Although a variety of imaging modalities are used or currently being investigated for patients with brain tumors including brain metastases, clinical image interpretation to date uses only a fraction of the underlying complex, high-dimensional digital information from routinely acquired imaging data. The growing availability of high-performance computing allows the extraction of quantitative imaging features from medical images that are usually beyond human perception. Using machine learning techniques and advanced statistical methods, subsets of such imaging features are used to generate mathematical models that represent characteristic signatures related to the underlying tumor biology and might be helpful for the assessment of prognosis or treatment response, or the identification of molecular markers. The identification of appropriate, characteristic image features as well as the generation of predictive or prognostic mathematical models is summarized under the term radiomics. This review summarizes the current status of radiomics in patients with brain metastases.

Mutations in the isocitrate dehydrogenase (IDH mut) gene have gained paramount importance for the prognosis of glioma patients. To date, reliable techniques for a preoperative evaluation of IDH genotype remain scarce. Therefore, we investigated the potential of O-(2-[18F]fluoroethyl)-L-tyrosine (FET) PET radiomics using textural features combined with static and dynamic parameters of FET uptake for noninvasive prediction of IDH genotype. Prior to surgery, 84 patients with newly diagnosed and untreated gliomas underwent FET PET using a standard scanner (15 of 56 patients with IDH mut) or a dedicated high-resolution hybrid PET/MR scanner (11 of 28 patients with IDH mut). Static, dynamic and textural parameters of FET uptake in the tumor area were evaluated. Diagnostic accuracy of the parameters was evaluated using the neuropathological result as reference. Additionally, FET PET and textural parameters were combined to further increase the diagnostic accuracy. The resulting models were validated using cross-validation. Independent of scanner type, the combination of standard PET parameters with textural features increased significantly diagnostic accuracy. The highest diagnostic accuracy of 93% for prediction of IDH genotype was achieved with the hybrid PET/MR scanner. Our findings suggest that the combination of conventional FET PET parameters with textural features provides important diagnostic information for the non-invasive prediction of the IDH genotype.

Stereotactic radiosurgery (SRS) has evolved as widely accepted treatment option for small-sized (Koos i up to ii) vestibular schwannoma (VS). for larger tumors (prevalent Koos Vi), microsurgery or combined treatment strategies are mostly recommended. However, in patients not suited for microsurgery, SRS might also be an alternative to balance tumor control, hearing preservation and adverse effects. The purpose of this analysis was to evaluate the efficacy and toxicity of SRS for VS with regard to different Koos grades. All patients with untreated VS who received SRS at our center were included. outcome analysis included tumor control, preservation of serviceable hearing based on median pure tone averages (ptA), and procedure-related adverse events rated by the common terminology criteria for Adverse Events (CTCAE; v4.03) classification. In total, 258 patients (median age 58 years, range 21-84) were identified with a mean follow-up of 52 months (range 3-228 months). Mean tumor volume was 1.8 ml (range 0.1-18.5). The mean marginal dose was 12.3 Gy ± 0.6 (range 11-13.5). The cohort was divided into two groups: A (Koos grades i and ii, n = 186) and B (Koos grades III and IV, n = 72). The actuarial tumor control rate was 98% after 2 years and 90% after 5 and 10 years. Koos grading did not show a significant impact on tumor control (p = 0.632) or hearing preservation (p = 0.231). After SRS, 18 patients (7%) had new transient or permanent symptoms classified by the CTCAE. The actuarial rate of ctcAe-free survival was not related to Koos grading (p = 0.093). Based on this selected population of Koos grade iii and iV VS without or with only mild symptoms from brainstem compression, SRS can be recommended as the primary therapy with the advantage of low morbidity and satisfactory tumor control. The overall hearing preservation rate and toxicity of SRS was influenced by age and cannot be predicted by tumor volume or Koos grading alone.

Background Stereotactic radiosurgery (SRS) may cause transient changes of morphology and volume in vestibular schwannomas (VS). This may lead to difficulties in distinguishing treatment-related changes (pseudoprogression) from tumor recurrence (true progression), especially at 12-24 months after treatment. Therefore, we investigated the time course of volume changes of VS after robot-guided SRS. Material and Methods We included all patients with unilateral VS who underwent single fraction robotic guided SRS using the Cyberknife® with a minimum follow-up (FU) of 24 months and MR images ≤3 mm slice thickness. Tumor volumes were measured on T1-weighted contrast enhanced images. Volume changes (percentage of tumor volume change compared to baseline) during FU were classified according to RANO criteria (“partial response” (PR) (≥65% decrease), “stable disease” (SD) (<65% decrease; <20% increase), or “progressive disease” (PD) (≥40% increase)). A new status “pseudoprogression” (PP) (>20% transient increase) was defined and divided into early (ePP, occurrence within first <12 months) and late (lPP, >12 months) PP. Results Overall 63 patients fulfilled the inclusion criteria. The median age was 56 years (range: 20-82) and the median initial tumor volume was 1.5 cm3 (range: 0.1 - 8.6). All patients received 13 Gy with an isodose level of 80%. The median radiological and clinical FU was 66 months (range: 24-103). We found PR in 36% (n=23), SD in 35% (n=22) and PP in 29% (n=18). The latter was separated in ePP in 16% (n=10) and lPP in 13% (n=8). The median time to peak in the ePP was six months (range: 4 - 10) and in the lPP 35 months (range: 14 - 61). The median time to return from peak to baseline was seven months in the ePP (range: 5 - 20) and 18 months (range: 6 - 33) in the lPP group. Using these criteria no PD was observed. Additionally, we did not find any significant impact of radiation parameters (coverage, nCi, prescription dose, maximal dose) or patient related parameters (tumor volume, age) on the onset of early and/or late PP. Conclusion In our study, we demonstrated that any volume increase assumed to be PD turned out to be ePP or lPP. This might impact the management of VS treated with robotic SRS during FU in favour of further observation.