Preterm birth is often associated with impaired neurodevelopment. Quantitative evaluation of MR images may indicate the state and expected progression of brain development in preterm born infants and aid in the decision of future interventions. Segmentation of different tissue types in the brain is a prerequisite for obtaining such MRI measurements.
In this project, we design methods for automatic and quantitative analysis of neonatal MR brain images in a longitudinally imaged cohort of preterm infants, focusing on brain tissue volumes and cortical morphology.
Automatic segmentation of images acquired at 30 (left) and 40 weeks postmenstrual age (right), in unmyelinated white matter (red), cortical grey matter (yellow), and cerebrospinal fluid in the extracerebral space (blue).
Papers in international journals
|1.||Evaluation of a deep learning approach for the segmentation of brain tissues and white matter hyperintensities of presumed vascular origin in MRI. NeuroImage Clinical, 2017, vol. 17, pp. 251-262.|
|2.||Prediction of cognitive and motor outcome of preterm infants based on automatic quantitative descriptors from neonatal MR brain images. Scientific Reports, 2017, vol. 7, nr. 2163.|
|3.||Relation between clinical risk factors, early cortical changes, and neurodevelopmental outcome in preterm infants. NeuroImage, 2016, vol. 5, nr. 142, pp. 301-310.|
|4.||Delayed cortical gray matter development in neonates with severe congenital heart disease. Pediatric Research, 2016, vol. 80, nr. 5, pp. 668-674.|
|5.||Automatic segmentation of MR brain images with a convolutional neural network. IEEE Transactions on Medical Imaging, 2016, vol. 35, nr. 5, pp. 1252-1261.|
|6.||Development of cortical morphology evaluated with longitudinal MR brain images of preterm infants. PLOS ONE, 2015, vol. 10, nr. 7, pp. e0131552.|
|7.||Automatic segmentation of MR brain images of preterm infants using supervised classification. NeuroImage, 2015, vol. 118, pp. 628-641.|
|8.||Evaluation of automatic neonatal brain segmentation algorithms: the NeoBrainS12 challenge. Medical Image Analysis, 2015, vol. 20, nr. 1, pp. 135-151.|
Papers in conference proceedings
|1.||Deep learning for multi-task medical image segmentation in multiple modalities. In: Medical Image Computing and Computer-Assisted Intervention, 2016, vol. 9901, pp. 478-486.|
|2.||Evaluation of an automatic brain segmentation method developed for neonates on adult MR brain images. In: SPIE Medical Imaging, 2015, vol. 9413, pp. 941315.|
|3.||Assessment of quantitative cortical biomarkers in the developing brain of preterm infants. In: SPIE Medical Imaging, 2013, vol. 8670, pp. 867011.|
|4.||Automatic segmentation of the preterm neonatal brain with MRI using supervised classification. In: SPIE Medical Imaging, 2013, vol. 8669, pp. 86693X-1-86693X-6.|
|1.||Automatic whole brain segmentation of MR brain images of preterm infants and adults using supervised classification. IEEE ISBI NeatBrainS15 workshop, 2015.|
|2.||Cortical morphology in infants with congenital heart disease pre- and post-surgery. Pediatric Academic Societies Annual Meeting, 2014.|
|3.||Quantitative evaluation of cortical development in serial MR images of preterm infants. Pediatric Academic Societies Annual Meeting, 2013.|