A lightweight generative model for interpretable subject-level prediction

Chiara Mauri*, Stefano Cerri, Oula Puonti, Mark Mühlau, Koen Van Leemput

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

15 Downloads (Pure)

Abstract

Recent years have seen a growing interest in methods for predicting an unknown variable of interest, such as a subject's diagnosis, from medical images depicting its anatomical-functional effects. Methods based on discriminative modeling excel at making accurate predictions, but are challenged in their ability to explain their decisions in anatomically meaningful terms. In this paper, we propose a simple technique for single-subject prediction that is inherently interpretable. It augments the generative models used in classical human brain mapping techniques, in which the underlying cause–effect relations can be encoded, with a multivariate noise model that captures dominant spatial correlations. Experiments demonstrate that the resulting model can be efficiently inverted to make accurate subject-level predictions, while at the same time offering intuitive visual explanations of its inner workings. The method is easy to use: training is fast for typical training set sizes, and only a single hyperparameter needs to be set by the user. Our code is available at https://github.com/chiara-mauri/Interpretable-subject-level-prediction.

Original languageEnglish
Article number103436
JournalMedical Image Analysis
Volume101
Number of pages18
ISSN1361-8415
DOIs
Publication statusPublished - 2025

Keywords

  • Brain age
  • Explainable AI
  • Generative models
  • Image-based prediction

Fingerprint

Dive into the research topics of 'A lightweight generative model for interpretable subject-level prediction'. Together they form a unique fingerprint.

Cite this