@inproceedings {2169, title = {Recurrent Inference Machines as Inverse Problem Solvers for MR Relaxometry}, booktitle = { MIDL 2021 - Medical Imaging with Deep Learning}, year = {2021}, author = {Emanoel Ribeiro Sabidussi and Matthan Caan and Shabab Bazrafkan and Arnold Jan den Dekker and Jan Sijbers and Wiro J Niessen and Dirk H J Poot} } @article {2190, title = {Recurrent Inference Machines as inverse problem solvers for MR relaxometry}, journal = {Medical Image Analysis}, volume = {74}, year = {2021}, pages = {1-11}, doi = {https://doi.org/10.1016/j.media.2021.102220}, author = {Emanoel Ribeiro Sabidussi and Stefan Klein and Matthan Caan and Shabab Bazrafkan and Arnold Jan den Dekker and Jan Sijbers and Wiro J Niessen and Dirk H J Poot} } @article {2087, title = {To Recurse or not to Recurse A Low Dose CT Study}, journal = {Progress in Artificial Intelligence}, volume = {10}, year = {2021}, pages = {65{\textendash}81}, doi = {https://doi.org/10.1007/s13748-020-00224-0}, author = {Shabab Bazrafkan and Vincent Van Nieuwenhove and Joris Soons and Jan De Beenhouwer and Jan Sijbers} } @inproceedings {2027, title = {BeadNet: a network for automated spherical marker detection in radiographs for geometry calibration}, booktitle = {6th International Conference on Image Formation in X-Ray Computed Tomography}, year = {2020}, pages = {518-521}, author = {Van Nguyen and Jan De Beenhouwer and Shabab Bazrafkan and A-T. Hoang and Sam Van Wassenbergh and Jan Sijbers} } @inproceedings {2034, title = {CNN-based Deblurring of Terahertz Images}, booktitle = {Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP)}, volume = {4}, year = {2020}, pages = {323-330}, doi = {10.5220/0008973103230330}, author = {Marina Ljubenovi{\'c} and Shabab Bazrafkan and Jan De Beenhouwer and Jan Sijbers} } @inproceedings {1977, title = {Deep learning-based 2D-3D sample pose estimation for X-ray 3DCT}, booktitle = {10th Conference on Industrial Computed Tomography (ICT 2020)}, year = {2020}, author = {Alice Presenti and Shabab Bazrafkan and Jan Sijbers and Jan De Beenhouwer} } @article {2058, title = {Deep neural network and data augmentation methodology for off-axis iris segmentation in wearable headsets}, journal = {Science Direct Elsevier Neural Networks}, volume = {121}, year = {2020}, month = {01/2020}, pages = {101-121}, chapter = {101-121}, doi = {https://doi.org/10.1016/j.neunet.2019.07.020}, url = {https://www.sciencedirect.com/science/article/pii/S0893608019302163?via\%3Dihub$\#$!}, author = {Viktor Varkarakis and Shabab Bazrafkan and Peter Corcoran} } @article {2055, title = {A low-cost geometry calibration procedure for a modular cone-beam X-ray CT system}, journal = {Nondestructive Testing and Evaluation }, volume = {35}, year = {2020}, pages = { 252-265}, doi = {https://doi.org/10.1080/10589759.2020.1774580}, author = {Van Nguyen and Jan De Beenhouwer and Joaquim Sanctorum and Sam Van Wassenbergh and Shabab Bazrafkan and Joris J. J. Dirckx and Jan Sijbers} } @inproceedings {2029, title = {Ring Artifact Reduction in Sinogram Space Using Deep Learning}, booktitle = {6th International Conference on Image Formation in X-Ray Computed Tomography}, year = {2020}, author = {Maxime Nauwynck and Shabab Bazrafkan and Anneke Van Heteren and Jan De Beenhouwer and Jan Sijbers} } @inproceedings {2068, title = {Ringing Artefact Removal From Sparse View Tomosynthesis using Deep Neural Networks}, booktitle = {The 6th International Conference on Image Formation in X-Ray Computed Tomography}, year = {2020}, pages = {380-383}, author = {Shabab Bazrafkan and Vincent Van Nieuwenhove and Joris Soons and Jan De Beenhouwer and Jan Sijbers} } @inproceedings {1966, title = {A Deep Learning Approach to Horse Bone Segmentation from Digitally Reconstructed Radiographs}, booktitle = {International Conference on Image Processing Theory, Tools, and Applications}, year = {2019}, doi = {10.1109/IPTA.2019.8936082}, author = {Jeroen Van Houtte and Shabab Bazrafkan and Filip Vandenberghe and Guoyan Zheng and Jan Sijbers} } @conference {1984, title = {A deep learning approach to T1 mapping in quantitative MRI}, volume = {32 (Suppl. 1)}, number = {S09.05}, year = {2019}, publisher = {Magn Reson Mater Phy}, abstract = {Quantitative MRI aims to measure biophysical tissue parameters through the analysis of the MR signal. Conventional parameter estimation methods, which often rely on a voxel-wise mapping, ignores spatial redundancies. In this work, a deep learning method for T1 mapping is proposed to overcome this limitation.}, doi = {10.1007/s10334-019-00754-2}, author = {Ribeiro Sabidussi, Emanoel and Michele Nicastro and Shabab Bazrafkan and Quinten Beirinckx and Ben Jeurissen and Jan Sijbers and Arnold Jan den Dekker and Stefan Klein and Dirk H J Poot} } @conference {1965, title = {Deep learning based missing wedge artefact removal for electron tomography}, year = {2019}, pages = {660-661}, author = {Juho Rimpelainen and Shabab Bazrafkan and Jan Sijbers and Jan De Beenhouwer} } @conference {1952, title = {Mixed-Scale Dense Convolutional Neural Network based Improvement of Glass Fiber-reinforced Composite CT Images}, year = {2019}, month = {07/2019}, abstract = {For the study of glass fiber-reinforced polymers (GFRP), {\textmu}CT is the method of choice. Obtaining GFRP parameters from a {\textmu}CT scan is difficult, due to the presence of noise and artifacts. We propose a method to improve GFRP image quality using a recently introduced deep neural network. We describe the network{\textquoteright}s setup and the data generation and show how the trained network improves the reconstruction.}, author = {Tim Elberfeld and Shabab Bazrafkan and Jan De Beenhouwer and Jan Sijbers} }