Multicenter privacy-preserving model training for deep learning brain metastases autosegmentation.

OBJECTIVES: This work aims to explore the impact of multicenter data heterogeneity on deep learning brain metastases (BM) autosegmentation performance, and assess the efficacy of an incremental transfer learning technique, namely learning without forgetting (LWF), to improve model generalizability without sharing raw data. MATERIALS AND METHODS: A total of six BM datasets from University Hospital Erlangen (UKER), University Hospital Zurich (USZ), Stanford, UCSF, New York University (NYU), and BraTS Challenge 2023 were used. First, the performance of the DeepMedic network for BM autosegmentation was established for exclusive single-center training and mixed multicenter training, respectively. Subsequently privacy-preserving bilateral collaboration was evaluated, where a pretrained model is shared to another center for further training using transfer learning (TL) either with or without LWF. RESULTS: For single-center training, average F1 scores of BM detection range from 0.625 (NYU) to 0.876 (UKER) on respective single-center test data. Mixed multicenter training notably improves F1 scores at Stanford and NYU, with negligible improvement at other centers. When the UKER pretrained model is applied to USZ, LWF achieves a higher average F1 score (0.839) than naive TL (0.570) and single-center training (0.688) on combined UKER and USZ test data. Naive TL improves sensitivity and contouring accuracy, but compromises precision. Conversely, LWF demonstrates commendable sensitivity, precision and contouring accuracy. When applied to Stanford, similar performance was observed. CONCLUSION: Data heterogeneity (e.g., variations in metastases density, spatial distribution, and image spatial resolution across centers) results in varying performance in BM autosegmentation, posing challenges to model generalizability. LWF is a promising approach to peer-to-peer privacy-preserving model training.

A case of complete pathological response after comprehensive treatment in a patient with pulmonary adenocarcinoma with synchronous solitary brain metastasis.

Systemic chemotherapy is the standard treatment for non-small cell lung cancer with distant metastases. However, additional local treatment for brain and thoracic lesions is recommended for patients with synchronous solitary brain metastases (SSBM). We report the case of a 71-year-old male diagnosed with pulmonary adenocarcinoma and SSBM. Pathological examination of the brain metastasis showed positive immunostaining for programmed cell death ligand 1 expression. After four cycles of chemotherapy with immune checkpoint inhibitors, right upper lobectomy with ND2a-1 was performed. Pathological examination revealed complete pathological response, and this patient is expected to experience long-term survival.

Intraoperative radiotherapy after neurosurgical resection of brain metastases as institutional standard treatment- update of the oncological outcome form a single center cohort after 117 procedures.

PURPOSE: Stereotactic radiotherapy (SRT) is the predominant method for the irradiation of resection cavities after resection of brain metastases (BM). Intraoperative radiotherapy (IORT) with 50 kV x-rays is an alternative way to irradiate the resection cavity focally. We have already reported the outcome of our first 40 IORT patients treated until 2020. Since then, IORT has become the predominant cavity treatment in our center due to patients´ choice. METHODS: We retrospectively analyzed the outcomes of all patients who underwent resection of BM and IORT between 2013 and August 2023 at Augsburg University Medical Center (UKA). RESULTS: We identified 105 patients with 117 resected BM treated with 50 kV x-ray IORT. Median diameter of the resected metastases was 3.1 cm (range 1.3 - 7.0 cm). Median applied dose was 20 Gy. All patients received standardized follow-up (FU) including three-monthly MRI of the brain. Mean FU was 14 months, with a median MRI FU for patients alive of nine months. Median overall survival (OS) of all treated patients was 18.2 months (estimated 1-year OS 57.7%). The observed local control (LC) rate of the resection cavity was 90.5% (estimated 1-year LC 84.2%). Distant brain control (DC) was 61.9% (estimated 1-year DC 47.9%). Only 16.2% of all patients needed WBI in the further course of disease. The observed radio necrosis rate was 2.6%. CONCLUSION: After 117 procedures IORT still appears to be a safe and appealing way to perform cavity RT after neurosurgical resection of BM with low toxicity and excellent LC.

