# On the generalizability of diffusion MRI signal representations across acquisition parameters, sequences and tissue types: Chronicles of the MEMENTO challenge

Alberto De Luca, Andrada Ianus, Alexander Leemans, Marco Palombo, Noam Shemesh, Hui Zhang, Daniel C. Alexander, Markus Nilsson, Martijn Froeling, Geert-Jan Biessels, Mauro Zucchelli, Matteo Frigo, Enes Albay, Sara Sedlar, Abib Alimi, Samuel Deslauriers-Gauthier, Rachid Deriche, Rutger Fick, Maryam Afzali, Tomasz Pieciak, Fabian Bogusz, Santiago Aja-Fernández, Evren Özarslan, Derek K. Jones, Haoze Chen, Mingwu Jin, Zhijie Zhang, Fengxiang Wang, Vishwesh Nath, Prasanna Parvathaneni, Jan Morez, Jan Sijbers, Ben Jeurissen, Shreyas Fadnavis, Stefan Endres, Ariel Rokem, Eleftherios Garyfallidis, Irina Sanchez, Vesna Prchkovska, Paulo Rodrigues, Bennet A. Landman, Kurt G. Schilling

NeuroImage · 2021 · Article

https://doi.org/10.1016/j.neuroimage.2021.118367

## Summary

The MEMENTO challenge tests how diffusion MRI signal models generalize to unseen measurements and different encoding schemes. Results show that fitting choices and hyperparameters matter alongside model selection, with double and oscillating encoding proving especially challenging.

## Study overview

Eight teams submitted 80 fits to predict withheld measurements from human and mouse diffusion MRI datasets. Most methods predicted single-diffusion-encoding signals well, with weaker performance at extreme diffusion weightings and on double or oscillating encoding. The comparison emphasizes reporting and optimizing fitting procedures as well as choosing a signal model.

## Findings / topics

- Generalization depended on the acquisition scheme and diffusion weighting.
- Fitting choices and hyperparameters substantially affected prediction performance.

## Resources

- [Original work](https://linkinghub.elsevier.com/retrieve/pii/S1053811921006431)
- [PDF](https://pmc.ncbi.nlm.nih.gov/articles/PMC7615259/pdf/EMS189821.pdf)
- [Open full text](https://pmc.ncbi.nlm.nih.gov/articles/PMC7615259/)

Lab page: https://www.microstructure-connectivity-lab.com/publications/memento-signal-generalizability/

This is a research summary, not the full article.