Comprehensive Summary
This review explored how the combination of imaging and metabolic analysis of PET-CT improves diagnostic accuracy, prognosis, interventional procedures, and therapeutic monitoring in patients with sarcoma. Using standard uptake values (SUVs) to measure metabolic activity, PET-CT has accurately differentiated benign from malignant tumors, assessed tumor grade and aggressiveness, predicted survival, identified metastatic lesions, and guided biopsies superiorly to conventional CT. Regarding treatment, PET-CT has also improved delineation of tumor borders during ablations, accuracy of radiotherapy, assessment of therapeutic response (outperforming prior size-based criteria), and predictiveness of surveillance (which was improved even further with the implementation of radiotracers). Radiation, false-positives due to post-therapeutic inflammation, and infrastructure remain significant limitations of PET-CT. Lastly, PET-CT has helped the creation of standardized biobanks consolidating imaging, genomic, and clinical data which will support AI-driven predictive models that individualize treatments for patients with sarcoma.
Outcomes and Implications
Sarcomas are a diverse class of malignancy primarily affecting children. Implementation of PET-CT into sarcoma management is clinically important because by improving diagnostic accuracy, therapeutic response assessment, and surveillance, it increases the lifespan of children, reduces errors and complications, and increases the specificity and effectiveness of treatments. Predictive AI models from PET-CT radiomics will likely improve patient stratification, personalized treatment plans, and radiation planning by protecting healthy tissue while ensuring full tumor coverage. Overall, it is clear that PET-CT has significant clinical benefit to patients with sarcoma, however, research is still needed to assess the role of AI in this process and the extent to which it benefits this patient population.