Encorafenib and binimetinib followed by radiotherapy for patients with BRAFV600-mutant melanoma and brain metastases (E-BRAIN/GEM1802 phase II study).

BACKGROUND: Encorafenib plus binimetinib (EB) is a standard of care treatment for advanced BRAFV600-mutant melanoma. We assessed efficacy and safety of encorafenib plus binimetinib in patients with BRAFV600-mutant melanoma and brain metastasis (BM) and explored if radiotherapy improves the duration of response. METHODS: E-BRAIN/GEM1802 was a prospective, multicenter, single arm, phase II trial that enrolled patients with melanoma BRAFV600-mutant and BM. Patients received encorafenib 450 mg once daily plus binimetinib 45 mg BID, and those who achieved partial response or stable disease at first tumor assessment were offered radiotherapy. Treatment continued until progression.Primary endpoint was intracranial response rate (icRR) after 2 months of EB, establishing a futility threshold of 60%. RESULTS: The study included 25 patients with no BM symptoms and 23 patients with BM symptoms regardless of using corticosteroids. Among them, 31 patients (64.6%) received sequential radiotherapy. After two months, icRR was 70.8% (95% CI: 55.9-83.1); 10.4% complete response. Median intracranial PFS and OS were 8.5 (95% CI: 6.4-11.8) and 15.9 (95% CI: 10.7-21.4) months, respectively (8.3 months for icPFS and 13.9 months OS for patients receiving RDT). Most common grade 3-4 treatment-related adverse event was alanine aminotransferase (ALT) increased (10.4%). CONCLUSION: Encorafenib plus binimetinib showed promising clinical benefit in terms of icRR, and tolerable safety profile with low frequency of high grade TRAEs, in patients with BRAFV600-mutant melanoma and BM, including those with symptoms and need for steroids. Sequential radiotherapy is feasible but it does not seem to prolong response.

EGFR kinase domain duplication in lung adenocarcinoma with systemic and intracranial response to a double-dose of furmonertinib: a case report and literature review.

Background: EGFR kinase domain duplication (EGFR-KDD) is an infrequent oncogenic driver mutation in lung adenocarcinoma. It may be a potential target benefit from EGFR-tyrosine kinase inhibitors (TKIs) treatment. Case presentation: A 66-year-old Chinese male was diagnosed with lung adenocarcinoma in stage IVb with brain metastases. Next-generation sequencing revealed EGFR-KDD mutation. The patient received furmonertinib 160mg daily for anti-cancer treatment and obtained therapeutic efficacy with partial response (PR). Progression-free survival (PFS) duration from monotherapy was 16 months. With slow progressions, combined radiotherapy and anti-vascular targeted therapy also brought a continuous decrease in the tumors. The patient has an overall survival (OS) duration of more than 22 months and still benefits from double-dose furmonertinib. Conclusions: This report provided direct evidence for the treatment of EGFR-KDD to use furmonertinib. A Large-scale study is needed to confirm this preliminary finding.

Utilizing human cerebral organoids to model breast cancer brain metastasis in culture.

BACKGROUND: Metastasis, the spread, and growth of malignant cells at secondary sites within a patient's body, accounts for over 90% of cancer-related mortality. Breast cancer is the most common tumor type diagnosed and the leading cause of cancer lethality in women in the United States. It is estimated that 10-16% breast cancer patients will have brain metastasis. Current therapies to treat patients with breast cancer brain metastasis (BCBM) remain palliative. This is largely due to our limited understanding of the fundamental molecular and cellular mechanisms through which BCBM progresses, which represents a critical barrier for the development of efficient therapies for affected breast cancer patients. METHODS: Previous research in BCBM relied on co-culture assays of tumor cells with rodent neural cells or rodent brain slice ex vivo. Given the need to overcome the obstacle for human-relevant host to study cell-cell communication in BCBM, we generated human embryonic stem cell-derived cerebral organoids to co-culture with human breast cancer cell lines. We used MDA-MB-231 and its brain metastatic derivate MDA-MB-231 Br-EGFP, other cell lines of MCF-7, HCC-1806, and SUM159PT. We leveraged this novel 3D co-culture platform to investigate the crosstalk of human breast cancer cells with neural cells in cerebral organoid. RESULTS: We found that MDA-MB-231 and SUM159PT breast cancer cells formed tumor colonies in human cerebral organoids. Moreover, MDA-MB-231 Br-EGFP cells showed increased capacity to invade and expand in human cerebral organoids. CONCLUSIONS: Our co-culture model has demonstrated a remarkable capacity to discern the brain metastatic ability of human breast cancer cells in cerebral organoids. The generation of BCBM-like structures in organoid will facilitate the study of human tumor microenvironment in culture.

