Julia Noothout obtained her Bachelor of Science degree in Medicine in 2013 from Utrecht University. In 2017 she received her Master of Science degree in Biomedical Image Sciences and with this combination of biomedical training and image processing related research she is able to combine her interest in functionality of the human body and medical imaging.
Her master thesis focused on segmentation of the aortic arch in low-dose chest CT by applying weakly supervised training for convolutional neural networks. In June 2017, Julia started her PhD at the Image Sciences Institute at UMC Utrecht and joined the Quantitative Medical Image Analysis Group. Her main research topic is Deep Transfer Learning techniques with an application to cardiac spectral CT.
Papers in conference proceedings
|1.||Automatic segmentation of organs at risk in thoracic CT scans by combining 2D and 3D convolutional neural networks. In: IEEE International Symposium on Biomedical Imaging, SegTHOR workshop (in press), 2019.|
|2.||Automatic segmentation of thoracic aorta segments in low-dose chest CT. In: SPIE Medical Imaging, 2018, vol. 10574, pp. 105741S.|
|3.||CNN-based Landmark Detection in Cardiac CTA Scans. In: Medical Imaging with Deep Learning (MIDL 2018), 2018.|