Summary

As part of Medical Imaging 2015 in February, SPIE, the American Association of Physicists in Medicine (AAPM), and the National Cancer Institute (NCI) will conduct a “Grand Challenge” on developing quantitative image analysis methods for the diagnostic classification of malignant and benign lung nodules. This LUNGx Challenge will provide an important first step in addressing the long-term effort to evaluate clinical decision tools.

Members of the medical imaging research community, many of whom will attend the Computer-Aided Diagnosis (CAD) conference at Medical Imaging 2015, will be asked to develop, refine, and disseminate advanced quantitative image-analysis systems for diagnosing malignant lung nodules on computed tomography (CT) scans to improve the quality of computer-aided diagnosis in the task of lung nodule classification.

Challenge organizers release training set cases: 21 November 2014
Release of test dataset without truth: 9 January 2015
Participants submit test set classification results: 6 February 2015

Challenge participants are invited to display poster presentations during the conference, and may demonstrate their algorithms during a live demonstration workshop on Tuesday. A special panel discussion on Tuesday afternoon will focus on the topic.

The participation of multiple research groups in the development of image analysis methods, some of which will be presented at SPIE Medical Imaging, is expected to yield advances in computer-aided diagnosis and, ultimately, to precision medicine.

The LUNGx Challenge is one of the many highlights in store at the symposium 21-26 February in Orlando, FL (USA). Other conference topics include digital pathology, ultrasonic imaging, image-guided procedures, robotic interventions, the physics of medical imaging, and image processing and archiving.

Presenters are encouraged to submit their work for the proceedings volume as well as for the new SPIE Journal of Medical Imaging.