Machine learning for medical imaging: methodological failures and recommendations for the future

Gaël Varoquaux, Veronika Cheplygina

Publikation: Artikel i tidsskrift og konference artikel i tidsskriftTidsskriftartikelForskningpeer review

Abstract

Research in computer analysis of medical images bears many promises to improve patients’ health. However, a number of systematic challenges are slowing down the progress of the field, from limitations of the data, such as biases, to research incentives, such as optimizing for publication. In this paper we review roadblocks to developing and assessing methods. Building our analysis on evidence from the literature and data challenges, we show that at every step, potential biases can creep in. On a positive note, we also discuss on-going efforts to counteract these problems. Finally we provide recommendations on how to further address these problems in the future.

OriginalsprogEngelsk
TidsskriftNature Digital Medicine
ISSN2398-6352
DOI
StatusUdgivet - 2022

Emneord

  • Medical Image Analysis
  • Systematic Challenges
  • Data Biases
  • Research Incentives
  • Bias Mitigation Strategies

Fingeraftryk

Dyk ned i forskningsemnerne om 'Machine learning for medical imaging: methodological failures and recommendations for the future'. Sammen danner de et unikt fingeraftryk.

Citationsformater