AI model mapped 52 brain regions on PET scans without needing an MRI in 1628 images

Study title: Brain fluorodeoxyglucose PET anatomical segmentation via AI: extensive validation in the neurodegenerative spectrum

By September 2026, a peer-reviewed study in Brain reported development and validation of a deep-learning model that automatically segments 52 anatomical regions on brain [18F]FDG PET images without requiring a paired MRI, tested on 1628 images spanning cognitively normal subjects and patients with mild cognitive impairment, Alzheimer's disease, frontotemporal lobar degeneration and Lewy body dementia.

Read the study abstract

The semi-quantitative assessment of brain [18F]FDG PET provides a more objective interpretation and improved accuracy in differentiating across neurodegenerative diseases. However, the correct identification of anatomical regions of interest without a structural MRI is challenging. Thus, this study aims to develop a deep-learning-based (DL-based) model for the automatic segmentation of 52 anatomical regions in brain [18F]FDG PET images and validate it across different metabolic profiles. 1628 brain [18F]FDG PET…

By the Truvace deskSeptember 16, 20261 min read1 sourceEvidence: Moderate · 70/100 — Controlled or validated comparison · n = 1,628 · 1 independent sourcePeer-reviewedTRV-2026-1110· cite & verify

Brain fluorodeoxyglucose PET anatomical segmentation via AI: extensive validation in the neurodegenerative spectrum — TORNAI-SpectrumOfMedicalImaging by Martin Tornai. CC BY 4.0 · https://creativecommons.org/licenses/by/4.0

In brief

The finding matters because semi-quantitative FDG PET assessment normally depends on MRI for anatomical definition, limiting use when MRI is unavailable; the model offers a reliable alternative that outperformed atlas-based methods, though real-world clinical impact, workflow integration, and performance in unrepresented populations remain to be established.

Main points

Internal dataset included 1628 brain [18F]FDG PET images from 1099 subjects: cognitively normal, mild cognitive impairment, subjective memory concerns, Alzheimer's disease, frontotemporal lobar degeneration and Lewy body dementia.
Train-test split was 1109/519 images for training and internal testing, plus 108 images for external validation; ground-truth segmentation was performed on paired T1-weighted MRI.
Per-region mean DSC ranged from 0.729 to 0.923 in internal test set with global mean DSC 0.84±0.06 and average ICC of 0.96±0.02 for SUVRmean agreement.

The gain

Deep-learning model automatically segmented 52 anatomical regions on brain FDG PET alone and achieved MRI-comparable pons-based SUVR quantification across cognitively normal and neurodegenerative patients.

The rundown

Researchers trained and tested a deep-learning model to segment 52 anatomical regions directly on brain [18F]FDG PET without structural MRI, using 1628 images from 1099 subjects and an additional 108 images for external validation, with ground truth derived from paired T1-weighted MRI and atlas-based segmentation as benchmark.

In internal testing, per-region mean Dice similarity coefficient ranged from 0.729 to 0.923 with global mean 0.84±0.06, SUVRmean quantification showed average ICC 0.96±0.02 and per-region relative deviation under 5%, and performance was significantly better than atlas-based segmentation with similar results in external validation.