Document Type : Systematic Review
Authors
- Mahsa Shakeri 1, 2
- Azadeh Amraee 3
- Seyyed Mohammad Hosseini 1, 2
- Leili Darvish 4, 5
- Forough Farkhondeh 6
- Ahmad Mostaar 7
- Hossein Ghadiri 1, 2
1 Department of Medical Physics and Biomedical Engineering, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
2 Research Center for Molecular and Cellular Imaging (RCMCI), Advanced Medical Technologies and Equipment Institute (AMTEI), Tehran University of Medical Sciences, Tehran, Iran
3 Department of Medical Physics, School of Medicine, Lorestan University of Medical Sciences, Khorramabad, Iran
4 Mother and Child Welfare Research Center, Hormozgan University of Medical Sciences, Bandar Abbas, Iran
5 5Department of Radiology, Faculty of ParaMedicine, Hormozgan University of Medical Sciences, Bandar Abbas, Iran
6 Medical Physics Department, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
7 Department of Medical Physics and Biomedical Engineering, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran
Abstract
Background: The assessment of treatment-induced changes in glioma and the evaluation of glioma prognosis are crucial components of effective treatment management. Radiomics models based on Positron Emission Tomography (PET) imaging can provide critical insights into therapeutic response monitoring.
Objective: This systematic review aimed to evaluate the performance of PET-based radiomics models in distinguishing treatment-related changes and predicting the prognosis of glioma.
Material and Methods: In this systematic review, the articles were searched from the Web of Science databases, MEDLINE, PubMed, and EMBASE. The search terms were “amino acid PET”, “PET”, “glioblastoma”, “glioma”, “positron emission tomography”, “machine learning”, “deep learning”, “radiomics”, “artificial intelligence”, “AI”, “prognosis”, “outcome”, “post treatment changes”, “treatment-related changes”, “progression”, “true progression” “pseudo-progression”, and “necrosis”. The titles, abstracts, and full text of the recognized citations were reviewed by two independent reviewers and then the selected articles were abstracted by two independent reviewers based on a standard grid. PRISMA checklist was applied to assess the overall quality of evidence for each outcome.
Results: The PET-based radiomics models outperform conventional PET parameter models, such as maximum tumor-to-brain ratios and mean tumor-to-brain ratios in distinguishing post-treatment changes and predicting glioma prognosis. The model integrating radiomics features and the conventional PET parameters achieved superior diagnostic performance compared to radiomics and conventional parameter models solely in differentiation treatment related changes.
Conclusion: PET based radiomics models demonstrate enhanced capability in differentiating tumor recurrence from treatment-related changes. The implementation of these models can facilitate personalized treatment plans and increase the patient’s overall survival or quality of life.
Keywords
)