山东大学学报 (医学版) ›› 2021, Vol. 59 ›› Issue (9): 89-96.doi: 10.6040/j.issn.1671-7554.0.2021.1017
王琳琳1,孙玉萍2
WANG Linlin1, SUN Yuping2
摘要： 在癌症的精准诊疗中,以深度学习为代表的人工智能技术日益展现出巨大的潜力。在医学影像、病理学等领域,人工智能技术的出现不仅有望大大降低相关科室人员的工作量,通过对影像、病理学图片进行定量描述,人工智能技术也可进一步挖掘出医学数据中潜在的复杂模式。综述首先对目前流行的人工智能技术进行简单的介绍。其次,重点探讨了深度学习技术如何最先影响到癌症影像诊断学的。随后,介绍了人工智能技术在癌症病理学、基因组学、免疫治疗等领域的最新进展。最后,进一步探讨了癌症领域人工智能临床落地过程中存在的困难,并提出一些可能的解决思路,以期为未来的研究提供参考。
中图分类号:
| [1] Mnih V, Kavukcuoglu K, Silver D, et al. Human-level control through deep reinforcement learning [J]. Nature, 2015, 518(7540): 529-533. [2] Moravcík M, Schmid M, Burch N, et al. DeepStack: expert-level artificial intelligence in heads-up no-limit poker [J]. Science, 2017, 356(6337): 508-513. [3] Xiong W, Droppo J, Huang X, et al. Achieving human parity in conversational speech recognition [EB/OL].(2017-02-17)[2021-05-10]. https://arxiv.org/abs/1610.05256. [4] Pendleton SD, Andersen H, Du X, et al. Perception, planning, control, and coordination for autonomous vehicles [J]. Machines, 2017, 5(1): 6. [5] Silver D, Huang A, Maddison CJ, et al. Mastering the game of Go with deep neural networks and tree search [J]. Nature, 2016, 529(7587): 484-489. [6] Grace K, Salvatier J, Dafoe A, et al. When will AI exceed human performance? evidence from AI experts [EB/OL].(2018-07-31)[2021-05-10]. https://arxiv.org/abs/1705.08807. [7] Rusk N. Deep learning [J]. Nature Methods, 2016, 13(1): 35-35. [8] Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks [J]. Nature, 2017, 542(7639): 115-118. [9] 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 [J]. JAMA, 2016, 316(22): 2402-2410. [10] Castellino RA. Computer aided detection(CAD): an overview [J]. Cancer Imaging, 2005, 5: 17-19. doi:10.1102/1470-7330.2005.0018. [11] Cole EB, Zhang Z, Marques HS, et al. Impact of computer-aided detection systems on radiologist accuracy with digital mammography [J]. AJR Am J Roentgenol, 2014, 203(4): 909-916. [12] Lehman CD, Wellman RD, Buist DS, et al. Diagnostic accuracy of digital screening mammography with and without computer-aided detection [J]. JAMA Intern Med, 2015, 175(11): 1828-1837. [13] Huang X, Shan J, Vaidya V. Lung nodule detection in CT using 3D convolutional neural networks[C] //2017 IEEE 14th International Symposium on Biomedical Imaging(ISBI 2017). Piscataway, NJ: IEEE, 2017: 379-383. [14] Armato SG, Petrick NA, Tsehay YK, et al. SPIE Proceedings [SPIE SPIE Medical Imaging - Orlando, Florida, United States(Saturday 11 February 2017)] Medical Imaging 2017: Computer-Aided Diagnosis - Convolutional neural network based deep-learning architecture for prostate cancer detection on multi [J]. onAcademic, 2017, 10134: 1013405. doi: 10.1117/12.2254423. [15] Kooi T, Litjens G, van Ginneken B, et al. Large scale deep learning for computer aided detection of mammographic lesions [J]. Med Image Anal, 2017, 35: 303-312. doi:10.1016/j.media.2016.07.007. [16] Champaign JL, Cederbom GJ. Advances in breast cancer detection with screening