Machine Learning: Discovering the Future of Medical Imaging

Machine Learning: Discovering the Future of Medical Imaging J Digit Imaging (2017) 30:391 DOI 10.1007/s10278-017-9994-1 EDITORIAL Bradley J. Erickson Published online: 26 June 2017 Society for Imaging Informatics in Medicine 2017 Machine learning, and deep learning in particular, is seen as Machine learning does have tremendous promise to reli- both the hope and the downfall of the medical imaging pro- ably identify many findings in images. While BComputers fession. Some hail the promise of computers reliably identify- Replacing Radiologists^ has been a common focus in the ing each and every finding, and some decry it as the demise of popular press, what may be the most exciting is that machine learning seems to be able to find features in images that are not medicine. This issue is devoted to reports on the application of machine learning in medical imaging, some of which were apparent to humans; included in this issue are manuscripts presented at the inaugural Conference on Machine describing prediction of genomic and molecular properties Intelligence in Medical Imaging (C-MIMI). that were once thought only identifiable with tissue. These BWith Great Power Comes Great Responsibility^— capabilities are the drivers behind the great excitement and Spiderman investment in this new field. This issue of JDI includes a broad range of manuscripts It is incumbent upon those of us in this field to understand including ones describing segmentation, classification, or di- and appreciate the potential of these methods to discover agnosis using MR, CT, and US images. There are papers de- things about medical images that may not be intuitive or ex- scribing techniques that are broadly useful in machine learn- pected. This BDiscovery Science^ is an area that has not been ing, and some review articles that provide a vision of the embraced in medical imaging but is a core value in genomics landscape of machine learning in medical imaging. The and precision medicine. Medical imaging must also take up breadth of articles and the techniques described is impressive the BDiscovery Science^ flag and recognize that important and reflects that we are in the early development stages of the advances are not always based on hypothesis testing. application of machine learning in medical imaging. BThe measure of a superhero is always his nemesis^— At the same time, we must be careful that the methods David Lyons applied and the findings reported are reliable. Machine learn- This special issue demonstrates the incredible potential of ing and deep learning, in particular, have great power to find machine learning to advance medical imaging science, and the things that may not be important but seem to be. Spurious attention to methods also demonstrates how we must avoid the connections are a constant risk for the machine learning sci- pitfalls. Machine learning is already dramatically altering the entist, and multiple rigorous tests must be applied to be certain everyday life of everyone and everything on the planet. that the apparent capability of an algorithm is correct. Weather predictions, self-driving cars, satellite-guided crop BEverything In Life Is Speaking Despite Its Apparent husbandry and of course, medical imaging. Silence^—Hazrat Khan Medical imaging has tremendous resources at its disposal. The Biden Cancer Moonshot specifically identifies the tremen- dous assets that are already available to be studied, and the need to efficiently convert the information present into knowledge. We have a responsibility to use those resources to assure that * Bradley J. Erickson bje@mayo.edu our patients receive the best care possible in the most cost- effective way. Machine learning and deep learning in particular, Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA appears to be an important component of achieving that goal. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Digital Imaging Springer Journals

Machine Learning: Discovering the Future of Medical Imaging

Free
1 page

Loading next page...
1 Page
 
/lp/springer_journal/machine-learning-discovering-the-future-of-medical-imaging-aphIgKOt4Z
Publisher
Springer International Publishing
Copyright
Copyright © 2017 by Society for Imaging Informatics in Medicine
Subject
Medicine & Public Health; Imaging / Radiology
ISSN
0897-1889
eISSN
1618-727X
D.O.I.
10.1007/s10278-017-9994-1
Publisher site
See Article on Publisher Site

Abstract

J Digit Imaging (2017) 30:391 DOI 10.1007/s10278-017-9994-1 EDITORIAL Bradley J. Erickson Published online: 26 June 2017 Society for Imaging Informatics in Medicine 2017 Machine learning, and deep learning in particular, is seen as Machine learning does have tremendous promise to reli- both the hope and the downfall of the medical imaging pro- ably identify many findings in images. While BComputers fession. Some hail the promise of computers reliably identify- Replacing Radiologists^ has been a common focus in the ing each and every finding, and some decry it as the demise of popular press, what may be the most exciting is that machine learning seems to be able to find features in images that are not medicine. This issue is devoted to reports on the application of machine learning in medical imaging, some of which were apparent to humans; included in this issue are manuscripts presented at the inaugural Conference on Machine describing prediction of genomic and molecular properties Intelligence in Medical Imaging (C-MIMI). that were once thought only identifiable with tissue. These BWith Great Power Comes Great Responsibility^— capabilities are the drivers behind the great excitement and Spiderman investment in this new field. This issue of JDI includes a broad range of manuscripts It is incumbent upon those of us in this field to understand including ones describing segmentation, classification, or di- and appreciate the potential of these methods to discover agnosis using MR, CT, and US images. There are papers de- things about medical images that may not be intuitive or ex- scribing techniques that are broadly useful in machine learn- pected. This BDiscovery Science^ is an area that has not been ing, and some review articles that provide a vision of the embraced in medical imaging but is a core value in genomics landscape of machine learning in medical imaging. The and precision medicine. Medical imaging must also take up breadth of articles and the techniques described is impressive the BDiscovery Science^ flag and recognize that important and reflects that we are in the early development stages of the advances are not always based on hypothesis testing. application of machine learning in medical imaging. BThe measure of a superhero is always his nemesis^— At the same time, we must be careful that the methods David Lyons applied and the findings reported are reliable. Machine learn- This special issue demonstrates the incredible potential of ing and deep learning, in particular, have great power to find machine learning to advance medical imaging science, and the things that may not be important but seem to be. Spurious attention to methods also demonstrates how we must avoid the connections are a constant risk for the machine learning sci- pitfalls. Machine learning is already dramatically altering the entist, and multiple rigorous tests must be applied to be certain everyday life of everyone and everything on the planet. that the apparent capability of an algorithm is correct. Weather predictions, self-driving cars, satellite-guided crop BEverything In Life Is Speaking Despite Its Apparent husbandry and of course, medical imaging. Silence^—Hazrat Khan Medical imaging has tremendous resources at its disposal. The Biden Cancer Moonshot specifically identifies the tremen- dous assets that are already available to be studied, and the need to efficiently convert the information present into knowledge. We have a responsibility to use those resources to assure that * Bradley J. Erickson bje@mayo.edu our patients receive the best care possible in the most cost- effective way. Machine learning and deep learning in particular, Department of Radiology, Mayo Clinic, Rochester, MN 55905, USA appears to be an important component of achieving that goal.

Journal

Journal of Digital ImagingSpringer Journals

Published: Jun 26, 2017

There are no references for this article.

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off