@article {997, title = {Optimisation of quantitative brain diffusion-relaxation MRI acquisition protocols with physics-informed machine learning}, journal = {Medical Image Analysis}, volume = {94}, year = {2024}, pages = {103134}, abstract = {

Diffusion-relaxation MRI aims to extract quantitative measures that characterise microstructural tissue properties such as orientation, size, and shape, but long acquisition times are typically required. This work proposes a physics-informed learning framework to extract an optimal subset of diffusion-relaxation MRI measurements for enabling shorter acquisition times, predict non-measured signals, and estimate quantitative parameters. In vivo and synthetic brain 5D-Diffusion-T1-T2*-weighted MRI data obtained from five healthy subjects were used for training and validation, and from a sixth participant for testing. One fully data-driven and two physics-informed machine learning methods were implemented and compared to two manual selection procedures and Cram{\'e}r–Rao lower bound optimisation. The physics-informed approaches could identify measurement-subsets that yielded more consistently accurate parameter estimates in simulations than other approaches, with similar signal prediction error. Five-fold shorter protocols yielded error distributions of estimated quantitative parameters with very small effect sizes compared to estimates from the full protocol. Selected subsets commonly included a denser sampling of the shortest and longest inversion time, lowest echo time, and high b-value. The proposed framework combining machine learning and MRI physics offers a promising approach to develop shorter imaging protocols without compromising the quality of parameter estimates and signal predictions.

}, keywords = {Brain, Diffusion-relaxation, Quantitative MRI, machine learning}, issn = {1361-8415}, doi = {https://doi.org/10.1016/j.media.2024.103134}, url = {https://www.sciencedirect.com/science/article/pii/S1361841524000598}, author = {{\'A}lvaro Planchuelo-G{\'o}mez and Maxime Descoteaux and Hugo Larochelle and Jana Hutter and Derek K. Jones and Chantal M.W. Tax} } @proceedings {988, title = {Comparison of data-driven and physics-informed learning approaches for optimising multi-contrast MRI acquisition protocols}, volume = {3701}, year = {2023}, month = {2023}, abstract = {

Multi-contrast MRI is used to assess the biological properties of tissues, but excessively long times are required to acquire high-quality datasets. To reduce acquisition time, physics-informed Machine Learning approaches were developed to select the optimal subset of measurements, decreasing the number of volumes by approximately 63\%, and predict the MRI signal and quantitative maps. These selection methods were compared to a full data-driven and two manual strategies. Synthetic and real 5D-Diffusion-T1-T2* data from five healthy participants were used. Feature selection via a combination of Machine Learning and physics modelling provides accurate estimation of quantitative parameters and prediction of MRI signal.

}, author = {{\'A}lvaro Planchuelo-G{\'o}mez and Descoteaux, Maxime and Aja-Fern{\'a}ndez, Santiago and Hutter, Jana and Jones, Derek K and Tax, Chantal M W} } @proceedings {987, title = {Super-resolution diffusion tensor imaging at 64 mT}, volume = {3624}, year = {2023}, month = {2023}, abstract = {

A super-resolution approach was used to create 2mm isotropic diffusion tensor images (DTI) from diffusion-weighted imaging data acquired on a low field, portable system. Mean diffusivity, fractional anisotropy and principal eigenvector orientation maps are shown. This work extends the very recently implemented capability of performing DTI on a 64mT system, and shows substantial improvement due to the increased through-plane resolution achieved with super-resolution.

}, author = {Plumley, Alix and Cercignani, Mara and {\'A}lvaro Planchuelo-G{\'o}mez and Gholam, James and Jones, Derek K} } @proceedings {984, title = {Tensors and Tracts at 64 mT}, volume = {104}, year = {2023}, month = {2023}, abstract = {

We present the first ever demonstration of Diffusion Tensor Magnetic Resonance Imaging (DT-MRI) including quantitative measures of mean diffusivity, fractional anisotropy, and successful tractographic reconstruction of projection and commissural pathways on a portable system operating at 64 mT.

