary stenosis: CT myocardial perfusion versus machine learning CT fractional flow reserve[J]. Radiology, 2019, 293(2): 305-14. doi: 10.1148/radiol.2019190098
[9]	Tesche C, Otani K, De Cecco CN, et al. Influence of coronary Calcium on diagnostic performance of machine learning CT-FFR: results from MACHINE registry[J]. JACC Cardiovasc Imaging, 2019, 20(8): 30635-7.
[10]	van Hamersvelt RW, Zreik M, Voskuil M, et al. Deep learning analysis of left ventricular myocardium in CT angiographic intermediate-degree coronary stenosis improves the diagnostic accuracy for identification of functionally significant stenosis[J]. Eur Radiol, 2019, 29(5): 2350-9. doi: 10.1007/s00330-018-5822-3
[11]	Meier R, Lux P, Med B, et al. Neural network-derived perfusion Maps for the assessment of lesions in patients with acute ischemic stroke[J]. Radiol Artif Intell, 2019, 1(5): e190019. doi: 10.1148/ryai.2019190019
[12]	Park YW, Oh J, You SC, et al. Radiomics and machine learning May accurately predict the grade and histological subtype in meningiomas using conventional and diffusion tensor imaging[J]. Eur Radiol, 2019, 29(8): 4068-76. doi: 10.1007/s00330-018-5830-3
[13]	Zhang N, Yang G, Gao Z, et al. Deep learning for diagnosis of chronic myocardial infarction on nonenhanced cardiac Cine MRI[J]. Radiology, 2019, 291(3): 606-17. doi: 10.1148/radiol.2019182304
[14]	Bonekamp D, Kohl S, Wiesenfarth M, et al. Radiomic machine learning for characterization of prostate lesions with MRI: comparison to ADC values[J]. Radiology, 2018, 289(1): 128-37. doi: 10.1148/radiol.2018173064
[15]	Aldoj N, Lukas S, Dewey M, et al. Semi-automatic classification of prostate Cancer on multi-parametric Mr imaging using a multi-channel 3D convolutional neural network[J]. Eur Radiol, 2019, 29(8): s00330.
[16]	Antonelli M, Johnston EW, Dikaios NA, et al. Machine learning classifiers can predict Gleason pattern 4 prostate Cancer with greater accuracy than experienced radiologists[J]. Eur Radiol, 2019, 29(9): 4754-64. doi: 10.1007/s00330-019-06244-2
[17]	Zhang S, Song G, Zang Y, et al. Non-invasive radiomics approach potentially predicts non-functioning pituitary adenomas subtypes before surgery[J]. Eur Radiol, 2018, 28(9): 3692-701. doi: 10.1007/s00330-017-5180-6
[18]	Oliveira FM, Faria DB, Costa DC, et al. Extraction, selection and comparison of features for an effective automated computer-aided diagnosis of Parkinson's disease based on[(123)I]FP-CIT SPECT images[J]. Eur J Nucl Med Mol Imaging, 2018, 45(6): 1052-62. doi: 10.1007/s00259-017-3918-7
[19]	Booij J, Dubroff J, Pryma D, et al. Diagnostic performance of the visual reading of(123)I-Ioflupane SPECT images with or without quantification in patients with movement disorders or dementia[J]. J Nucl Med, 2017, 58(11): 1821-6. doi: 10.2967/jnumed.116.189266
[20]	Albert NL, Unterrainer M, Diemling MA, et al. Implementation of the European multicentre database of healthy controls for {[}I-123] FP-CIT SPECT increases diagnostic accuracy in patients with clinically uncertain parkinsonian syndromes[J]. Eur J Nucl Med Mol Imaging, 2016, 43(7): 1315-22. doi: 10.1007/s00259-015-3304-2
[21]	Wenzel M, Milletari F, Krüger J, et al. Automatic classification of dopamine transporter SPECT: deep convolutional neural networks can be trained to be robust with respect to variable image characteristics[J]. Eur J Nucl Med Mol Imaging, 2019, 46(13): 2800-11. doi: 10.1007/s00259-019-04502-5
[22]	Choi H, Ha S, Im HJ, et al. Refining diagnosis of Parkinson's disease with deep learning-based interpretation of dopamine transporter imaging[J]. Neuroimage Clin, 2017, 16(9): 586-94.
[23]	Betancur J, Commandeur F, Motlagh M, et al. Deep learning for prediction of obstructive disease from fast myocardial perfusion SPECT: A multicenter study[J]. JACC Cardiovasc Imaging, 2018, 11(11): 1654-63. doi: 10.1016/j.jcmg.2018.01.020
[24]	Xu L, Tetteh G, Lipkova J, et al. Automated Whole-Body bone lesion detection for multiple myeloma on 68 Ga-Pentixafor PET/CT imaging using deep learning methods[J]. Contrast Media Mol Imaging, 2018, 18(1): 1-11.
[25]	Zhang J, Zhao X, Zhao Y, et al. Value of pre-therapy 18F-FDG PET/CT radiomics in predicting EGFR mutation status in patients with non-small cell lung Cancer[J]. Eur J Nucl Med Mol Imaging, 2019, 18(11): s00259.
[26]	Vonk-Noordegraaf A, Haddad F, Chin KM, et al. Right heart adaptation to pulmonary arterial hypertension: physiology and pathobiology[J]. J Am Coll Cardiol, 2013, 62(25 Suppl): D22-33.
[27]	Dawes TJ, de Marvao A, Shi WA, et al. Machine learning of three-dimensional right ventricular motion enables outcome prediction in pulmonary hypertension: a cardiac Mr imaging study[J]. Radiology, 2017, 283(2): 381-90. doi: 10.1148/radiol.2016161315
[28]	Betancur J, Otaki Y, Motwani M, et al. Prognostic value of combined clinical and myocardial perfusion imaging data using machine learning[J]. JACC Cardiovasc Imaging, 2018, 11(7): 1000-9. doi: 10.1016/j.jcmg.2017.07.024
[29]	Foley KG, Hills RK, Berthon BA, et al. Development and validation of a prognostic model incorporating texture analysis derived from standardised segmentation of PET in patients with oesophageal Cancer[J]. Eur Radiol, 2018, 28(1): 428-36. doi: 10.1007/s00330-017-4973-y
[30]	Ruijsink B, Puyol AE, Oksuz I, et al. Fully automated, Quality-Controlled cardiac analysis from CMR: validation and Large-Scale application to characterize cardiac function[J]. JACC Cardiovasc Imaging, 2019, 10(7): 30585-6.