Adjustment for the Age- and Gender-Related Metabolic Changes Improves the Differential Diagnosis of Parkinsonism

Abstract

Age and gender are the important factors for brain metabolic declines in both normal aging and neurodegeneration, and the confounding effects may influence early and differential diagnosis of neurodegenerative diseases based on the [ 18 F] fluorodeoxyglucose positron emission tomography ([ 18 F]FDG PET). We aimed to explore the potential of the adjustment of age-and gender-related confounding factors on [ 18 F]FDG PET images in differentiation of Parkinson's disease (PD), multiple system atrophy (MSA) and progressive supra-nuclear palsy (PSP). Eight hundred and seventy-seven clinically definitely diagnosed Parkinsonian patients from a benchmark Huashan Parkinsonian PET imaging database were included. An age-and gender-adjusted Z (AGAZ) score was established based on the gender-specific longitudinal metabolic changes on healthy subjects. AGAZ scores and standardized uptake value ratio (SUVR) values were quantified at regional-level and support vector machine-based error-correcting output codes method was applied for classification. Additional references of the classifications based on metabolic pattern scores were included. The feature-based AGAZ score showed the best performance in classification (accuracy for PD, MSA, PSP: 93.1%, 96.3%, 94.8%). In both genders, the AGAZ score consistently achieved the best efficiency, and the improvements compared to the conventional SUVR value for PD, MSA, and PSP mainly laid in specificity (Male: 5.7%; Female: 11.1%), sensitivity (Male: 7.2%; Female: 7.3%), and sensitivity (Male: 7.3%; Female: 17.2%). Female patients benefited more from the adjustment on [ 18 F]FDG PET in MSA and PSP groups (absolute net reclassification index, p < 0.001). Collectively, the adjustment of age-and gender-related confounding factors may improve the differential diagnosis of Parkinsonism. Particularly, the diagnosis of female Parkinsonian population has the best improvement from this correction.

Diagnostic performance of artificial intelligence-assisted PET imaging for Parkinson’s disease: a systematic review and meta-analysis

“…In addition, AI can facilitate junior physicians training by providing immediate diagnostic feedback 47 . A collaborative human-AI model could optimize diagnostic accuracy by integrating the unique strengths of both components and potentially incorporating nonimagebased patient data such as demographic information and history of motor impairment [48][49][50] . These AI methods, with their potential for quality assurance and personalized, predictive medicine, represent promising models for improving healthcare.…”

Characterization of tau propagation pattern and cascading hypometabolism from functional connectivity in Alzheimer's disease

“…All 18 F‐Florzolotau (90–110 min post‐injection) and 18 F‐FDG (60–70 min post‐injection) PET images were scanned on a Biograph mCT Flow PET/CT scanner (Siemens, Erlangen, Germany) after intravenous injection of 18 F‐Florzolotau (370 mBq) or 18 F‐FDG (185 mBq) on various study days. The detailed parameters can be found elsewhere (Liu et al, 2023; Lu, Wang, et al, 2023). All anatomical T1‐weighted MRI and fMRI were consecutively scanned on a 3.0‐T horizontal magnet scanner (Discovery MR750; GE Medical Systems, Milwaukee, WI) using the following parameters: echo time (TE), 3.2 ms; repetition time (TR), 8.2 ms; TI, 450 ms; flip angle, 12°; 25.6 cm field of view (FOV); acquisition matrix, 256 × 256 × 152; and voxel size, 1 × 1 × 1 mm.…”

Improved interpretation of 18F-florzolotau PET in progressive supranuclear palsy using a normalization-free deep-learning classifier

“…On the other hand, semi-quantification analysis is mainly used in research settings as an alternative to visual reading. This involves calculating tracer uptake in selected regions of interest (ROIs) and dividing it by the signal in the reference region to obtain semi-quantitative parameters (i.e., standardized uptake value ratios, SUVRs), 9 which serve as relatively objective bases for tau PET-imaging interpretation. However, this methodology is limited by the need for spatial normalization, 10 potential inconsistencies in ROI selection, the involvement of the same ROIs in different diseases, the lack of widely accepted cut-offs for PET parameters, 11 and uncertainties in establishing the most suitable reference areas.…”