Artificial intelligence for lung cancer screening

Background

To be able to detect lung cancer in an early stage, screening of high-risk subjects using low-dose CT has been proposed. In 2011, the National Lung Screening Trial (NLST) was the first multicenter randomized controlled trial (RCT) to demonstrate that three rounds of annual screening of a high-risk population using low-dose chest computed tomography (CT) lead to 20% fewer lung cancer deaths after seven years of follow-up, compared to annual screening with chest radiography. Over 53,000 participants were included in this landmark study. The Dutch-Belgian NELSON trial – the second largest RCT with 15,789 participants – recently published their results and showed a 24% mortality reduction in a high-risk population of men compared to no screening. Based on the results of these trials, several countries have started the implementation of lung cancer screening, and other countries are conducting pilot trials.

AI holds great potential to assist in many of the detection and characterization tasks that have to be performed by a radiologist, and may be able to play an important role in reducing costs and improving the efficiency of screening.

Aim

In this project, we aim to develop algorithms that will improve the accuracy and cost-effectiveness of lung cancer screening. Much of our work is about extending and improving our current nodule CAD algorithms and automating lung cancer screening. Next to that, we also have a strong focus on performing clinical research in this area. To help us achieve our goals, we have developed a high-throughput workstation for lung cancer screening, which incorporates many of the algorithms we develop: CIRRUS Lung Screening. Together with MeVis Medical Solutions, we have commercialized this workstation under the name Veolity.

Funding

This project has received and continues to receive funding from several sources: Dutch Research Council (NWO), Radboudumc and MeVis Medical Solutions AG.

