Article Text

Download PDFPDF
Decoding pulmonary nodules: can machine learning enhance malignancy risk stratification?
  1. Colin Jacobs
  1. Medical Imaging, Radboudumc, Nijmegen, The Netherlands
  1. Correspondence to Dr Colin Jacobs, Medical Imaging, Radboudumc, Nijmegen, The Netherlands; colin.jacobs{at}radboudumc.nl

Statistics from Altmetric.com

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

Randomised controlled trials, with the National Lung Screening Trial and Dutch-Belgian NELSON trial being the two largest, have demonstrated that lung cancer screening of high-risk individuals using low-dose CT reduces lung cancer mortality compared with no screening or screening with chest X-ray. Fuelled by the positive results of these landmark trials, low-dose CT-based lung cancer screening of high-risk individuals is being implemented at national or regional scale in an increasing number of countries worldwide. A comprehensive overview of the current status of implementation of lung cancer screening worldwide can be observed in the interactive lung cancer screening overview maintained by the Lung Cancer Policy Network.1

One of the challenges in the radiological interpretation of screening CT scans is the management of screen-detected pulmonary nodules. The prevalence of nodules in screening CT scans of the eligible population is high and ranges from 22% to 74%, depending on the inclusion criteria, CT parameters and minimal size cut-off. The vast majority of these pulmonary nodules are benign. This illustrates the importance of accurate risk estimators and management guidelines for screen-detected nodules; they will be crucial to maintain a good sensitivity for malignant nodules, …

View Full Text

Footnotes

  • Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

  • Competing interests None declared.

  • Provenance and peer review Commissioned; internally peer reviewed.

Linked Articles