Format

Send to

Choose Destination
CA Cancer J Clin. 2019 Mar;69(2):127-157. doi: 10.3322/caac.21552. Epub 2019 Feb 5.

Artificial intelligence in cancer imaging: Clinical challenges and applications.

Author information

1
Assistant Professor of Neurosurgery, Department of Neurosurgery, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA.
2
Research Scientist, Department of Radiation Oncology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA.
3
Associate Member, Department of Cancer Epidemiology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL.
4
Professor of Radiology, Department of Radiology, University of Chicago, Chicago, IL.
5
Research Associate, The Francis Crick Institute, London, United Kingdom.
6
Research Associate, University College London Cancer Institute, London, United Kingdom.
7
Research Assistant, Department of Radiology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA.
8
Research Assistant, Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada.
9
Research Assistant, Department of Radiology, Columbia University College of Physicians and Surgeons, New York, NY.
10
Research Assistant, Department of Radiology, New York Presbyterian Hospital, New York, NY.
11
Research Fellow, The Francis Crick Institute, London, United Kingdom.
12
Research Fellow, University College London Cancer Institute, London, United Kingdom.
13
Associate Professor of Neurosurgery, Department of Neurosurgery, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA.
14
Associate Professor, Department of Radiation Oncology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA.
15
Associate Professor, Department of Medicine, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA.
16
Professor of Radiology, Department of Radiology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA.
17
Professor, The Francis Crick Institute, London, United Kingdom.
18
Professor, University College London Cancer Institute, London, United Kingdom.
19
Professor of Radiology, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA.
20
Professor of Radiology, Department of Radiology, Columbia University College of Physicians and Surgeons, New York, NY.
21
Chair, Department of Radiology, New York Presbyterian Hospital, New York, NY.
22
Professor of Radiology, Department of Cancer Physiology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, FL.
23
Assistant Professor, Department of Radiology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA.
24
Associate Professor, Departments of Radiation Oncology and Radiology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA.
25
Professor in AI in Medicine, Radiology and Nuclear Medicine, GROW, Maastricht University Medical Centre (MUMC+), Maastricht, The Netherlands.

Abstract

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.

KEYWORDS:

artificial intelligence; cancer imaging; clinical challenges; deep learning; radiomics

PMID:
30720861
PMCID:
PMC6403009
[Available on 2020-03-01]
DOI:
10.3322/caac.21552
Free full text

Publication type, Grant support

Publication type

Grant support

Supplemental Content

Full text links

Icon for Wiley
Loading ...
Support Center