mammography [J]. Ochsner J, 2000, 2(1): 33-35. [17] Shiraishi J, Li Q, Appelbaum D, et al. Computer-aided diagnosis and artificial intelligence in clinical imaging [J]. Semin Nucl Med, 2011, 41(6): 449-462. [18] Cheng JZ, Ni D, Chou YH, et al. Computer-aided diagnosis with deep learning architecture: applications to breast lesions in US images and pulmonary nodules in CT scans [J]. Sci Rep, 2016, 6: 24454. doi:10.1038/srep24454. [19] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation [J]. IEEE Trans Pattern Anal Mach Intell, 2017, 39(4): 640-651. doi:10.1109/TPAMI.2016.2572683. [20] Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation [C]. International Conference on Medical Image Computing and Computer-Assisted Intervention. Switzerland: Springer International Publishing, 2015. [21] Moeskops P, Wolterink JM, van der Velden BHM, et al. Deep learning for multi-task medical image segmentation in multiple modalities [C]. International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham:Springer, 2016: 478-486. [22] Jaffe CC. Measures of response: RECIST, WHO, and new alternatives [J]. J Clin Oncol, 2006, 24(20): 3245-3251. [23] Ehteshami Bejnordi B, Veta M, Johannes van Diest P, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer [J]. JAMA, 2017, 318(22): 2199-2210. [24] Mobadersany P, Yousefi S, Amgad M, et al. Content summaries of selected best papers for the 2019 IMIA yearbook, section bioinformatics and translational informatics [J]. Proc Natl Acad Sci USA, 2018, 115(13): E2970-E2979. [25] Ehteshami Bejnordi B, Veta M, Johannes van Diest P, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer [J]. JAMA, 2017, 318(22): 2199-2210. [26] Zou J, Huss M, Abid A, et al. A primer on deep learning in genomics [J]. Nat Genet, 2019, 51(1): 12-18. [27] F Stephen Hodi, O'Day SJ, McDermott DF, et al. Improved survival with ipilimumab in patients with metastatic melanoma [J]. N Engl J Med, 2010, 363(8): 711-723. [28] Garon EB, Rizvi NA, Hui R, et al. Pembrolizumab for the treatment of non-small-cell lung cancer [J]. N Engl J Med, 2015, 372(21): 2018-2028. [29] Borghaei H, Paz-Ares L, Horn L, et al. Nivolumab versus docetaxel in advanced nonsquamous non-small-cell lung cancer [J]. N Engl J Med, 2015, 373(17): 1627-1639. [30] Ferris RL, Blumenschein G, Fayette J, et al. Nivolumab for recurrent squamous-cell carcinoma of the head and neck [J]. N Engl J Med, 2016, 375(19): 1856-1867. [31] Le DT, Durham JN, Smith KN, et al. Mismatch repair deficiency predicts response of solid tumors to PD-1 blockade [J]. Science, 2017, 357(6349): 409-413. [32] Motzer RJ, Escudier B, McDermott DF, et al. Nivolumab versus everolimus in advanced renal-cell carcinoma [J]. N Engl J Med, 2015, 373(19): 1803-1813. [33] Brahmer J, Reckamp KL, Baas P, et al. Nivolumab versus docetaxel in advanced squamous-cell non-small-cell lung cancer [J]. N Engl J Med, 2015, 373(2): 123-135. [34] Mehra R, Seiwert TY, Gupta S, et al. Efficacy and