Artificial intelligence in cancer imaging: Clinical challenges and applications

被引:1271
作者
Bi, Wenya Linda [1 ]
Hosny, Ahmed [2 ]
Schabath, Matthew B. [3 ]
Giger, Maryellen L. [4 ]
Birkbak, Nicolai J. [5 ,6 ]
Mehrtash, Alireza [7 ,8 ]
Allison, Tavis [9 ,10 ]
Arnaout, Omar [1 ]
Abbosh, Christopher [5 ,6 ]
Dunn, Ian F. [1 ]
Mak, Raymond H. [2 ]
Tamimi, Rulla M. [11 ]
Tempany, Clare M. [12 ]
Swanton, Charles [5 ,6 ]
Hoffmann, Udo [13 ,14 ]
Schwartz, Lawrence H. [10 ,15 ]
Gillies, Robert J. [16 ]
Huang, Raymond Y. [7 ]
Aerts, Hugo J. W. L. [2 ,7 ,17 ]
机构
[1] Harvard Med Sch, Brigham & Womens Hosp, Dana Farber Canc Inst, Neurosurg,Dept Neurosurg, Boston, MA 02115 USA
[2] Harvard Med Sch, Dept Radiat Oncol, Brigham & Womens Hosp, Dana Farber Canc Inst, Boston, MA 02115 USA
[3] H Lee Moffitt Canc Ctr & Res Inst, Dept Canc Epidemiol, Tampa, FL USA
[4] Univ Chicago, Dept Radiol, Radiol, Chicago, IL 60637 USA
[5] Francis Crick Inst, London, England
[6] UCL, Inst Canc, London, England
[7] Harvard Med Sch, Dept Radiol, Brigham & Womens Hosp, Dana Farber Canc Inst, Boston, MA 02115 USA
[8] Univ British Columbia, Dept Elect & Comp Engn, Vancouver, BC, Canada
[9] Columbia Univ, Coll Phys & Surg, Dept Radiol, New York, NY USA
[10] New York Presbyterian Hosp, Dept Radiol, New York, NY USA
[11] Harvard Med Sch, Brigham & Womens Hosp, Dept Med, Dana Farber Canc Inst, Boston, MA 02115 USA
[12] Harvard Med Sch, Brigham & Womens Hosp, Dana Farber Canc Inst, Radiol,Dept Radiol, Boston, MA 02115 USA
[13] Massachusetts Gen Hosp, Dept Radiol, Radiol, Boston, MA USA
[14] Harvard Med Sch, Boston, MA 02115 USA
[15] Columbia Univ, Coll Phys & Surg, Dept Radiol, Radiol, New York, NY USA
[16] H Lee Moffitt Canc Ctr & Res Inst, Dept Canc Physiol, Radiol, Tampa, FL USA
[17] MUMC, AI Med Radiol & Nucl Med, GROW, Maastricht, Netherlands
基金
加拿大健康研究院; 加拿大自然科学与工程研究理事会; 英国惠康基金; 美国国家卫生研究院; 英国医学研究理事会;
关键词
artificial intelligence; cancer imaging; clinical challenges; deep learning; radiomics; COMPUTER-AIDED DETECTION; DIGITAL BREAST TOMOSYNTHESIS; BACKGROUND PARENCHYMAL ENHANCEMENT; CONVOLUTIONAL NEURAL-NETWORK; MULTI-PARAMETRIC MRI; DETECTION CAD SYSTEM; HIGH-GRADE GLIOMAS; PROSTATE-CANCER; LUNG-CANCER; PULMONARY NODULES;
D O I
10.3322/caac.21552
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Judgement, as one of the core tenets of medicine, relies upon the integration of multilayered data with nuanced decision making. Cancer offers a unique context for medical decisions given not only its variegated forms with evolution of disease but also the need to take into account the individual condition of patients, their ability to receive treatment, and their responses to treatment. Challenges remain in the accurate detection, characterization, and monitoring of cancers despite improved technologies. Radiographic assessment of disease most commonly relies upon visual evaluations, the interpretations of which may be augmented by advanced computational analyses. In particular, artificial intelligence (AI) promises to make great strides in the qualitative interpretation of cancer imaging by expert clinicians, including volumetric delineation of tumors over time, extrapolation of the tumor genotype and biological course from its radiographic phenotype, prediction of clinical outcome, and assessment of the impact of disease and treatment on adjacent organs. AI may automate processes in the initial interpretation of images and shift the clinical workflow of radiographic detection, management decisions on whether or not to administer an intervention, and subsequent observation to a yet to be envisioned paradigm. Here, the authors review the current state of AI as applied to medical imaging of cancer and describe advances in 4 tumor types (lung, brain, breast, and prostate) to illustrate how common clinical problems are being addressed. Although most studies evaluating AI applications in oncology to date have not been vigorously validated for reproducibility and generalizability, the results do highlight increasingly concerted efforts in pushing AI technology to clinical use and to impact future directions in cancer care.
引用
收藏
页码:127 / 157
页数:31
相关论文
共 219 条
[1]   Phylogenetic ctDNA analysis depicts early-stage lung cancer evolution [J].
