Machine learning for medical imaging

Research output: Contribution to journalArticle

112 Citations (Scopus)

Abstract

Machine learning is a technique for recognizing patterns that can be applied to medical images. Although it is a powerful tool that can help in rendering medical diagnoses, it can be misapplied. Machine learning typically begins with the machine learning algorithm system computing the image features that are believed to be of importance in making the prediction or diagnosis of interest. The machine learning algorithm system then identifies the best combination of these image features for classifying the image or computing some metric for the given image region. There are several methods that can be used, each with different strengths and weaknesses. There are open-source versions of most of these machine learning methods that make them easy to try and apply to images. Several metrics for measuring the performance of an algorithm exist; however, one must be aware of the possible associated pitfalls that can result in misleading metrics. More recently, deep learning has started to be used; this method has the benefit that it does not require image feature identification and calculation as a first step; rather, features are identified as part of the learning process. Machine learning has been used in medical imaging and will have a greater influence in the future. Those working in medical imaging must be aware of how machine learning works.

Original languageEnglish (US)
Pages (from-to)505-515
Number of pages11
JournalRadiographics
Volume37
Issue number2
DOIs
StatePublished - Mar 1 2017

Fingerprint

Diagnostic Imaging
Learning
Machine Learning

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Machine learning for medical imaging. / Erickson, Bradley J; Korfiatis, Panagiotis; Akkus, Zeynettin; Kline, Timothy.

In: Radiographics, Vol. 37, No. 2, 01.03.2017, p. 505-515.

Research output: Contribution to journalArticle

@article{6d6a87c69cff4f6387b5f871852fdee3,
title = "Machine learning for medical imaging",
abstract = "Machine learning is a technique for recognizing patterns that can be applied to medical images. Although it is a powerful tool that can help in rendering medical diagnoses, it can be misapplied. Machine learning typically begins with the machine learning algorithm system computing the image features that are believed to be of importance in making the prediction or diagnosis of interest. The machine learning algorithm system then identifies the best combination of these image features for classifying the image or computing some metric for the given image region. There are several methods that can be used, each with different strengths and weaknesses. There are open-source versions of most of these machine learning methods that make them easy to try and apply to images. Several metrics for measuring the performance of an algorithm exist; however, one must be aware of the possible associated pitfalls that can result in misleading metrics. More recently, deep learning has started to be used; this method has the benefit that it does not require image feature identification and calculation as a first step; rather, features are identified as part of the learning process. Machine learning has been used in medical imaging and will have a greater influence in the future. Those working in medical imaging must be aware of how machine learning works.",
author = "Erickson, {Bradley J} and Panagiotis Korfiatis and Zeynettin Akkus and Timothy Kline",
year = "2017",
month = "3",
day = "1",
doi = "10.1148/rg.2017160130",
language = "English (US)",
volume = "37",
pages = "505--515",
journal = "Radiographics",
issn = "0271-5333",
publisher = "Radiological Society of North America Inc.",
number = "2",

}

TY - JOUR

T1 - Machine learning for medical imaging

AU - Erickson, Bradley J

AU - Korfiatis, Panagiotis

AU - Akkus, Zeynettin

AU - Kline, Timothy

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Machine learning is a technique for recognizing patterns that can be applied to medical images. Although it is a powerful tool that can help in rendering medical diagnoses, it can be misapplied. Machine learning typically begins with the machine learning algorithm system computing the image features that are believed to be of importance in making the prediction or diagnosis of interest. The machine learning algorithm system then identifies the best combination of these image features for classifying the image or computing some metric for the given image region. There are several methods that can be used, each with different strengths and weaknesses. There are open-source versions of most of these machine learning methods that make them easy to try and apply to images. Several metrics for measuring the performance of an algorithm exist; however, one must be aware of the possible associated pitfalls that can result in misleading metrics. More recently, deep learning has started to be used; this method has the benefit that it does not require image feature identification and calculation as a first step; rather, features are identified as part of the learning process. Machine learning has been used in medical imaging and will have a greater influence in the future. Those working in medical imaging must be aware of how machine learning works.

AB - Machine learning is a technique for recognizing patterns that can be applied to medical images. Although it is a powerful tool that can help in rendering medical diagnoses, it can be misapplied. Machine learning typically begins with the machine learning algorithm system computing the image features that are believed to be of importance in making the prediction or diagnosis of interest. The machine learning algorithm system then identifies the best combination of these image features for classifying the image or computing some metric for the given image region. There are several methods that can be used, each with different strengths and weaknesses. There are open-source versions of most of these machine learning methods that make them easy to try and apply to images. Several metrics for measuring the performance of an algorithm exist; however, one must be aware of the possible associated pitfalls that can result in misleading metrics. More recently, deep learning has started to be used; this method has the benefit that it does not require image feature identification and calculation as a first step; rather, features are identified as part of the learning process. Machine learning has been used in medical imaging and will have a greater influence in the future. Those working in medical imaging must be aware of how machine learning works.

UR - http://www.scopus.com/inward/record.url?scp=85015225428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015225428&partnerID=8YFLogxK

U2 - 10.1148/rg.2017160130

DO - 10.1148/rg.2017160130

M3 - Article

VL - 37

SP - 505

EP - 515

JO - Radiographics

JF - Radiographics

SN - 0271-5333

IS - 2

ER -