LaMontagne, Pamela

Abstract INTRODUCTION The Centiloid scale is the standard for amyloid (Aβ) PET quantification in research and clinical settings. However, variability between tracers and scanners remains a challenge. METHODS This study introduces DeepSUVR, a deep learning method to correct Centiloid quantification, by penalizing implausible longitudinal trajectories during training. The model was trained using data from 2,129 participants (7,149 Aβ positron emission tomography [PET] scans) in the Australian Imaging, Biomarkers and Lifestyle Study of ageing (AIBL)/Alzheimer's Disease Neuroimaging Initiative (ADNI) and validated using 15,807 Aβ PET scans from 10,543 participants across 10 external datasets. RESULTS DeepSUVR increased correlation between tracers, and reduced variability in the Aß‐negatives. It showed significantly stronger association with cognition, visual reads, neuropathology, and increased longitudinal consistency between studies. DeepSUVR also increased the effect size for detecting small treatment related slowing of amyloid accumulation in the A4 study. DISCUSSION DeepSUVR substantially advances Aβ PET quantification, outperforming all standard approaches, which is particularly important for clinical decision making and to detect subtle or early changes in Aβ. Highlights Novel artificial intelligence (AI)‐method that penalizes biologically implausible longitudinal trajectories, enabling the model to learn standardized uptake value ratios (SUVR) correction factors without requiring longitudinal data at inference time. Improves Centiloid consistency across tracers and studies, significantly enhancing cross‐sectional and longitudinal amyloid positron emission tomography (PET) quantification. DeepSUVR‐derived Centiloids show stronger associations with cognition, visual reads, and neuropathology. Longitudinal variability is reduced three‐ to five‐fold, enabling more reliable tracking of amyloid accumulation and better detection of treatment effects. Novel reference and target masks derived from DeepSUVR replicate most of the model's performance, offering a practical alternative for integration into existing pipelines.

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.

The translation of AI-generated brain metastases (BM) segmentation into clinical practice relies heavily on diverse, high-quality annotated medical imaging datasets. The BraTS-METS 2023 challenge has gained momentum for testing and benchmarking algorithms using rigorously annotated internationally compiled real-world datasets. This study presents the results of the segmentation challenge and characterizes the challenging cases that impacted the performance of the winning algorithms. Untreated brain metastases on standard anatomic MRI sequences (T1, T2, FLAIR, T1PG) from eight contributed international datasets were annotated in stepwise method: published UNET algorithms, student, neuroradiologist, final approver neuroradiologist. Segmentations were ranked based on lesion-wise Dice and Hausdorff distance (HD95) scores. False positives (FP) and false negatives (FN) were rigorously penalized, receiving a score of 0 for Dice and a fixed penalty of 374 for HD95. The mean scores for the teams were calculated. Eight datasets comprising 1303 studies were annotated, with 402 studies (3076 lesions) released on Synapse as publicly available datasets to challenge competitors. Additionally, 31 studies (139 lesions) were held out for validation, and 59 studies (218 lesions) were used for testing. Segmentation accuracy was measured as rank across subjects, with the winning team achieving a LesionWise mean score of 7.9. The Dice score for the winning team was 0.65 ± 0.25. Common errors among the leading teams included false negatives for small lesions and misregistration of masks in space. The Dice scores and lesion detection rates of all algorithms diminished with decreasing tumor size, particularly for tumors smaller than 100 mm3. In conclusion, algorithms for BM segmentation require further refinement to balance high sensitivity in lesion detection with the minimization of false positives and negatives. The BraTS-METS 2023 challenge successfully curated well- annotated, diverse datasets and identified common errors, facilitating the translation of BM segmentation across varied environments and providing the tools for future development of personalized volumetric reports to patients undergoing BM treatment.

Importance Tau positron emission tomography (PET) allows in vivo detection of neurofibrillary tangles, a core neuropathologic feature of Alzheimer disease (AD). Objective To provide estimates of the frequency of tau PET positivity and its associated risk of clinical outcomes. Design, Setting, and Participants Longitudinal study using data pooled from 21 cohorts, comprising a convenience sample of 6514 participants from 13 countries, collected between January 2013 and June 2024. Cognitively unimpaired individuals and patients with a clinical diagnosis of mild cognitive impairment (MCI), AD dementia, or other neurodegenerative disorders were included. Exposures Tau PET with flortaucipir F 18, amyloid-β (Aβ) PET, and clinical examinations. Tau PET scans were visually rated as positive according to a US Food and Drug Administration– and European Medicines Agency–approved method, designed to indicate the presence of advanced neurofibrillary tangle pathology (Braak stages V-VI). Main Outcomes and Measures Frequency of tau PET positivity and absolute risk of clinical progression (eg, progression to MCI or dementia). Results Among the 6514 participants (mean age, 69.5 years; 50.5% female), median follow-up time ranged from 1.5 to 4.0 years. Of 3487 cognitively unimpaired participants, 349 (9.8%) were tau PET positive; the estimated frequency of tau PET positivity was less than 1% in those aged younger than 50 years, and increased from 3% (95% CI, 2%-4%) at 60 years to 19% (95% CI, 16%-24%) at 90 years. Tau PET positivity frequency estimates increased across MCI and AD dementia clinical diagnoses (43% [95% CI, 41%-46%] and 79% [95% CI, 77%-82%] at 75 years, respectively). Most tau PET–positive individuals (92%) were also Aβ PET positive. Cognitively unimpaired participants who were positive for both Aβ PET and tau PET had a higher absolute risk of progression to MCI or dementia over the following 5 years (57% [95% CI, 45%-71%]) compared with both Aβ PET–positive/tau PET–negative (17% [95% CI, 13%-22%]) and Aβ PET–negative/tau PET–negative (6% [95% CI, 5%-8%]) individuals. Among participants with MCI at the time of the tau PET scan, an Aβ PET–positive/tau PET–positive profile was associated with a 5-year absolute risk of progression to dementia of 70% (95% CI, 59%-81%). Conclusions and Relevance In a large convenience sample, a positive tau PET scan occurred at a nonnegligible rate among cognitively unimpaired individuals, and the combination of Aβ PET positivity and tau PET positivity was associated with a high risk of clinical progression in both preclinical and symptomatic stages of AD. These findings underscore the potential of tau PET as a biomarker for staging AD pathology.