safety of pembrolizumab in recurrent/metastatic head and neck squamous cell carcinoma: pooled analyses after long-term follow-up in KEYNOTE-012 [J]. Br J Cancer, 2018, 119(2): 153-159. [35] Hamanishi J, Mandai M, Ikeda T, et al. Safety and antitumor activity of anti-PD-1 antibody, nivolumab, in patients with platinum-resistant ovarian cancer [J]. J Clin Oncol, 2015, 33(34): 4015-4022. [36] Larkin J, Chiarion-Sileni V, Gonzalez R, et al. Combined nivolumab and ipilimumab or monotherapy in untreated melanoma [J]. N Engl J Med, 2015, 373(1): 23-34. [37] Langer CJ, Gadgeel SM, Borghaei H, et al. Carboplatin and pemetrexed with or without pembrolizumab for advanced, non-squamous non-small-cell lung cancer: a randomised, phase 2 cohort of the open-label KEYNOTE-021 study [J]. Lancet Oncol, 2016, 17(11): 1497-1508. [38] Topalian SL, Taube JM, Anders RA, et al. Mechanism-driven biomarkers to guide immune checkpoint blockade in cancer therapy [J]. Nat Rev Cancer, 2016, 16(5): 275-287. [39] Sunshine J, Taube JM. PD-1/PD-L1 inhibitors[J]. Curr Opin Pharmacol, 2015, 23: 32-38. doi:10.1016/j.coph.2015.05.011. [40] Xie F, Zhang J, Wang J, et al. Multifactorial deep learning reveals Pan-cancer genomic tumor clusters with distinct immunogenomic landscape and response to immunotherapy [J]. Clin Cancer Res, 2020, 26(12): 2908-2920. [41] Hosny A, Parmar C, Quackenbush J, et al. Artificial intelligence in radiology [J]. Nat Rev Cancer, 2018, 18(8): 500-510. [42] Vamathevan J, Clark D, Czodrowski P, et al. Applications of machine learning in drug discovery and development [J]. Nat Rev Drug Discov, 2019, 18(6): 463-477. [43] Bera K, Schalper KA, Rimm DL, et al. Artificial intelligence in digital pathology-new tools for diagnosis and precision oncology [J]. Nat Rev Clin Oncol, 2019, 16(11): 703-715. [44] Nagendran M, Chen Y, Lovejoy CA, et al. Artificial intelligence versus clinicians: systematic review of design, reporting standards, and claims of deep learning studies [J]. BMJ, 2020, 368: m689. doi:10.1136/bmj.m689. [45] Liu X, Faes L, Kale AU, et al. A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis [J]. Lancet Digital Health, 2019, 1(6): e271-e297. [46] Justice AC, Covinsky KE, Berlin JA. Assessing the generalizability of prognostic information [J]. Ann Intern Med, 1999, 130(6): 515-524. [47] Subbaswamy A, Saria S. From development to deployment: dataset shift, causality, and shift-stable models in health AI [J]. Biostatistics, 2020, 21(2): 345-352. [48] Zech JR, Badgeley MA, Liu M. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study [J]. PLoS Met, 2018, 15(11): e1002683. [49] Winkler JK, Fink C, Toberer F, et al. Association between surgical skin markings in dermoscopic images and diagnostic performance of a deep learning convolutional neural network for melanoma recognition [J]. JAMA dermatology, 2019, 155(10): 1135-1141. [50] Narla A, Kuprel B, Sarin K, et al. Automated classification of skin lesions: from pixels to practice [J]. J Invest Dermatol, 2018, 138(10): 2108-2110. [51] Moons KG, Altman DG, Reitsma JB, et al. Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis(TRIPOD): explanation and elaboration [J]. Ann Intern Med, 2015, 162(1): W1-73. [52] Ioannidis JPA, Khoury MJ. Improving validation practices in “omics” research [J]. Science, 2011, 334(6060): 1230-1232. [53] Obermeyer Z, Emanuel EJ. Predicting the future- big data, machine learning, and clinical medicine [J]. N Engl J Med, 2016, 375(13): 1216-1219. [54] Keane PA, Topol EJ. With an eye to AI and autonomous diagnosis [J]. NPJ Digit Med, 2018, 1: 40. doi:10.1038/s41746-018-0048-y. [55] Kawaguchi K, Kaelbling LP, Bengio Y. Generalization in deep learning[EB/OL].(2020-07-27)[2021-05-12]. https://arxiv.org/abs/1710.05468. [56] LeCun Y, Bengio Y, Hinton G. Deep learning [J]. Nature, 2015, 521(7553): 436-444. [57] Pfeifer R, Schreter Z, Fogelman-Soulié F,et al. Connectionism in perspective [M]. Amsterdam: Elsevier, 1989. [58] Pan SJ, Yang Q. A survey on transfer learning[J]. Ieee T Knowl Data En, 2009, 22(10): 1345-1359. [59] Weiss K, Khoshgoftaar TM, Wang DD. A survey of transfer learning [J]. J Big Data, 2016, 3(1):1-40. [60] Deng J, Dong W, Socher R, et al. Imagenet: a large-scale hierarchical image database [C]. IEEE Conf Comput Vis Pattern Recog Piscataway, NJ: Ieee, 2009: 248-255. [61] Shankar S, Halpern Y, Breck E, et al. No classification without representation: assessing geodiversity issues in open data sets for the developing world [EB/OL].(2017-11-22)[2021-05-13]. https://arxiv.org/abs/1711.08536. [62] Geirhos R, Rubisch P, Michaelis C, et al. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness [EB/OL].(2019-01-14)[2021-05-13]. https://arxiv.org/abs/1811.12231. [63] Sun C, Shrivastava A, Singh S, et al. Revisiting unreasonable effectiveness of data in deep learning era [EB/OL].(2017-08-04)[2021-05-13]. https://arxiv.org/abs/1707.02968. [64] Simard P, Victorri B, LeCun Y, et al. Tangent prop-a formalism for specifying selected invariances in an adaptive network [C]. NIPS, 1991, 91: 895-903. [65] de Andrade A. Best practices for convolutional neural networks applied to object recognition in images [EB/OL].(2019-10-29)[2021-05-13]. https://arxiv.org/abs/1910.13029. [66] Shorten C, Khoshgoftaar TM. A survey on image data augmentation for deep learning [J]. J Big Data, 2019, 6(1): 1-48. [67] Roth HR, Lu L, Liu J, et al. Improving computer-aided detection using convolutional neural networks and random view aggregation [J]. IEEE Trans Med Imaging, 2016, 35(5): 1170-1181. [68] Lakhani P, Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks [J]. Radiology, 2017, 284(2): 574-582. [69] Zeshan, Hussain, Francisco, et al. Differential data augmentation techniques for medical imaging classification tasks [J]. Amia Annu Symp Proc, 2018, 2017: 979. [70] Sajjad M, Khan S, Muhammad K, et al. Multi-grade brain tumor classification using deep CNN with extensive data