}, author = {Plumley, Alix and Padormo, Francesco and Cercignani, Mara and O{\textquoteright}Halloran, Rafael and Teixeira, Rui and {\'A}lvaro Planchuelo-G{\'o}mez and Legouhy, Antoine and Luo, Tianrui and Jones, Derek K} } @article {956, title = {Anisotropy measure from three diffusion-encoding gradient directions}, journal = {Magnetic Resonance Imaging}, volume = {88}, year = {2022}, month = {2022}, pages = {38{\textendash}43}, author = {Santiago Aja-Fern{\'a}ndez and Guillem Par{\'\i}s and Carmen Mart{\'\i}n-Mart{\'\i}n and Derek K. Jones and AntonioTrist{\'a}n-Vega} } @conference {974, title = {Data-driven and physics-informed learning of efficient acquisition protocols}, booktitle = {ISMRM Workshop on Diffusion MRI: From Research to Clinic}, year = {2022}, address = {Amsterdam, The Netherlands}, author = {{\'A}lvaro Planchuelo-G{\'o}mez and Descoteaux, Maxime and Aja-Fern{\'a}ndez, Santiago and Hutter, Jana and Jones, Derek K. and Tax, Chantal M.W.} } @conference {976, title = {Tensors and Tracts at 64 mT}, booktitle = {ISMRM Workshop on Diffusion MRI: From Research to Clinic}, year = {2022}, address = {Amsterdam, The Netherlands}, author = {Plumley, Alix and Padormo, Francesco and Cercignani, Mara and O{\textquoteright}Halloran, Rafael and Teixeira, Rui and {\'A}lvaro Planchuelo-G{\'o}mez and Legouhy, Antoine and Luo, Tianrui and Jones, Derek K.} } @article {899, title = {Apparent propagator anisotropy from single-shell diffusion MRI acquisitions}, journal = {Magnetic Resonance in Medicine}, volume = {85}, year = {2021}, month = {2021}, pages = {2869-2881}, chapter = {2869}, doi = {https://doi.org/10.1002/mrm.28620}, url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/mrm.28620}, author = {Santiago Aja-Fern{\'a}ndez and Antonio Trist{\'a}n-Vega and Derek K. Jones} } @article {951, title = {Time-efficient three-dimensional transmural scar assessment provides relevant substrate characterization for ventricular tachycardia features and long-term recurrences in ischemic cardiomyopathy}, journal = {Scientific Reports}, volume = {11}, year = {2021}, month = {2021}, url = {https://www.nature.com/articles/s41598-021-97399-w}, author = {S. Merino-Caviedes and Guti{\'e}rrez, L. and Alfonso-Almaz{\'a}n, J. and Santiago Sanz-Est{\'e}banez and Lucilio Cordero-Grande and Quintanilla, J. and S{\'a}nchez-Gonz{\'a}lez, J. and Marina-Breysse, M. and Gal{\'a}n-Arriola, C. and Enr{\'\i}quez-V{\'a}zquez, D. and Torres, C. and Pizarro, G. and Ib{\'a}{\~n}ez, B. and Peinado, R. and Merino, J. and P{\'e}rez-Villacast{\'\i}n, J. and Jalife. J and L{\'o}pez-Yunta, M. and V{\'a}zquez, M. and Aguado-Sierra, J. and Gonz{\'a}lez-Ferrer, J. and P{\'e}rez-Castellano, N. and Mart{\'\i}n-Fern{\'a}ndez, M. and Alberola-L{\'o}pez, C and Filgueiras-Rama, D.} } @article {933, title = {On the generalizability of diffusion MRI signal representations across acquisition parameters, sequences and tissue types: chronicles of the MEMENTO challenge}, journal = {NeuroImage}, year = {2021}, month = {2021}, pages = {118367}, issn = {1053-8119}, doi = {https://doi.org/10.1016/j.neuroimage.2021.118367}, url = {https://www.sciencedirect.com/science/article/pii/S1053811921006431}, author = {Alberto De Luca and Andrada Ianus and Alexander Leemans and Marco Palombo and Noam Shemesh and Hui Zhang and Daniel C. Alexander and Markus Nilsson and Martijn Froeling and Geert-Jan Biessels and Mauro Zucchelli and Matteo Frigo and Enes Albay and Sara Sedlar and Abib Alimi and Samuel