@proceedings {985, title = {Validation of Deep Learning techniques for quality augmentation in diffusion MRI for clinical studies}, volume = {2786}, year = {2023}, month = {2023}, abstract = {

This work gathers the results of the QuadD22 challenge, held in MICCAI 2022. We evaluate whether Deep Learning (DL) Techniques are able to improve the quality of diffusion MRI data in clinical studies. To that end, we focused on a real study on migraine, where the differences between groups are drastically reduced when using 21 gradient directions instead of 61. Thus, we asked the participants to augment dMRI data acquired with only 21 directions to 61 via DL. The results were evaluated using a real clinical study with TBSS in which we statistically compared episodic migraine to chronic migraine.

}, author = {Aja-Fernandez, Santiago and Martin-Martin, Carmen and Pieciak, Tomasz and {\'A}lvaro Planchuelo-G{\'o}mez and Faiyaz, Abrar and Uddin, Nasir and Tiwari, Abhishek and Shigwan, Saurabh J and Zheng, Tianshu and Cao, Zuozhen and Blumberg, Stefano B and Sen, Snigdha and Yigit Avci, Mehmet and Li, Zihan and Wang, Xinyi and Tang, Zihao and Rauland, Amelie and Merhof, Dorit and Manzano Maria, Renata and Campos, Vinicius P and HashemiazadehKolowri, SeyyedKazem and DiBella, Edward and Peng, Chenxu and Chen, Zan and Ullah, Irfan and Mani, Merry and Eckstrom, Samuel and Baete, Steven H and Scifitto, Scifitto and Singh, Rajeev Kumar and Wu, Dan and Goodwin-Allcock, Tobias and Slator, Paddy J and Bilgic, Berkin and Tian, Qiyuan and Cabezas, Mariano and Santini, Tales and Andrade da Costa Vieira, Marcelo and Shen, Zhimin and Abdolmotalleby, Hesam and Filipiak, Patryk and Tristan-Vega, Antonio and de Luis-Garcia, Rodrigo} } @article {995, title = {Validation of deep learning techniques for quality augmentation in diffusion MRI for clinical studies}, journal = {NeuroImage: Clinical}, volume = {39}, year = {2023}, pages = {103483}, abstract = {

The objective of this study is to evaluate the efficacy of deep learning (DL) techniques in improving the quality of diffusion MRI (dMRI) data in clinical applications. The study aims to determine whether the use of artificial intelligence (AI) methods in medical images may result in the loss of critical clinical information and/or the appearance of false information. To assess this, the focus was on the angular resolution of dMRI and a clinical trial was conducted on migraine, specifically between episodic and chronic migraine patients. The number of gradient directions had an impact on white matter analysis results, with statistically significant differences between groups being drastically reduced when using 21 gradient directions instead of the original 61. Fourteen teams from different institutions were tasked to use DL to enhance three diffusion metrics (FA, AD and MD) calculated from data acquired with 21 gradient directions and a b-value of 1000 s/mm2. The goal was to produce results that were comparable to those calculated from 61 gradient directions. The results were evaluated using both standard image quality metrics and Tract-Based Spatial Statistics (TBSS) to compare episodic and chronic migraine patients. The study results suggest that while most DL techniques improved the ability to detect statistical differences between groups, they also led to an increase in false positive. The results showed that there was a constant growth rate of false positives linearly proportional to the new true positives, which highlights the risk of generalization of AI-based tasks when assessing diverse clinical cohorts and training using data from a single group. The methods also showed divergent performance when replicating the original distribution of the data and some exhibited significant bias. In conclusion, extreme caution should be exercised when using AI methods for harmonization or synthesis in clinical studies when processing heterogeneous data in clinical studies, as important information may be altered, even when global metrics such as structural similarity or peak signal-to-noise ratio appear to suggest otherwise.

