CT based screening of heavy smokers is designed for early detection of lung cancer, but also offers the possibility to detect multiple other diseases at an early stage. This is especially interesting when the screening images would allow automatic detection of these diseases.
This project is focusing on the automatic detection of cardiovascular disease and osteoporosis in lung cancer screening trials. The detection needs to be robust against various acquisition protocols, to allow application of these automatic algorithms to scans acquired in different lung cancer screening trials.
This is a collaborative project between the Image Sciences Institute (ISI), UMC Utrecht and the Diagnostic Image Analysis Group (DIAG), Radboud University Medical Center.
A section from a CT scan acquired in Dutch-Belgian lung cancer screening trial (NELSON). The image offers the possibility to quantify calcifications in the coronary arteries and in the aorta as signs of cardiovascular disease, as well as analysis of vertebra to detect early signs of osteoporosis.
Vertebra segmentation in low-dose chest CT using an iterative fully convolutional neural network. The segmentations are used to detect vertebral compression fractures.
Papers in international journals
|1.||Iterative fully convolutional neural networks for automatic vertebra segmentation and identification. Medical Image Analysis, 2019, vol. 53, pp. 142-155.|
|2.||Sex differences in coronary artery and thoracic aorta calcification and their association with cardiovascular mortality in heavy smokers. JACC: Cardiovascular Imaging (in press), 2019.|
|3.||Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions. IEEE Transactions on Medical Imaging, 2018, vol. 37, nr. 2, pp. 615-625.|
Papers in conference proceedings
|1.||Iterative fully convolutional neural networks for automatic vertebra segmentation. In: Medical Imaging with Deep Learning (MIDL 2018), 2018.|
|2.||Iterative convolutional neural networks for automatic vertebra identification and segmentation in CT images. In: SPIE Medical Imaging, 2018, pp. 1057408.|
|3.||Deep convolutional neural networks for automatic coronary calcium scoring in a screening study with low-dose chest CT. In: SPIE Medical Imaging, 2016, vol. 9785, pp. 978511.|
|1.||Improved lung cancer and mortality prediction accuracy using survival models based on semi-automatic CT image measurements. World Conference on Lung Cancer, 2018.|
|2.||Deep learning analysis for automatic calcium scoring in routine chest CT. Radiological Society of North America, 103rd Annual Meeting, 2017.|
|3.||Automatic coronary calcium scoring and cardiovascular risk estimation in the Pan-Canadian lung cancer screening trial. Radiological Society of North America, 101th Annual Meeting, 2015.|