AI for Thoracic Oncology

Lung cancer is the leading cause of cancer-related death worldwide, for which the five-year survival rates have yet to surpass 20%. The World Health Organization (WHO) has estimated that there were 2.21 million cases of lung cancer and 1.80 million deaths due to lung cancer in 2020. Tobacco smoking remains the main risk factor for lung cancer. Imaging is crucial for early detection, diagnosis, treatment planning and monitoring of lung cancer. It plays an important role in the multidisciplinary management of lung cancer patients.

In the AI for Thoracic Imaging research group, we aim to develop, validate and deploy algorithms that assist in the interpretation of radiological imaging for lung cancer. This research group is led by Colin Jacobs.

Lung AI group

Click on the cards below to learn about the various projects in this research group.

Projects

NELSON-POP: Personalized outcome prediction in lung cancer screening

Accurate estimation of the probability of lung cancer of screen-detected pulmonary nodules using artificial intelligence

Read more →
SOLACE: Strengthening the screening Of Lung cAnCer in Europe

Strengthening the screening of lung cancer in Europe

Read more →
MERAI Lab: MeVis and Radboudumc ICAI Lab

MERAI Lab is a collaboration between Radboudumc and MeVis Medical Solutions AG with the aim to create AI solutions in the lung oncology field.

Read more →
AMARA: Accurate malignancy risk estimation of pulmonary nodules using AI

Accurate malignancy risk estimation of pulmonary nodules using artificial intelligence

Read more →
IMAGIO: Imaging and Advanced Guidance for Workflow Optimization in Interventional Oncology

IMAGIO will leverage Interventional Oncology in the clinical setting to improve the cancer survival outcomes, through minimally invasive, efficient, and affordable care pathways for three disease states: liver cancer, lung cancer and sarcoma.

Read more →

Algorithms

Several algorithms that this group has developed can be tried on the grand-challenge.org platform:

Lung nodule detection for routine clinical CT scans

Deep learning for the detection of pulmonary nodules in chest CT scans

Airway nodule detection for routine clinical CT scans

Deep learning for the detection of airway nodules in chest CT scans

Pulmonary Nodule Malignancy Prediction

Deep Learning for Malignancy Probability Estimation of Low-Dose Screening CT Detected Pulmonary Nodules

Deep learning to estimate pulmonary nodule malignancy risk using a current and a prior CT image

Deep learning to estimate pulmonary nodule malignancy risk using a prior CT image

People

Colin Jacobs

Colin Jacobs

Associate Professor

Cornelia Schaefer-Prokop

Cornelia Schaefer-Prokop

Senior Researcher

Ernst Scholten

Ernst Scholten

Senior Researcher

Noa Antonissen

Noa Antonissen

Postdoctoral Researcher

Dré Peeters

Dré Peeters

PhD Candidate

Renate Dinnessen

Renate Dinnessen

PhD Candidate

Lars Leijten

Lars Leijten

PhD Candidate

Bogdan Obreja

Bogdan Obreja

PhD Candidate

Michel Vitale

Michel Vitale

PhD Candidate

Lisa Klok

Lisa Klok

PhD Candidate

Giulia Raffaella De Luca

Giulia Raffaella De Luca

Visiting Researcher

Zeinab Rahmanifard

Zeinab Rahmanifard

Master Student

Julia Haentjes

Julia Haentjes

Master Student

Doris Schouwenaars

Doris Schouwenaars

Student assistant

Lotte Besselaar

Lotte Besselaar

Student assistant

Scott Korman

Scott Korman

Student assistant