}, keywords = {Angular resolution, Artificial Intelligence, Deep learning, Diffusion tensor, diffusion MRI, machine learning}, issn = {2213-1582}, doi = {https://doi.org/10.1016/j.nicl.2023.103483}, url = {https://www.sciencedirect.com/science/article/pii/S2213158223001742}, author = {Santiago Aja-Fern{\'a}ndez and Carmen Mart{\'\i}n-Mart{\'\i}n and {\'A}lvaro Planchuelo-G{\'o}mez and Abrar Faiyaz and Md Nasir Uddin and Giovanni Schifitto and Abhishek Tiwari and Saurabh J. Shigwan and Rajeev Kumar Singh and Tianshu Zheng and Zuozhen Cao and Dan Wu and Stefano B. Blumberg and Snigdha Sen and Tobias Goodwin-Allcock and Paddy J. Slator and Mehmet Yigit Avci and Zihan Li and Berkin Bilgic and Qiyuan Tian and Xinyi Wang and Zihao Tang and Mariano Cabezas and Amelie Rauland and Dorit Merhof and Renata Manzano Maria and Vin{\'\i}cius Paran{\'\i}ba Campos and Tales Santini and Marcelo Andrade da Costa Vieira and SeyyedKazem HashemizadehKolowri and Edward DiBella and Chenxu Peng and Zhimin Shen and Zan Chen and Irfan Ullah and Merry Mani and Hesam Abdolmotalleby and Samuel Eckstrom and Steven H. Baete and Patryk Filipiak and Tanxin Dong and Qiuyun Fan and Rodrigo de Luis-Garc{\'\i}a and Antonio Trist{\'a}n-Vega and Tomasz Pieciak} } @article {795, title = {Space-time variant weighted regularization in compressed sensing cardiac cine MRI}, journal = {Magnetic Resonance Imaging}, volume = {58}, year = {2019}, pages = {44 - 55}, abstract = {

Purpose: To analyze the impact on image quality and motion fidelity of a motion-weighted space-time variant regularization term in compressed sensing cardiac cine MRI.
Methods: k-t SPARSE-SENSE with temporal total variation (tTV) is used as the base reconstruction algorithm. Motion in the dynamic image is estimated by means of a robust registration technique for non-rigid motion. The resulting deformation fields are used to leverage the regularization term. The results are compared with standard k-t SPARSE-SENSE with tTV regularization as well as with an improved version of this algorithm that makes use of tTV and temporal Fast Fourier Transform regularization in x-f domain.
Results: The proposed method with space-time variant regularization provides higher motion fidelity and image quality than the two previously reported methods. Difference images between undersampled reconstruction and fully sampled reference images show less systematic errors with the proposed approach.
Conclusions: Usage of a space-time variant regularization offers reconstructions with better image quality than the state of the art approaches used for comparison.

}, keywords = {Cine cardiac MRI, Space-time variant regularization, compressed sensing, k-t SPARSE-SENSE}, issn = {0730-725X}, doi = {https://doi.org/10.1016/j.mri.2019.01.005}, url = {http://www.sciencedirect.com/science/article/pii/S0730725X18301978}, author = {Alejandro Godino-Moya and J Royuela-del-Val and Muhammad Usman and Rosa-Mar{\'\i}a Mench{\'o}n-Lara and Marcos Mart{\'\i}n-Fern{\'a}ndez and Claudia Prieto and Carlos Alberola-L{\'o}pez} } @conference {603, title = {Multiresolution Reconstruction of Real-Time MRI with Motion Compensated Compressed Sensing: Application to 2D Free-Breathing Cardiac MRI}, booktitle = {International Symposium on Biomedical Engineering: From Nano to Macro}, year = {2016}, month = {2016}, publisher = {IEEE Signal Processing Society}, organization = {IEEE Signal Processing Society}, address = {Prague, Check Republic}, abstract = {

Real-time MRI is a novel noninvasive imaging technique that allows the visualization of physiological processes with both good spatial and temporal resolutions. However, the reconstruction of images from highly undersampled data, needed to perform real-time imaging, remains challenging. Recently, the combination of Compressed Sensing theory with motion compensation techniques has shown to achieve better results than previous methods. In this work we describe a real-time MRI algorithm based on the acquisition of the k-space data following a Golden Radial trajectory, Compressed Sensing reconstruction and a groupwise temporal registration algorithm for the estimation and compensation of the motion in the image, all this embedded within a temporal multiresolution scheme. We have applied the proposed method to the reconstruction of free-breathing acquisition of short axis views of the heart, achieving a temporal resolution of 25ms, corresponding to an acceleration factor of 28 with respect to fully sampled Cartesian acquisitions.

