RT info:eu-repo/semantics/article
T1 Validation of deep learning techniques for quality augmentation in diffusion MRI for clinical studies
A1 Aja Fernández, Santiago
A1 Martín Martín, Carmen
A1 Planchuelo Gómez, Álvaro
A1 Faiyaz, Abrar
A1 Uddin, Md Nasir
A1 Schifitto, Giovanni
A1 Tiwari, Abhishek
A1 Shigwan, Saurabh J.
A1 Kumar Singh, Rajeev
A1 Zheng, Tianshu
A1 Cao, Zuozhen
A1 Wu, Dan
A1 Blumberg, Stefano B.
A1 Sen, Snigdha
A1 Goodwin-Allcock, Tobias
A1 Slator, Paddy J.
A1 Yigit Avci, Mehmet
A1 Li, Zihan
A1 Bilgic, Berkin
A1 Tian, Qiyuan
A1 Wang, Xinyi
A1 Tang, Zihao
A1 Cabezas, Mariano
A1 Rauland, Amelie
A1 Merhof, Dorit
A1 Manzano María, Renata
A1 Campos, Vinícius Paraníba
A1 Santini, Tales
A1 da Costa Vieira, Marcelo Andrade
A1 HashemizadehKolowri, SeyyedKazem
A1 DiBella, Edward
A1 Peng, Chenxu
A1 Shen, Zhimin
A1 Chen, Zan
A1 Ullah, Irfan
A1 Mani, Merry
A1 Abdolmotallby, Hesam
A1 Eckstrom, Samuel
A1 Baete, Steven H.
A1 Filipiak, Patryk
A1 Dong, Tanxin
A1 Fan, Qiuyun
A1 Luis García, Rodrigo de
A1 Tristán Vega, Antonio
A1 Pieciak, Tomasz
K1 Deep learning
K1 Machine learning
K1 Artificial intelligence
K1 Diffusion MRI
K1 Angular resolution
K1 Diffusion tensor
AB 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.
PB Elsevier
SN 2213-1582
YR 2023
FD 2023
LK https://uvadoc.uva.es/handle/10324/70628
UL https://uvadoc.uva.es/handle/10324/70628
LA eng
NO NeuroImage: Clinical, 2023, vol. 39, p. 103483
DS UVaDOC
RD 24-nov-2024