Machine learning concepts, concerns and opportunities for a pediatric radiologist

Michael Moore, Einat Slonimsky, Aaron D. Long, Raymond W. Sze, Ramesh S. Iyer

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Machine learning, a subfield of artificial intelligence, is a rapidly evolving technology that offers great potential for expanding the quality and value of pediatric radiology. We describe specific types of learning, including supervised, unsupervised and semisupervised. Subsequently, we illustrate two core concepts for the reader: data partitioning and under/overfitting. We also provide an expanded discussion of the challenges of implementing machine learning in children’s imaging. These include the requirement for very large data sets, the need to accurately label these images with a relatively small number of pediatric imagers, technical and regulatory hurdles, as well as the opaque character of convolution neural networks. We review machine learning cases in radiology including detection, classification and segmentation. Last, three pediatric radiologists from the Society for Pediatric Radiology Quality and Safety Committee share perspectives for potential areas of development.

Original languageEnglish (US)
Pages (from-to)509-516
Number of pages8
JournalPediatric Radiology
Volume49
Issue number4
DOIs
StatePublished - Apr 1 2019

Fingerprint

Pediatrics
Radiology
Artificial Intelligence
Learning
Technology
Safety
Radiologists
Machine Learning
Datasets

All Science Journal Classification (ASJC) codes

  • Pediatrics, Perinatology, and Child Health
  • Radiology Nuclear Medicine and imaging

Cite this

Moore, Michael ; Slonimsky, Einat ; Long, Aaron D. ; Sze, Raymond W. ; Iyer, Ramesh S. / Machine learning concepts, concerns and opportunities for a pediatric radiologist. In: Pediatric Radiology. 2019 ; Vol. 49, No. 4. pp. 509-516.
@article{39dbd82ba7c742fa85aba4d3f11cd0d7,
title = "Machine learning concepts, concerns and opportunities for a pediatric radiologist",
abstract = "Machine learning, a subfield of artificial intelligence, is a rapidly evolving technology that offers great potential for expanding the quality and value of pediatric radiology. We describe specific types of learning, including supervised, unsupervised and semisupervised. Subsequently, we illustrate two core concepts for the reader: data partitioning and under/overfitting. We also provide an expanded discussion of the challenges of implementing machine learning in children’s imaging. These include the requirement for very large data sets, the need to accurately label these images with a relatively small number of pediatric imagers, technical and regulatory hurdles, as well as the opaque character of convolution neural networks. We review machine learning cases in radiology including detection, classification and segmentation. Last, three pediatric radiologists from the Society for Pediatric Radiology Quality and Safety Committee share perspectives for potential areas of development.",
author = "Michael Moore and Einat Slonimsky and Long, {Aaron D.} and Sze, {Raymond W.} and Iyer, {Ramesh S.}",
year = "2019",
month = "4",
day = "1",
doi = "10.1007/s00247-018-4277-7",
language = "English (US)",
volume = "49",
pages = "509--516",
journal = "Pediatric Radiology",
issn = "0301-0449",
publisher = "Springer Verlag",
number = "4",

}

Machine learning concepts, concerns and opportunities for a pediatric radiologist. / Moore, Michael; Slonimsky, Einat; Long, Aaron D.; Sze, Raymond W.; Iyer, Ramesh S.

In: Pediatric Radiology, Vol. 49, No. 4, 01.04.2019, p. 509-516.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Machine learning concepts, concerns and opportunities for a pediatric radiologist

AU - Moore, Michael

AU - Slonimsky, Einat

AU - Long, Aaron D.

AU - Sze, Raymond W.

AU - Iyer, Ramesh S.

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Machine learning, a subfield of artificial intelligence, is a rapidly evolving technology that offers great potential for expanding the quality and value of pediatric radiology. We describe specific types of learning, including supervised, unsupervised and semisupervised. Subsequently, we illustrate two core concepts for the reader: data partitioning and under/overfitting. We also provide an expanded discussion of the challenges of implementing machine learning in children’s imaging. These include the requirement for very large data sets, the need to accurately label these images with a relatively small number of pediatric imagers, technical and regulatory hurdles, as well as the opaque character of convolution neural networks. We review machine learning cases in radiology including detection, classification and segmentation. Last, three pediatric radiologists from the Society for Pediatric Radiology Quality and Safety Committee share perspectives for potential areas of development.

AB - Machine learning, a subfield of artificial intelligence, is a rapidly evolving technology that offers great potential for expanding the quality and value of pediatric radiology. We describe specific types of learning, including supervised, unsupervised and semisupervised. Subsequently, we illustrate two core concepts for the reader: data partitioning and under/overfitting. We also provide an expanded discussion of the challenges of implementing machine learning in children’s imaging. These include the requirement for very large data sets, the need to accurately label these images with a relatively small number of pediatric imagers, technical and regulatory hurdles, as well as the opaque character of convolution neural networks. We review machine learning cases in radiology including detection, classification and segmentation. Last, three pediatric radiologists from the Society for Pediatric Radiology Quality and Safety Committee share perspectives for potential areas of development.

UR - http://www.scopus.com/inward/record.url?scp=85063891349&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063891349&partnerID=8YFLogxK

U2 - 10.1007/s00247-018-4277-7

DO - 10.1007/s00247-018-4277-7

M3 - Article

C2 - 30923883

AN - SCOPUS:85063891349

VL - 49

SP - 509

EP - 516

JO - Pediatric Radiology

JF - Pediatric Radiology

SN - 0301-0449

IS - 4

ER -