The advent of immunotherapy using immune checkpoint inhibitors (ICIs) and targeted therapy (TT) has dramatically improved the prognosis of various cancer types. However, following ICI therapy or TT—either alone (especially ICI) or in combination with radiotherapy—imaging findings on anatomical contrast-enhanced MRI can be unpredictable and highly variable, and are often difficult to interpret regarding treatment response and outcome. This review aims at summarizing the imaging challenges related to TT and ICI monotherapy as well as combined with radiotherapy in patients with brain metastases, and to give an overview on advanced imaging techniques which potentially overcome some of these imaging challenges. Currently, major evidence suggests that imaging parameters especially derived from amino acid PET, perfusion-/diffusion-weighted MRI, or MR spectroscopy may provide valuable additional information for the differentiation of treatment-induced changes from brain metastases recurrence and the evaluation of treatment response.

Currently, a reliable diagnostic test for differentiating pseudoprogression from early tumor progression is lacking. We explored the potential of O-(2-[¹⁸F]fluoroethyl)-L-tyrosine (FET) positron emission tomography (PET) radiomics for this clinically important task. Thirty-four patients (isocitrate dehydrogenase (IDH)-wildtype glioblastoma, 94%) with progressive magnetic resonance imaging (MRI) changes according to the Response Assessment in Neuro-Oncology (RANO) criteria within the first 12 weeks after completing temozolomide chemoradiation underwent a dynamic FET PET scan. Static and dynamic FET PET parameters were calculated. For radiomics analysis, the number of datasets was increased to 102 using data augmentation. After randomly assigning patients to a training and test dataset, 944 features were calculated on unfiltered and filtered images. The number of features for model generation was limited to four to avoid data overfitting. Eighteen patients were diagnosed with early tumor progression, and 16 patients had pseudoprogression. The FET PET radiomics model correctly diagnosed pseudoprogression in all test cohort patients (sensitivity, 100%; negative predictive value, 100%). In contrast, the diagnostic performance of the best FET PET parameter (TBR_max) was lower (sensitivity, 81%; negative predictive value, 80%). The results suggest that FET PET radiomics helps diagnose patients with pseudoprogression with a high diagnostic performance. Given the clinical significance, further studies are warranted.

This Policy Review provides recommendations for the use of PET imaging in patients with gliomas and represents a joint effort of the Response Assessment in Neuro-Oncology (RANO) working group for PET and the European Association for Neuro-Oncology. The initial guideline was published in 2016, and summarised the previously established clinical benefit of PET with radiolabelled glucose and amino acid tracers in patients with gliomas. Since then, numerous additional studies have been published on this topic, focusing on differential diagnosis, prediction of molecular information, and prognostication. Further studies evaluated PET for biopsy guidance and delineation of glioma extent for local therapy planning, including resection and radiotherapy. In patients undergoing treatment, PET was studied for the assessment of response to local and systemic treatments and PET-based standardised response criteria (PET RANO 1.0) were proposed. In this Policy Review, the updated recommendations are based on evidence generated from studies that validated PET findings by histomolecular findings or clinical course. This guideline further underscores the previously reported clinical value of PET imaging and the superiority of amino acid PET over glucose PET, providing a framework for the use of PET in the management of patients with gliomas. The guideline also underscores the scarcity of class 1 evidence showing that incorporating PET imaging into clinical workflows improves patient outcomes, highlighting priority areas for future clinical studies designed to address this gap.

The large language model Generative Pretrained Transformer 4th-generation model (GPT-4; OpenAI) allows for the creation of summaries and graphic representations of the course of disease from the reports of various MRI examinations in patients with glioblastomas.