Clinical decision support for 19 patterns
+ nodule detection

contextflow SEARCH Lung CT provides radiologists with complementary information for the identification and interpretation of lung-specific image patterns in CT scans.

  • Detects, highlights & quantifies lung abnormalities
  • Retrieves visually-similar, expert-verified reference cases
  • Enriches the reading worklist with quantitative image analysis results
  • Enhances reporting with quantitative and visual information
  • Provides heatmaps with visual overview of lung abnormalities
  • View sample integration

contextflow SEARCH Quantitative image analysis

  • Provides lung coverage values and distribution maps for 6 image patterns + visualization and measurements of detected lung nodules
    • Effusion
    • Emphysema
    • Ground-glass opacity
    • Honeycombing
    • Nodules
    • Pneumothorax
    • Reticular Pattern

Preliminary study results show average reading time is 31% shorter when contextflow SEARCH Lung CT is available for use with a trend towards improved diagnostic accuracy. These results hold for both junior and senior radiologists.*

*Not yet published study results

contextflow SEARCH Qualitative analysis

  • Analyzes and classifies 19 image patterns in selected regions of interest
  • Retrieves visually-similar, expert-labeled reference cases
  • Provides relevant links to literature, guidelines and differential diagnoses
  • We currently support the following patterns in lung CTs:
  • airway wall thickening 
  • atelectasis
  • bronchiectasis
  • bulla
  • consolidation
  • cyst
  • effusion
  • emphysema
  • ground glass
  • honeycombing
  • mass
  • mosaic perfusion pattern
  • nodular pattern
  • nodule
  • pneumothorax
  • pulmonary cavity
  • reticular pattern
  • tree-in-bud
  • non-specific: includes image patterns not currently incorporated and patterns with no evidence of pathological changes

Schedule a demo

Download Flyer


I really like the transparency of contextflow SEARCH as opposed to other black box AI solutions. It’s designed to support my workflow while leaving the final decision up to me.

Elmar Kotter

Vice Chair and Head of Imaging Informatics at the Department of Radiology at Freiburg University Medical Center


After using and advising several radiology AI software companies, I can say that what contextflow offers is actually the next generation of AI products to support the radiologist, not replace them. Their general approach means they recognize all relevant findings, not just one.

Anand Patel

MD, Chief of Interventional Radiology, Providence Little Company of Mary Medical Centers


We’re very interested in using AI to improve the hospital experience for both doctors and patients; contextflow’s use of deep learning, particularly for lung diseases, is exactly the type of technology we want to evaluate. I very much look forward to the results.

Christian Herold

Head of Radiology at Vienna General Hospital


At Dubrava University Hospital, we take pride in providing the best care possible to our patients. There are many AI radiology solutions, but we agreed to the proof of concept with contextflow because their solution provides real value, particularly for new residents.

Boris Brkljacic

President of the European Society of Radiology


We are very interested in using tools based on artificial intelligence like contextflow SEARCH to support the decision in the diagnostic process based on the image.

Lluís Donoso Bach

President of the International Society of Radiology