Purpose: This European Organisation for Research and Treatment of Cancer phase III trial assesses whether adjuvant whole-brain radiotherapy (WBRT) increases the duration of functional independence after surgery or radiosurgery of brain metastases.Patients and Methods: Patients with one to three brain metastases of solid tumors (small-cell lung cancer excluded) with stable systemic disease or asymptomatic primary tumors and WHO performance status (PS) of 0 to 2 were treated with complete surgery or radiosurgery and randomly assigned to adjuvant WBRT (30 Gy in 10 fractions) or observation (OBS). The primary end point was time to WHO PS deterioration to more than 2.Results: Of 359 patients, 199 underwent radiosurgery, and 160 underwent surgery. In the radiosurgery group, 100 patients were allocated to OBS, and 99 were allocated to WBRT. After surgery, 79 patients were allocated to OBS, and 81 were allocated to adjuvant WBRT. The median time to WHO PS more than 2 was 10.0 months (95% CI, 8.1 to 11.7 months) after OBS and 9.5 months (95% CI, 7.8 to 11.9 months) after WBRT (P = .71). Overall survival was similar in the WBRT and OBS arms (median, 10.9 v 10.7 months, respectively; P = .89). WBRT reduced the 2-year relapse rate both at initial sites (surgery: 59% to 27%, P < .001; radiosurgery: 31% to 19%, P = .040) and at new sites (surgery: 42% to 23%, P = .008; radiosurgery: 48% to 33%, P = .023). Salvage therapies were used more frequently after OBS than after WBRT. Intracranial progression caused death in 78 (44%) of 179 patients in the OBS arm and in 50 (28%) of 180 patients in the WBRT arm.Conclusion: After radiosurgery or surgery of a limited number of brain metastases, adjuvant WBRT reduces intracranial relapses and neurologic deaths but fails to improve the duration of functional independence and overall survival.

Background: Magnetic resonance imaging (MRI) and amino acid positron-emission tomography (PET) of the brain contain a vast amount of structural and functional information that can be analyzed by machine learning algorithms and radiomics for the use of radiotherapy in patients with malignant brain tumors. Methods: This study is based on comprehensive literature research on machine learning and radiomics analyses in neuroimaging and their potential application for radiotherapy in patients with malignant glioma or brain metastases. Results: Feature-based radiomics and deep learning-based machine learning methods can be used to improve brain tumor diagnostics and automate various steps of radiotherapy planning. In glioma patients, important applications are the determination of WHO grade and molecular markers for integrated diagnosis in patients not eligible for biopsy or resection, automatic image segmentation for target volume planning, prediction of the location of tumor recurrence, and differentiation of pseudoprogression from actual tumor progression. In patients with brain metastases, radiomics is applied for additional detection of smaller brain metastases, accurate segmentation of multiple larger metastases, prediction of local response after radiosurgery, and differentiation of radiation injury from local brain metastasis relapse. Importantly, high diagnostic accuracies of 80–90% can be achieved by most approaches, despite a large variety in terms of applied imaging techniques and computational methods. Conclusion: Clinical application of automated image analyses based on radiomics and artificial intelligence has a great potential for improving radiotherapy in patients with malignant brain tumors. However, a common problem associated with these techniques is the large variability and the lack of standardization of the methods applied.

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.

Background: Structural follow-up magnetic resonance imaging (MRI) after stereotactic radiosurgery (SRS) for brain metastases frequently displays local changes in the area of applied irradiation, which are often difficult to interpret (e.g., local tumor recurrence, radiation-induced changes). The use of stereotactic biopsy for histological assessment of these changes has a high diagnostic accuracy and can be considered as method of choice. In order to solve this relevant clinical problem non-invasively, advanced MRI techniques and amino acid positron-emission-tomography (PET) are increasingly used. Case presentation: We report the long-term follow-up of a patient who had been treated with linear accelerator based SRS for cerebral metastases of a lung cancer. Fifty-eight months after SRS, the differentiation of local recurrent brain metastasis from radiation-induced changes using structural MRI was difficult. For further differentiation, perfusion-weighted MRI (PWI), proton magnetic resonance spectroscopy (MRS), and ¹¹C-methyl-L-methionine (MET) PET was performed. Due to artifacts and technical limitations, PWI MRI and MRS findings were not conclusive. In contrast, MET PET findings were suggestive for radiation-induced changes. Finally, a stereotactic biopsy for histological assessment of these changes demonstrated clearly a radiation-induced necrosis and the absence of vital tumor. Conclusion: The use of stereotactic biopsy for histological assessment of indistinguishable lesions on structural MRI after SRS for treatment of brain metastasis represents a highly reliable method to differentiate local tumor recurrence from radiation-induced changes. In this field, results of studies with both advanced MRI techniques and amino acid PET suggest encouraging results. However, artifacts and technical limitations (e.g., lesion size) are still a problem and comparative studies are needed to investigate the relationship, diagnostic performance, and complementary character of advanced MRI techniques and amino acid PET.

Combination concepts of radiotherapy and immune checkpoint inhibition are currently of high interest. We examined imaging findings, acute toxicity, and local control in patients with melanoma brain metastases receiving programmed death 1 (PD-1) inhibitors and/or robotic stereotactic radiosurgery (SRS). Twenty-six patients treated with SRS alone (n = 13; 20 lesions) or in combination with anti-PD-1 therapy (n = 13; 28 lesions) were analyzed. Lesion size was evaluated three and six months after SRS using a volumetric assessment based on cranial magnetic resonance imaging (cMRI) and acute toxicity after 12 weeks according to the Common Terminology Criteria for Adverse Events (CTCAE). Local control after six months was comparable (86%, SRS + anti-PD-1, and 80%, SRS). All toxicities reported were less than or equal to grade 2. One metastasis (5%) in the SRS group and six (21%) in the SRS + anti-PD-1 group increased after three months, whereas four (14%) of the six regressed during further follow-ups. This was rated as pseudoprogression (PsP). Three patients (23%) in the SRS + anti-PD-1 group showed characteristics of PsP. Treatment with SRS and anti-PD-1 antibodies can be combined safely in melanoma patients with cerebral metastases. Early volumetric progression of lesions under simultaneous treatment may be related to PsP; thus, the evaluation of combined radioimmunotherapy remains challenging and requires experienced teams.