Abbosh, Christopher ;
Birkbak, Nicolai J. ;
Wilson, Gareth A. ;
Jamal-Hanjani, Mariam ;
Constantin, Tudor ;
Salari, Raheleh ;
Le Quesne, John ;
Moore, David A. ;
Veeriah, Selvaraju ;
Rosenthal, Rachel ;
Marafioti, Teresa ;
Kirkizlar, Eser ;
Watkins, Thomas B. K. ;
McGranahan, Nicholas ;
Ward, Sophia ;
Martinson, Luke ;
Riley, Joan ;
Fraioli, Francesco ;
Al Bakir, Maise ;
Gronroos, Eva ;
Zambrana, Francisco ;
Endozo, Raymondo ;
Bi, Wenya Linda ;
Fennessy, Fiona M. ;
Sponer, Nicole ;
Johnson, Diana ;
Laycock, Joanne ;
Shafi, Seema ;
Czyzewska-Khan, Justyna ;
Rowan, Andrew ;
Chambers, Tim ;
Matthews, Nik ;
Turajlic, Samra ;
Hiley, Crispin ;
Lee, Siow Ming ;
Forster, Martin D. ;
Ahmad, Tanya ;
Falzon, Mary ;
Borg, Elaine ;
Lawrence, David ;
Hayward, Martin ;
Kolvekar, Shyam ;
Panagiotopoulos, Nikolaos ;
Janes, Sam M. ;
Thakrar, Ricky ;
Ahmed, Asia ;
Blackhall, Fiona ;
Summers, Yvonne ;
Hafez, Dina ;
Naik, Ashwini .
NATURE, 2017, 545 (7655) :446-+
[2]   Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic Screening [J].
Aberle, Denise R. ;
Adams, Amanda M. ;
Berg, Christine D. ;
Black, William C. ;
Clapp, Jonathan D. ;
Fagerstrom, Richard M. ;
Gareen, Ilana F. ;
Gatsonis, Constantine ;
Marcus, Pamela M. ;
Sicks, JoRean D. .
NEW ENGLAND JOURNAL OF MEDICINE, 2011, 365 (05) :395-409
[3]   The Potential of Radiomic-Based Phenotyping in PrecisionMedicine A Review [J].
Aerts, Hugo J. W. L. .
JAMA ONCOLOGY, 2016, 2 (12) :1636-1642
[4]   Defining a Radiomic Response Phenotype: A Pilot Study using targeted therapy in NSCLC [J].
Aerts, Hugo J. W. L. ;
Grossmann, Patrick ;
Tan, Yongqiang ;
Oxnard, Geoffrey G. ;
Rizvi, Naiyer ;
Schwartz, Lawrence H. ;
Zhao, Binsheng .
SCIENTIFIC REPORTS, 2016, 6
[5]   Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach [J].
Aerts, Hugo J. W. L. ;
Velazquez, Emmanuel Rios ;
Leijenaar, Ralph T. H. ;
Parmar, Chintan ;
Grossmann, Patrick ;
Cavalho, Sara ;
Bussink, Johan ;
Monshouwer, Rene ;
Haibe-Kains, Benjamin ;
Rietveld, Derek ;
Hoebers, Frank ;
Rietbergen, Michelle M. ;
Leemans, C. Rene ;
Dekker, Andre ;
Quackenbush, John ;
Gillies, Robert J. ;
Lambin, Philippe .
NATURE COMMUNICATIONS, 2014, 5
[6]   Unsupervised Medical Image Segmentation Based on the Local Center of Mass [J].
Aganj, Iman ;
Harisinghani, Mukesh G. ;
Weissleder, Ralph ;
Fischl, Bruce .
SCIENTIFIC REPORTS, 2018, 8
[7]   Diagnostic accuracy of multi-parametric MRI and TRUS biopsy in prostate cancer (PROMIS): a paired validating confirmatory study [J].
Ahmed, Hashim U. ;
Bosaily, Ahmed El-Shater ;
Brown, Louise C. ;
Gabe, Rhian ;
Kaplan, Richard ;
Parmar, Mahesh K. ;
Collaco-Moraes, Yolanda ;
Ward, Katie ;
Hindley, Richard G. ;
Freeman, Alex ;
Kirkham, Alex P. ;
Oldroyd, Robert ;
Parker, Chris ;
Emberton, Mark .
LANCET, 2017, 389 (10071) :815-822
[8]   A prognostic cytogenetic scoring system to guide the adjuvant management of patients with atypical meningioma [J].
Aizer, Ayal A. ;
Abedalthagafi, Malak ;
Bi, Wenya Linda ;
Horvath, Margaret C. ;
Arvold, Nils D. ;
Al-Mefty, Ossama ;
Lee, Eudocia Q. ;
Nayak, Lakshmi ;
Rinne, Mikael L. ;
Norden, Andrew D. ;
Reardon, David A. ;
Wen, Patrick Y. ;
Ligon, Keith L. ;
Ligon, Azra H. ;
Beroukhim, Rameen ;
Dunn, Ian F. ;
Santagata, Sandro ;
Alexander, Brian M. .
NEURO-ONCOLOGY, 2016, 18 (02) :269-274
[9]   Predicting Deletion of Chromosomal Arms 1p/19q in Low-Grade Gliomas from MR Images Using Machine Intelligence [J].
Akkus, Zeynettin ;
Ali, Issa ;
Sedlar, Jiri ;
Agrawal, Jay P. ;
Parney, Ian F. ;
Giannini, Caterina ;
Erickson, Bradley J. .
JOURNAL OF DIGITAL IMAGING, 2017, 30 (04) :469-476
[10]   Validation of a method for measuring the volumetric breast density from digital mammograms [J].
Alonzo-Proulx, O. ;
Packard, N. ;
Boone, J. M. ;
Al-Mayah, A. ;
Brock, K. K. ;
Shen, S. Z. ;
Yaffe, M. J. .
PHYSICS IN MEDICINE AND BIOLOGY, 2010, 55 (11) :3027-3044