RESUMO
PURPOSE: We evaluate the ability of Artificial Intelligence with automatic classification methods applied to semi-quantitative data from brain 18F-FDG PET/CT to improve the differential diagnosis between Alzheimer Disease (AD) and Mild Cognitive Impairment (MCI). PROCEDURES: We retrospectively analyzed a total of 150 consecutive patients who underwent diagnostic evaluation for suspected AD (n = 67) or MCI (n = 83). All patients received brain 18F-FDG PET/CT according to the international guidelines, and images were analyzed both Qualitatively (QL) and Quantitatively (QN), the latter by a fully automated post-processing software that produced a z score metabolic map of 25 anatomically different cortical regions. A subset of n = 122 cases with a confirmed diagnosis of AD (n = 53) or MDI (n = 69) by 18-24-month clinical follow-up was finally included in the study. Univariate analysis and three automated classification models (classification tree -ClT-, ridge classifier -RC- and linear Support Vector Machine -lSVM-) were considered to estimate the ability of the z scores to discriminate between AD and MCI cases in. RESULTS: The univariate analysis returned 14 areas where the z scores were significantly different between AD and MCI groups, and the classification accuracy ranged between 74.59% and 76.23%, with ClT and RC providing the best results. The best classification strategy consisted of one single split with a cut-off value of ≈ -2.0 on the z score from temporal lateral left area: cases below this threshold were classified as AD and those above the threshold as MCI. CONCLUSIONS: Our findings confirm the usefulness of brain 18F-FDG PET/CT QL and QN analyses in differentiating AD from MCI. Moreover, the combined use of automated classifications models can improve the diagnostic process since its use allows identification of a specific hypometabolic area involved in AD cases in respect to MCI. This data improves the traditional 18F-FDG PET/CT image interpretation and the diagnostic assessment of cognitive disorders.
RESUMO
We evaluated the effect of a reduced acquisition time for 18F-FDG PET studies of Alzheimer dementia (AD) and frontotemporal dementia (FTD) to derive a limit for reductions of acquisition time (improving patient compliance) and administered activity (lowering the radiation dose) with uncompromised diagnostic outcome. Methods: We included patients with a clinical diagnosis of AD (n = 13) or FTD (n = 12) who were examined with 18F-FDG PET/CT after injection of 210 ± 9 MBq of 18F-FDG. List-mode data were reconstructed over various time intervals simulating reduced acquisition times or administered activities. Volume-of-interest-based and voxelwise statistical analyses including group contrasts were performed for 15 different acquisition times ranging from 10 min to 2 s. In addition, masked visual reads were obtained from 3 readers independently for 7 different acquisition times down to 30 s, providing a diagnosis of either AD or FTD and the individual diagnostic certainty. Results: Regional mean uptake changed by less than 5% at a reduced acquisition time down to 1 min in all regions and patients except for the posterior cingulate cortex of 1 patient. Voxelwise group contrasts suggest a sufficient measurement time of only 2 min, for which the number of significant voxels decreased by merely 5% while maintaining their spatial pattern. In 450 visual reads at reduced times, no change in the original diagnosis was observed. The diagnostic certainty showed only a very slow and mild decline, with small effect sizes (Cohen's d) of 0.3, at acquisition times of 3 and 2 min compared with the original results at 10 min. Conclusion: Statistical results at a region and voxel level, as well as single-subject visual reads, reveal a considerable potential to reduce the typical 10-min acquisition time (by a factor of 4) without compromising diagnostic quality. Conversely, our data suggest that for a given acquisition time of 10 min and a similar effect size, the administered activity may be reduced to 50 MBq, resulting in an effective dose of less than 1 mSv for the PET examination.