The performance of machine learning approaches for attenuation correction of PET in neuroimaging: A meta-analysis

Purpose: This systematic review provides a consensus on the clinical feasibility of machine learning (ML) methods for brain PET attenuation correction (AC). Performance of ML-AC were compared to clinical standards.Methods: Two hundred and eighty studies were identified through electronic searches of brain PET studies published between January 1, 2008, and August 1, 2022. Reported outcomes for image quality, tissue classifi-cation performance, regional and global bias were extracted to evaluate ML-AC performance. Methodological quality of included studies and the quality of evidence of analysed outcomes were assessed using QUADAS-2 and GRADE, respectively.Results: A total of 19 studies (2371 participants) met the inclusion criteria. Overall, the global bias of ML methods was 0.76 +/- 1.2%. For image quality, the relative mean square error (RMSE) was 0.20 +/- 0.4 while for tissues classification, the Dice similarity coefficient (DSC) for bone/soft tissue/air were 0.82 +/- 0.1 / 0.95 +/- 0.03 / 0.85 +/- 0.14. Conclusions: In general, ML-AC performance is within acceptable limits for clinical PET imaging. The sparse information on ML-AC robustness and its limited qualitative clinical evaluation may hinder clinical imple-mentation in neuroimaging, especially for PET/MRI or emerging brain PET systems where standard AC approaches are not readily available.(c) 2023 Elsevier Masson SAS. All rights reserved.

Automated summary

This systematic review provides a consensus on the clinical feasibility of machine learning methods for brain PET attenuation correction. The performance of ML-AC was compared to clinical standards. The results suggest that ML-AC has acceptable performance for clinical PET imaging but further research is needed to assess its robustness and clinical implementation.