People

Colin Jacobs

Colin Jacobs

Assistant Professor

Anton Schreuder

Anton Schreuder

PhD Candidate

Sil van de Leemput

Sil van de Leemput

Research Software Engineer

RTC Deep Learning

Marco Marra

Marco Marra

Research Software Engineer

DIAG Research Software Engineering

Ernst Scholten

Ernst Scholten

Radiologist

Mathias Prokop

Mathias Prokop

Professor

Radboudumc

Publications

  • K. Venkadesh, A. Setio, A. Schreuder, E. Scholten, K. Chung, M. W Wille, Z. Saghir, B. van Ginneken, M. Prokop and C. Jacobs, "Deep Learning for Malignancy Risk Estimation of Pulmonary Nodules Detected at Low-Dose Screening CT", Radiology, 2021:204433.
  • A. Schreuder, O. Mets, C. Schaefer-Prokop, C. Jacobs and M. Prokop, "Microsimulation modeling of extended annual CT screening among lung cancer cases in the National Lung Screening Trial", Lung Cancer, 2021;156:5-11.
  • A. Schreuder, C. Jacobs, N. Lessmann, M. Broeders, M. Silva, I. Išgum, P. de Jong, N. Sverzellati, M. Prokop, U. Pastorino, C. Schaefer-Prokop and B. van Ginneken, "Combining pulmonary and cardiac computed tomography biomarkers for disease-specific risk modelling in lung cancer screening", European Respiratory Journal, 2021.
  • K. Venkadesh, A. Setio, Z. Saghir, B. van Ginneken and C. Jacobs, "Deep Learning for Lung Nodule Malignancy Prediction: Comparison With Clinicians and the Brock Model on an Independent Dataset From a Large Lung Screening Trial", Annual Meeting of the Radiological Society of North America, 2020.
  • A. Schreuder, E. Scholten, B. van Ginneken and C. Jacobs, "Artificial intelligence for detection and characterization of pulmonary nodules in lung cancer CT screening: ready for practice?", Translational Lung Cancer Research, 2021;10(5):2378-2388.
  • M. Silva, G. Milanese, S. Sestini, F. Sabia, C. Jacobs, B. van Ginneken, M. Prokop, C. Schaefer-Prokop, A. Marchiano, N. Sverzellati and U. Pastorino, "Lung cancer screening by nodule volume in Lung-RADS v1.1: negative baseline CT yields potential for increased screening interval", European Radiology, 2020;31(4):1956-1968.
  • H. Kauczor, A. Baird, T. Blum, L. Bonomo, C. Bostantzoglou, O. Burghuber, B. Čepicka, A. Comanescu, S. Courad, A. Devaraj, V. Jespersen, S. Morozov, I. Agmon, N. Peled, P. Powell, H. Prosch, S. Ravara, J. Rawlinson, M. Revel, M. Silca, A. Snoeckx, B. van Ginneken, J. van Meerbeeck, C. Vardavas, O. von Stackelberg, M. Gaga, O. behalf of the of (ESR) and T. (ERS), "ESR/ERS statement paper on lung cancer screening", European Radiology, 2020;30:3277-3294.
  • C. Jacobs and B. van Ginneken, "Google's lung cancer AI: a promising tool that needs further validation", Nature Reviews Clinical Oncology, 2019;16(9):532-533.
  • S. van Riel, C. Jacobs, E. Scholten, R. Wittenberg, M. Winkler Wille, B. de Hoop, R. Sprengers, O. Mets, B. Geurts, M. Prokop, C. Schaefer-Prokop and B. van Ginneken, "Observer variability for Lung-RADS categorisation of lung cancer screening CTs: impact on patient management", European Radiology, 2019;29(2):924-931.
  • A. Schreuder, C. Jacobs, L. Gallardo-Estrella, M. Prokop, C. Schaefer-Prokop and B. van Ginneken, "Predicting all-cause and lung cancer mortality using emphysema score progression rate between baseline and follow-up chest CT images: A comparison of risk model performances", PLoS One, 2019;14(2):e0212756.
  • G. Aresta, C. Jacobs, T. Araujo, A. Cunha, I. Ramos, B. van Ginneken and A. Campilho, "iW-Net: an automatic and minimalistic interactive lung nodule segmentation deep network", Nature Scientific Reports, 2019;9(1):11591.
  • M. Tammemagi, A. Ritchie, S. Atkar-Khattra, B. Dougherty, C. Sanghera, J. Mayo, R. Yuan, D. Manos, A. McWilliams, H. Schmidt, M. Gingras, S. Pasian, L. Stewart, S. Tsai, J. M.Seely, P. Burrowes, R. Bhatia, E. A.Haider, C. Boylan, C. Jacobs, B. van Ginneken, M. Tsao, S. Lam and the Pan-Canadian Early Detection of Lung Cancer Study Group, "Predicting Malignancy Risk of Screen Detected Lung Nodules - Mean Diameter or Volume", Journal of Thoracic Oncology, 2019;14(2):203-211.
  • J. Charbonnier, K. Chung, E. Scholten, E. van Rikxoort, C. Jacobs, N. Sverzellati, M. Silva, U. Pastorino, B. van Ginneken and F. Ciompi, "Automatic segmentation of the solid core and enclosed vessels in subsolid pulmonary nodules", Nature Scientific Reports, 2018;8(1):646.
  • K. Chung, F. Ciompi, J. Scholten E. Th. Goo, M. Prokop, C. Jacobs, B. van Ginneken and C. Schaefer-Prokop, "Visual Discrimination of Screen-detected Persistent from Transient Subsolid Nodules: an Observer Study", PLoS One, 2018;13(2):e0191874.