Deslauriers-Gauthier and Rachid Deriche and Rutger Fick and Maryam Afzali and Tomasz Pieciak and Fabian Bogusz and Santiago Aja-Fern{\'a}ndez and Evren {\"O}zarslan and Derek K. Jones and Haoze Chen and Mingwu Jin and Zhijie Zhang and Fengxiang Wang and Vishwesh Nath and Prasanna Parvathaneni and Jan Morez and Jan Sijbers and Ben Jeurissen and Shreyas Fadnavis and Stefan Endres and Ariel Rokem and Eleftherios Garyfallidis and Irina Sanchez and Vesna Prchkovska and Paulo Rodrigues and Bennet A. Landman and Kurt G. Schilling} } @article {912, title = {On the generalizability of diffusion MRI signal representations across acquisition parameters, sequences and tissue types: chronicles of the MEMENTO challenge}, journal = {bioRxiv}, year = {2021}, month = {2021}, doi = {10.1101/2021.03.02.433228}, url = {https://www.biorxiv.org/content/early/2021/03/02/2021.03.02.433228}, author = {De Luca, Alberto and Ianus, Andrada and Leemans, Alexander and Palombo, Marco and Shemesh, Noam and Zhang, Hui and Alexander, Daniel C and Nilsson, Markus and Froeling, Martijn and Biessels, Geert-Jan and Zucchelli, Mauro and Frigo, Matteo and Albay, Enes and Sedlar, Sara and Alimi, Abib and Deslauriers-Gauthier, Samuel and Deriche, Rachid and Fick, Rutger and Maryam Afzali and Tomasz Pieciak and Bogusz, Fabian and Santiago Aja-Fern{\'a}ndez and Ozarslan, Evren and Derek K. Jones and Chen, Haoze and Jin, Mingwu and Zhang, Zhijie and Wang, Fengxiang and Nath, Vishwesh and Parvathaneni, Prasanna and Morez, Jan and Sijbers, Jan and Jeurissen, Ben and Fadnavis, Shreyas and Endres, Stefan and Rokem, Ariel and Garyfallidis, Eleftherios and Sanchez, Irina and Prchkovska, Vesna and Rodrigues, Paulo and Landman, Bennet A and Schilling, Kurt G} } @inbook {895, title = {Alternative Diffusion Anisotropy Metric from Reduced MRI Acquisitions}, booktitle = {Computational Diffusion MRI}, year = {2020}, pages = {13{\textendash}24}, publisher = {Springer, Cham}, organization = {Springer, Cham}, author = {Santiago Aja-Fern{\'a}ndez and Antonio Trist{\'a}n-Vega and Rodrigo de Luis-Garc{\'\i}a and Derek K. Jones} } @article {839, title = {Direction-averaged diffusion-weighted MRI signal using different axisymmetric B-tensor encoding schemes}, journal = {Magnetic Resonance in Medicine}, volume = {n/a}, year = {2020}, month = {2020}, keywords = {B-tensor encoding, diffusion-weighted~MRI, direction-averaged diffusion signal, high b-value, power-law}, doi = {10.1002/mrm.28191}, url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/mrm.28191}, author = {Maryam Afzali and Santiago Aja-Fern{\'a}ndez and Derek K. Jones} } @article {914, title = {Q-space quantitative diffusion MRI measures using a stretched-exponential representation}, journal = {arXiv}, year = {2020}, url = {https://arxiv.org/abs/2009.07376}, author = {Tomasz Pieciak and Maryam Afzali and Fabian Bogusz and Santiago Aja-Fern{\'a}ndez and Derek K. Jones} } @article {863, title = {A three-variety automatic and non-intrusive computer vision system for the estimation of orange fruit pH value}, journal = {Measurement}, volume = {152}, year = {2020}, pages = {107298}, abstract = {An automatic 3-variety computer vision orange fruit pH value assessment system in the visible-range is presented, including each 100 different color images from Bam, Blood and Thomson orange of which the true pH has been measured and is known in advance. A total of 452 features are extracted from segmented orange color images. Results with repeated