Connectionists: published: IRMA - Machine learning-based harmonization of 18F-FDG PET brain scans in multi-center studies

[Michael Biehl]

Our paper "IRMA: Machine learning-based harmonization of 18F-FDG PET brain
scans in multi-center studies"
by Sofie Lövdal et al. has been published in the European Journal of
Nuclear Medicine and Molecular Imaging
and is available online (open access):
https://link.springer.com/article/10.1007/s00259-025-07114-4

In this work we apply interpretable machine learning systems for the
analysis of 18-FDG PET
brain scans from different medical centers. We show that the center origin
of healthy control brain
images acquired with different scanners/protocols can be identified with
high confidence. Consequently,
machine learning models  trained with data from different scanners may be
heavily impacted by this
bias when applied to a clinically  relevant problem, e.g. the differential
diagnosis of neurodegenerative
disorders. We propose IRMA (Iterated Relevance Matrix Analysis)  as a
recursive method to learn and
disregard bias in PET feature vectors. Related code is freely available at
https://github.com/SofieLovdal/IRMA-harmonization

---------------------------------------------------
Prof. Dr. Michael Biehl
Bernoulli Institute for Mathematics,
Computer Science & Artificial Intelligence
P.O. Box 407, 9700 AK Groningen, NL
https://www.cs.rug.nl/~biehl     m.biehl at rug.nl
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20250219/3227e837/attachment.html>