  • A. Schreuder, C. Schaefer-Prokop, E. Scholten, C. Jacobs, M. Prokop and B. van Ginneken, "Lung cancer risk to personalise annual and biennial follow-up computed tomography screening", Thorax, 2018;73(7):626-633.
  • A. Schreuder, B. van Ginneken, E. Scholten, C. Jacobs, M. Prokop, N. Sverzellati, S. Desai, A. Devaraj and C. Schaefer-Prokop, "Classification of CT Pulmonary Opacities as Perifissural Nodules: Reader Variability", Radiology, 2018;288(3):867-875.
  • M. Silva, M. Prokop, C. Jacobs, G. Capretti, N. Sverzellati, F. Ciompi, B. van Ginneken, C. Schaefer-Prokop, C. Galeone, A. Marchiano and U. Pastorino, "Long-term Active Surveillance of Screening Detected Subsolid Nodules is a Safe Strategy to Reduce Overtreatment", Journal of Thoracic Oncology, 2018;13:1454-1463.
  • M. Silva, C. Schaefer-Prokop, C. Jacobs, G. Capretti, F. Ciompi, B. van Ginneken, U. Pastorino and N. Sverzellati, "Detection of Subsolid Nodules in Lung Cancer Screening: Complementary Sensitivity of Visual Reading and Computer-Aided Diagnosis", Investigative Radiology, 2018;53(8):441-449.
  • K. Chung, C. Jacobs, E. Scholten, J. Goo, H. Prosch, N. Sverzellati, F. Ciompi, O. Mets, P. Gerke, M. Prokop, B. van Ginneken and C. Schaefer-Prokop, "Lung-RADS Category 4X: Does It Improve Prediction of Malignancy in Subsolid Nodules?", Radiology, 2017;284(1):264-271.
  • K. Chung, C. Jacobs, E. Scholten, O. Mets, I. Dekker, M. Prokop, B. van Ginneken and C. Schaefer-Prokop, "Malignancy estimation of Lung-RADS criteria for subsolid nodules on CT: accuracy of low and high risk spectrum when using NLST nodules", European Radiology, 2017;27:4672-4679.
  • F. Ciompi, K. Chung, S. van Riel, A. Setio, P. Gerke, C. Jacobs, E. Scholten, C. Schaefer-Prokop, M. Wille, A. Marchiano, U. Pastorino, M. Prokop and B. van Ginneken, "Towards automatic pulmonary nodule management in lung cancer screening with deep learning", Nature Scientific Reports, 2017(46479).
  • S. van Riel, F. Ciompi, C. Jacobs, M. Winkler Wille, E. Scholten, M. Naqibullah, S. Lam, M. Prokop, C. Schaefer-Prokop and B. van Ginneken, "Malignancy risk estimation of screen-detected nodules at baseline CT: comparison of the PanCan model, Lung-RADS and NCCN guidelines", European Radiology, 2017;27(10):4019-4029.
  • A. Setio, A. Traverso, T. de Bel, M. Berens, C. Bogaard, P. Cerello, H. Chen, Q. Dou, M. Fantacci, B. Geurts, R. Gugten, P. Heng, B. Jansen, M. de Kaste, V. Kotov, J. Lin, J. Manders, A. Sonora-Mengana, J. Garcia-Naranjo, E. Papavasileiou, M. Prokop, M. Saletta, C. Schaefer-Prokop, E. Scholten, L. Scholten, M. Snoeren, E. Torres, J. Vandemeulebroucke, N. Walasek, G. Zuidhof, B. Ginneken and C. Jacobs, "Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge", Medical Image Analysis, 2017;42:1-13.
  • C. Jacobs, E. van Rikxoort, K. Murphy, M. Prokop, C. Schaefer-Prokop and B. van Ginneken, "Computer-aided detection of pulmonary nodules: a comparative study using the public LIDC/IDRI database", European Radiology, 2016;26:2139-2147.
  • A. Ritchie, C. Sanghera, C. Jacobs, W. Zhang, J. Mayo, H. Schmidt, M. Gingras, S. Pasian, L. Stewart, S. Tsai, D. Manos, J. Seely, P. Burrowes, R. Bhatia, S. Atkar-Khattra, B. van Ginneken, M. Tammemagi, M. Tsao, S. Lam and the Pan-Canadian Early Detection of Lung Cancer Study Group, "Computer Vision Tool and Technician as First Reader of Lung Cancer Screening CT Scans", Journal of Thoracic Oncology, 2016;11(5):709-717.
  • C. Jacobs, E. van Rikxoort, E. Scholten, P. de Jong, M. Prokop, C. Schaefer-Prokop and B. van Ginneken, "Solid, Part-Solid, or Non-solid?: Classification of Pulmonary Nodules in Low-Dose Chest Computed Tomography by a Computer-Aided Diagnosis System", Investigative Radiology, 2015;50(3):168-173.
  • B. Lassen, C. Jacobs, J. Kuhnigk, B. van Ginneken and E. van Rikxoort, "Robust semi-automatic segmentation of pulmonary subsolid nodules in chest computed tomography scans", Physics in Medicine and Biology, 2015;60(3):1307-1323.
  • S. van Riel, C. Sánchez, A. Bankier, D. Naidich, J. Verschakelen, E. Scholten, P. de Jong, C. Jacobs, E. van Rikxoort, L. Peters-Bax, M. Snoeren, M. Prokop, B. van Ginneken and C. Schaefer-Prokop, "Observer Variability for Classification of Pulmonary Nodules on Low-Dose CT Images and Its Effect on Nodule Management", Radiology, 2015;277(3):863-871.
  • C. Jacobs, E. van Rikxoort, T. Twellmann, E. Scholten, P. de Jong, J. Kuhnigk, M. Oudkerk, H. de Koning, M. Prokop, C. Schaefer-Prokop and B. van Ginneken, "Automatic Detection of Subsolid Pulmonary Nodules in Thoracic Computed Tomography Images", Medical Image Analysis, 2014;18:374-384.