}, keywords = {Compressive sensing \& sampling, Image reconstruction {\textendash} analytical \& iterative methods, Magnetic resonance imaging (MRI)}, author = {J Royuela-del-Val and Muhammad Usman and Lucilio Cordero-Grande and M. Mart{\'\i}n-Fern{\'a}ndez and Federico Simmross-Wattenberg and Claudia Prieto and Carlos Alberola-Lopez} } @conference {690, title = {Whole-heart single breath-hold cardiac cine: A robust motion-compensated compressed sensing reconstruction method}, booktitle = {International Workshop on Reconstruction and Analysis of Moving Body Organs (RAMBO/MICCAI) }, year = {2016}, month = {2016}, address = {Athens, Greece}, author = {J Royuela-del-Val and Muhammad Usman and Lucilio Cordero-Grande and Marcos Mart{\'\i}n-Fern{\'a}ndez and Federico Simmross-Wattenberg and Claudia Prieto and Carlos Alberola-Lopez} } @conference {588, title = {Multiresolution Reconstruction of Real-Time MRI with Motion Compensated Compressed Sensing: Application to 2D Free-Breathing Cardiac MRI}, booktitle = {XXXIII Congreso Anual de la Sociedad Espa{\~n}ola de Ingenier{\'\i}a Biom{\'e}dica (CASEIB)}, year = {2015}, month = {11/2015}, address = {Madrid}, author = {J Royuela-del-Val and Muhammad Usman and Lucilio Cordero-Grande and Marcos Martin-Fernandez and Federico Simmross-Wattenberg and Claudia Prieto and Carlos Alberola-Lopez} } @conference {520, title = {Single Breath Hold Whole Heart Cine MRI With Iterative Groupwise Cardiac Motion Compensation and Sparse Regularization (kt-WiSE)}, booktitle = {Proceedings of the International Society for Magnetic Resonance in Medicine 23}, year = {2015}, author = {J Royuela-del-Val and Muhammad Usman and Lucilio Cordero-Grande and Federico Simmross-Wattenberg and Marcos Martin-Fern{\'a}ndez and Claudia Prieto and Carlos Alberola-Lopez} } @article {bouix2007evaluating, title = {On evaluating brain tissue classifiers without a ground truth}, journal = {Neuroimage}, volume = {36}, number = {4}, year = {2007}, pages = {1207{\textendash}1224}, publisher = {Academic Press}, author = {Bouix, Sylvain and Marcos Martin-Fernandez and Ungar, Lida and Nakamura, Motoaki and Koo, Min-Seong and McCarley, Robert W and Martha E Shenton} } @inbook {martin2005two, title = {Two methods for validating brain tissue classifiers}, booktitle = {Medical Image Computing and Computer-Assisted Intervention{\textendash}MICCAI 2005}, year = {2005}, pages = {515{\textendash}522}, publisher = {Springer Berlin Heidelberg}, organization = {Springer Berlin Heidelberg}, author = {Marcos Martin-Fernandez and Bouix, Sylvain and Ungar, Lida and McCarley, Robert W and Martha E Shenton} } @article {409, title = {Cost functions to estimate a posteriori probabilities in multiclass problems}, journal = {IEEE Transactions on Neural Networks}, volume = {10}, year = {1999}, pages = {645-656}, abstract = {

The problem of designing cost functions to estimate a posteriori probabilities in multiclass problems is addressed in this paper. We establish necessary and sufficient conditions that these costs must satisfy in one-class one-output networks whose outputs are consistent with probability laws. We focus our attention on a particular subset of the corresponding cost functions; those which verify two usually interesting properties: symmetry and separability (well-known cost functions, such as the quadratic cost or the cross entropy are particular cases in this subset). Finally, we present a universal stochastic gradient learning rule for single-layer networks, in the sense of minimizing a general version of these cost functions for a wide family of nonlinear activation functions.

}, keywords = {Cost functions, Estimation, Functions, Learning algorithms, Multiclass problems, Neural networks, Pattern recognition, Probability, Problem solving, Random processes, Stochastic gradient learning rule}, issn = {10459227}, doi = {10.1109/72.761724}, url = {http://www.scopus.com/inward/record.url?eid=2-s2.0-0032643080\&partnerID=40\&md5=d528195bd6ec84531e59ddd2ececcd46}, author = {Jes{\'u}s Cid-Sueiro and J I Arribas and S Urban-Munoz and A R Figueiras-Vidal} }