# Revisiting Centiloids using AI

## TL;DR

This paper introduces DeepSUVR, an AI method that improves the accuracy and consistency of amyloid PET scans, which are used to study Alzheimer's disease.

## Contribution

DeepSUVR is a novel deep learning method that corrects Centiloid quantification by penalizing implausible longitudinal trajectories.

## Key findings

- DeepSUVR increased correlation between tracers and reduced variability in Aβ-negative scans.
- It showed the strongest association with cognition and best longitudinal consistency across studies.
- DeepSUVR increased the effect size for detecting lower Centiloid increase per year in the A4 study.

## Abstract

The Centiloid scale is the standard for Amyloid (Aβ) PET quantification, widely used in research, clinical settings, and trial stratification. However, variability between tracers and scanners remains a challenge. This study introduces DeepSUVR, a deep learning method to correct Centiloid quantification, by penalising implausible longitudinal trajectories during training. The model was trained using data from 2,098 participants (6,762 Aβ PET scans) in AIBL/ADNI and validated using 15,806 Aβ PET scans from 10,543 participants across 10 external datasets. DeepSUVR increased correlation between tracers, and reduced variability in the Aβ-negatives. It showed the strongest association with cognition, highest AUC against visual reads and best longitudinal consistency between studies. DeepSUVR also increased the effect size for detecting lower Centiloid increase per year in the A4 study. DeepSUVR advances Aβ PET quantification, outperforming standard approaches, which is particularly important for consistent decision making and to detect subtle and early changes in clinical interventions.