Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

Veronika Cheplygina; Marleen de Bruijne; Josien P W Pluim

doi:10.1016/j.media.2019.03.009

Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

Veronika Cheplygina, Marleen de Bruijne, Josien P W Pluim

132 Citations (Scopus)

Abstract

Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods that can learn with less/other types of supervision, have been proposed. We give an overview of semi-supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis or segmentation tasks. We also discuss connections between these learning scenarios, and opportunities for future research. A dataset with the details of the surveyed papers is available via https://figshare.com/articles/Database_of_surveyed_literature_in_Not-so-supervised_a_survey_of_semi-supervised_multi-instance_and_transfer_learning_in_medical_image_analysis_/7479416.

Original language	English
Journal	Medical Image Analysis
Volume	54
Pages (from-to)	280-296
Number of pages	17
ISSN	1361-8415
DOIs	https://doi.org/10.1016/j.media.2019.03.009
Publication status	Published - May 2019

Access to Document

10.1016/j.media.2019.03.009

Cite this

@article{2d7679bd78f44abbb6987579efd124a6,

title = "Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis",

abstract = "Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods that can learn with less/other types of supervision, have been proposed. We give an overview of semi-supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis or segmentation tasks. We also discuss connections between these learning scenarios, and opportunities for future research. A dataset with the details of the surveyed papers is available via https://figshare.com/articles/Database_of_surveyed_literature_in_Not-so-supervised_a_survey_of_semi-supervised_multi-instance_and_transfer_learning_in_medical_image_analysis_/7479416.",

author = "Veronika Cheplygina and {de Bruijne}, Marleen and Pluim, {Josien P W}",

note = "Copyright {\textcopyright} 2019. Published by Elsevier B.V.",

year = "2019",

month = may,

doi = "10.1016/j.media.2019.03.009",

language = "English",

volume = "54",

pages = "280--296",

journal = "Medical Image Analysis",

issn = "1361-8415",

publisher = "Elsevier",

}

TY - JOUR

T1 - Not-so-supervised

T2 - A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

AU - Cheplygina, Veronika

AU - de Bruijne, Marleen

AU - Pluim, Josien P W

PY - 2019/5

Y1 - 2019/5

N2 - Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods that can learn with less/other types of supervision, have been proposed. We give an overview of semi-supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis or segmentation tasks. We also discuss connections between these learning scenarios, and opportunities for future research. A dataset with the details of the surveyed papers is available via https://figshare.com/articles/Database_of_surveyed_literature_in_Not-so-supervised_a_survey_of_semi-supervised_multi-instance_and_transfer_learning_in_medical_image_analysis_/7479416.

AB - Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods that can learn with less/other types of supervision, have been proposed. We give an overview of semi-supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis or segmentation tasks. We also discuss connections between these learning scenarios, and opportunities for future research. A dataset with the details of the surveyed papers is available via https://figshare.com/articles/Database_of_surveyed_literature_in_Not-so-supervised_a_survey_of_semi-supervised_multi-instance_and_transfer_learning_in_medical_image_analysis_/7479416.

U2 - 10.1016/j.media.2019.03.009

DO - 10.1016/j.media.2019.03.009

M3 - Journal article

C2 - 30959445

SN - 1361-8415

VL - 54

SP - 280

EP - 296

JO - Medical Image Analysis

JF - Medical Image Analysis

ER -

Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis

Abstract

Access to Document

Fingerprint

Cite this