Early volumetric change and treatment outcome of metastatic brain tumors after external beam radiotherapy: differential radiotherapy for brain metastasis

Factors associated with the local control of brain metastases: a systematic search and machine learning application

BACKGROUND

Enhancing Local Control (LC) of brain metastases is pivotal for improving overall survival, which makes the prediction of local treatment failure a crucial aspect of treatment planning. Understanding the factors that influence LC of brain metastases is imperative for optimizing treatment strategies and subsequently extending overall survival. Machine learning algorithms may help to identify factors that predict outcomes.

METHODS

This paper systematically reviews these factors associated with LC to select candidate predictor features for a practical application of predictive modeling. A systematic literature search was conducted to identify studies in which the LC of brain metastases is assessed for adult patients. EMBASE, PubMed, Web-of-Science, and the Cochrane Database were searched up to December 24, 2020. All studies investigating the LC of brain metastases as one of the endpoints were included, regardless of primary tumor type or treatment type. We first grouped studies based on primary tumor types resulting in lung, breast, and melanoma groups. Studies that did not focus on a specific primary cancer type were grouped based on treatment types resulting in surgery, SRT, and whole-brain radiotherapy groups. For each group, significant factors associated with LC were identified and discussed. As a second project, we assessed the practical importance of selected features in predicting LC after Stereotactic Radiotherapy (SRT) with a Random Forest machine learning model. Accuracy and Area Under the Curve (AUC) of the Random Forest model, trained with the list of factors that were found to be associated with LC for the SRT treatment group, were reported.

RESULTS

The systematic literature search identified 6270 unique records. After screening titles and abstracts, 410 full texts were considered, and ultimately 159 studies were included for review. Most of the studies focused on the LC of the brain metastases for a specific primary tumor type or after a specific treatment type. Higher SRT radiation dose was found to be associated with better LC in lung cancer, breast cancer, and melanoma groups. Also, a higher dose was associated with better LC in the SRT group, while higher tumor volume was associated with worse LC in this group. The Random Forest model predicted the LC of brain metastases with an accuracy of 80% and an AUC of 0.84.

CONCLUSION

This paper thoroughly examines factors associated with LC in brain metastases and highlights the translational value of our findings for selecting variables to predict LC in a sample of patients who underwent SRT. The prediction model holds great promise for clinicians, offering a valuable tool to predict personalized treatment outcomes and foresee the impact of changes in treatment characteristics such as radiation dose.

Hippocampus-Sparing Whole-Brain Radiotherapy and Simultaneous Integrated Boost for Multiple Brain Metastases From Lung Adenocarcinoma

In this study, the volume response and treatment outcome after hippocampus-sparing whole-brain radiotherapy (HS-WBRT) with simultaneous integrated boost (SIB) using tomotherapy were evaluated. Patients with primary lung adenocarcinoma and multiple brain metastases who had a Karnofsky performance status ≥70 and exhibited well-controlled extracranial disease were treated. The prescribed dose was administered in 10 to 14 fractions as 25 to 28 Gy to whole-brain parenchyma, as 40 to 48 Gy to the gross metastatic lesion, and as 30 to 42 Gy to a 5-mm margin to the metastatic lesion. Double-dose gadolinium contrast-enhanced magnetic resonance imaging at 1-mm slice thickness was performed before treatment and at 1, 4, and 7 months post-treatment. The tumor volume reduction ratio was calculated for each follow-up. Between July 2011 and September 2012, 11 patients with 70 lesions were included in this analysis. The median number of lesions per patient was 4 (range, 2-15). The median initial tumor volume was 0.235 cm3 (range, 0.020-10.140 cm3). The treatment plans were evaluated regarding conformation number (CN), target coverage (TC), and homogeneity index (HI). The median follow-up duration was 14 months (range, 3-25 months) and the 1-year intracranial control rate was 67%. The tumor volume reduction was most prominent during the first month with a median reduction rate of 0.717 (range, −0.190 to 1.000). Complete remission was seen in 22 (33%) lesions, and 45 (64%) lesions showed more than 65% reduction in tumor volume. The CN, TC, and HI values were comparable to that of previous studies, and the mean hippocampal dose was 13.65 Gy. No treatment breaks or ≥G3 acute toxicities were observed during or after treatment. The HS-WBRT with SIB in patients with multiple brain metastases was effective and feasible for volume reduction and showed excellent intracranial control.

Stereotactic radiosurgery for brain metastases from hepatocellular carcinoma

The purpose of this study is to investigate the possible role of stereotactic radiosurgery (SRS) in the management of patients with brain metastases from hepatocellular carcinoma (HCC). Thirty-two consecutive patients with 80 brain metastases from HCC were treated with SRS. Twenty-eight (87.5 %) patients were male, and the mean age of the patients was 54 ± 12 years (range 22-73). Twenty-seven (84.4 %) patients were classified as RTOG RPA Class 2. The mean tumor volume was 6.14 ± 11.3 cm(3) (range 0.01-67.3). The mean marginal dose prescribed was 20.1 ± 3.6 Gy (range 10.0-25.0). The median overall survival time after SRS was 11.3 ± 5.8 weeks (95 % CI 0-22.7). A greater total volume of brain metastases (>14 cm(3)) was the only independent prognostic factor (HR = 2.419; 95 % CI 1.040-5.624; p = 0.040). The actuarial control rate of brain metastases was 51.3 % at 4 months after SRS. The prescribed marginal dose (>18 Gy) was significantly related with the actuarial tumor control (HR = 0.254; 95 % CI 0.089-0.725; p = 0.010). The prognosis of patients with brain metastases from HCC is dismal even with the modern technology of radiosurgery. The marginal dose prescribed should be reevaluated to improve upon the current poor local control rates.