augmentation [J]. J Comput Sci, 2019, 30: 174-182. doi:10.1016/j.jocs.2018.12.003. [71] Stacke K, Eilertsen G, Unger J, et al. Measuring domain shift for deep learning in histopathology [J]. IEEE J Biomed Health, 2020, 25(2): 325-336. [72] ellez D, Litjens G, Bándi P, et al. Quantifying the effects of data augmentation and stain color normalization in convolutional neural networks for computational pathology [J]. Med Image Anal, 2019, 58: 101544. doi:10.1016/j.media.2019.101544. [73] van den Hout WB. The area under an ROC curve with limited information [J]. Med Decis Making, 2003, 23(2): 160-166. [74] Fawcett T. An introduction to ROC analysis[J]. Pattern recognition letters, 2006, 27(8): 861-874. [75] Harrell FE, Califf RM, Pryor DB, et al. Evaluating the yield of medical tests [J]. Jama, 1982, 247(18): 2543-2546. [76] Lobo JM, Jiménez-Valverde A, Real R. AUC: a misleading measure of the performance of predictive distribution models [J]. Global Ecol Biogeogr, 2008, 17(2): 145-151. [77] Ioannidis JPA. What have we(not)learnt from millions of scientific papers with P values? [J]. Am Stat, 2019, 73(Suppl1): 20-25. [78] Michiels S, Koscielny S, Hill C. Prediction of cancer outcome with microarrays: a multiple random validation strategy [J]. Lancet, 2005, 365(9458): 488-492. [79] Miller, R.G. Simultaneous statistical inference [M]. 2nd edition. Cham: Springer, 1981. [80] Hochberg Y, Tamhane AC. Multiple comparison procedures [M]. New Jersey: John Wiley & Sons, Inc, 1987. |
| [1] | 王伟 王沂峰 张岭梅 林琼燕 黄菊. 人卵巢癌OVCAR3细胞系中侧群细胞的分离及其成瘤性、侵袭性的实验研究[J]. 山东大学学报(医学版), 2209, 47(6): 8-11. |
| [2] | 张士宝 刘庆勇 阮喜云 陈杰 张建军 李宗武 杨广笑 王全颖. NT4-SAC-HA2-TAT融合基因表达载体的构建及鉴定[J]. 山东大学学报(医学版), 2209, 47(6): 15-19. |
| [3] | 李波波 李道堂 刘曙光 王兴武. 食管癌患者血清中DKK-1的表达[J]. 山东大学学报(医学版), 2209, 47(6): 58-61. |
| [4] | 鹿向东 杨伟 徐广明 曲元明. 脑膜瘤中PPAR-γ的表达及曲格列酮对脑膜瘤培养细胞生长的影响[J]. 山东大学学报(医学版), 2209, 47(6): 65-. |
| [5] | 黄方 康瑞 吴春林. VEGFC、NF-κBp65及Survivin在鼻咽癌中的表达及临床意义[J]. 山东大学学报(医学版), 2209, 47(6): 83-. |
| [6] | 梁晨,姚丽娟,吕龙飞,唐泽,秦达,崔有斌,余孝淇. 三维重建联合CT引导下穿刺定位在微创治疗肺磨玻璃结节中的应用[J]. 山东大学学报 (医学版), 2026, 64(5): 74-82. |
| [7] | 林明霞,刘桂斌,马燕花,连曌昱,任洋洋. ATP酶铜转运蛋白α介导的铜死亡途径及在肿瘤治疗中的价值[J]. 山东大学学报 (医学版), 2026, 64(4): 117-124. |
| [8] | 中国医师协会骨科医师分会智能骨科学组,中华预防医学会脊柱疾病预防与控制专业委员会脊柱脊髓损伤疾病预防与控制学组. 人工智能脊柱退变影像学测量位点与标注专家共识(2025)[J]. 山东大学学报 (医学版), 2026, 64(2): 1-10. |
| [9] | 季心宇,余思沂,孙圆圆,姬冰. 基于人工智能和步态分析的骨科疾病辅助诊疗方法[J]. 山东大学学报 (医学版), 2026, 64(2): 34-43. |
| [10] | 邹宇锦,万熠,纪振冰,梁西昌. 促骨再生-抗肿瘤双功能钛合金植入体的生物实验研究[J]. 山东大学学报 (医学版), 2026, 64(2): 50-65. |
| [11] | 王建民,李晓峰,由志涛,董圣杰,赵宇驰,李占菊,邹德鑫,张剑锋,孙涛,杜伟. 基于可解释机器学习的后路腰椎椎体间融合术后慢性疼痛风险预测模型构建[J]. 山东大学学报 (医学版), 2026, 64(2): 78-88. |
| [12] | 李雪凯,孙淋涵,刘端瑞,倪阳. 乳酸化修饰在肿瘤炎癌进程中的功能与机制研究进展[J]. 山东大学学报 (医学版), 2025, 63(9): 65-76. |
| [13] | 杨帆. 多模态医学数据融合技术及应用[J]. 山东大学学报 (医学版), 2025, 63(8): 17-40. |
| [14] | 王雪梅,杨豪,宋洋,程世超,张婷婷,王艳春. 抗糖尿病药物与女性恶性肿瘤的因果关联:一项两样本孟德尔随机化分析[J]. 山东大学学报 (医学版), 2025, 63(6): 67-77. |
| [15] | 赵汉卿,周新睿,李子建,唐兴. 循环肿瘤细胞联合血清学检测在非小细胞肺癌中的应用[J]. 山东大学学报 (医学版), 2025, 63(5): 79-85. |
|
||