trials include: true versus estimated mean pH values, true minus estimated pH values boxplots, fitness regression dispersion plots and various error measure boxplots, for both single orange variety as well as the three-orange varieties altogether (test set), showing consistent results over all three orange varieties. Regression coefficient for pH estimation in Bam, Blood and Thomson orange varieties, were 0.950, 0.935 and 0.957, respectively. Results show that the hybrid ANN-ABC estimates pH values in orange quite similarly among orange varieties, implying that properly pH values estimation is possible for different orange varieties, regardless of orange type.}, doi = {https://doi.org/10.1016/j.measurement.2019.107298}, url = {https://www.sciencedirect.com/science/article/pii/S0263224119311625}, author = {Sabzi, Sajad and Javadikia, Hossein and J I Arribas} } @conference {jimenez2019novel, title = {A Novel Design Method for Digital FIR/IIR Filters Based on the Shuffle Frog-Leaping Algorithm}, booktitle = {2019 27th European Signal Processing Conference (EUSIPCO)}, year = {2019}, pages = {1{\textendash}5}, publisher = {IEEE}, organization = {IEEE}, author = {Jim{\'e}nez-Galindo, Daniel and Pablo Casaseca-de-la-Higuera and San-Jos{\'e}-Revuelta, Luis M} } @article {858, title = {An automatic and non-intrusive hybrid computer vision system for the estimation of peel thickness in Thomson orange}, journal = {Spanish Journal of Agricultural Research}, volume = {16}, year = {2018}, pages = {e0204}, abstract = {Orange peel has important flavor and nutrition properties and is often used for making jam and oil in the food industry. For previous reasons, oranges with high peel thickness are valuable. In order to properly estimate peel thickness in Thomson orange fruit, based on a number of relevant image features (area, eccentricity, perimeter, length/area, blue component, green component, red component, width, contrast, texture, width/area, width/length, roughness, and length) a novel automatic and non-intrusive approach based on computer vision with a hybrid particle swarm optimization (PSO), genetic algorithm (GA) and artificial neural network (ANN) system is proposed. Three features (width/area, width/length and length/area ratios) were selected as inputs to the system. A total of 100 oranges were used, performing cross validation with 100 repeated experiments with uniform random samples test sets. Taguchi{\textquoteright}s robust optimization technique was applied to determine the optimal set of parameters. Prediction results for orange peel thickness (mm) based on the levels that were achieved by Taguchi{\textquoteright}s method were evaluated in several ways, including orange peel thickness true-estimated boxplots for the 100 orange database and various error parameters: the sum square error (SSE), the mean absolute error (MAE), the coefficient of determination (R2), the root mean square error (RMSE), and the mean square error (MSE), resulting in mean error parameter values of R2=0.854{\textpm}0.052, MSE=0.038{\textpm}0.010, and MAE=0.159{\textpm}0.023, over the test set, which to our best knowledge are remarkable numbers for an automatic and non-intrusive approach with potential application to real-time orange peel thickness estimation in the food industry. }, doi = {http://dx.doi.org/10.5424/sjar/2018164-11185}, url = {https://revistas.inia.es/index.php/sjar/article/view/11185}, author = {H Javadikia and S Sabzi and J I Arribas} }