Predictors for the Differentiation between Glioblastoma, Primary Central Nervous System Lymphoma, and Metastasis in Patients with a Solitary Enhancing Intracranial Mass.

Introduction Differentiation between glioblastoma (GBM), primary central nervous system lymphoma (PCNSL), and metastasis is important in decision-making before surgery. However, these malignant brain tumors have overlapping features. This study aimed to identify predictors differentiating between GBM, PCNSL, and metastasis. Materials and Methods Patients with a solitary intracranial enhancing tumor and a histopathological diagnosis of GBM, PCNSL, or metastasis were investigated. All patients with intracranial lymphoma had PCNSL without extracranial involvement. Demographic, clinical, and radiographic data were analyzed to determine their associations with the tumor types. Results The predictors associated with GBM were functional impairment ( p = 0.001), large tumor size ( p < 0.001), irregular tumor margin ( p < 0.001), heterogeneous contrast enhancement ( p < 0.001), central necrosis ( p < 0.001), intratumoral hemorrhage ( p = 0.018), abnormal flow void ( p < 0.001), and hypodensity component on noncontrast cranial computed tomography (CT) scan ( p < 0.001). The predictors associated with PCNSL comprised functional impairment ( p = 0.005), deep-seated tumor location ( p = 0.006), homogeneous contrast enhancement ( p < 0.001), absence of cystic appearance ( p = 0.008), presence of hypointensity component on precontrast cranial T1-weighted magnetic resonance imaging (MRI; p = 0.027), and presence of isodensity component on noncontrast cranial CT ( p < 0.008). Finally, the predictors for metastasis were an infratentorial ( p < 0.001) or extra-axial tumor location ( p = 0.035), smooth tumor margin ( p < 0.001), and presence of isointensity component on cranial fluid-attenuated inversion recovery MRI ( p = 0.047). Conclusion These predictors may be used to differentiate between GBM, PCNSL, and metastasis, and they are useful in clinical management.

Proteomics shows that brain metastases of lung adenocarcinoma overexpress ribosomal proteins in response to gamma knife radiosurgery.

Gamma knife radiosurgery (GKRS) is recommended as the first-line treatment for brain metastases of lung adenocarcinoma (LUAD) in many guidelines, but its specific mechanism is unclear. We aimed to study the changes in the proteome of brain metastases of LUAD in response to the hyperacute phase of GKRS and further explore the mechanism of differentially expressed proteins (DEPs). Cancer tissues were collected from a clinical trial for neoadjuvant stereotactic radiosurgery before surgical resection of large brain metastases (ChiCTR2000038995). Five brain metastasis tissues of LUAD were collected within 24 h after GKRS. Five brain metastasis tissues without radiotherapy were collected as control samples. Proteomics analysis showed that 163 proteins were upregulated and 25 proteins were downregulated. GO and KEGG enrichment analyses showed that the DEPs were closely related to ribosomes. Fifty-three of 70 ribosomal proteins were significantly overexpressed, while none of them were underexpressed. The risk score constructed from 7 upregulated ribosomal proteins (RPL4, RPS19, RPS16, RPLP0, RPS2, RPS26 and RPS25) was an independent risk factor for the survival time of LUAD patients. Overexpression of ribosomal proteins may represent a desperate response to lethal radiotherapy. We propose that targeted inhibition of these ribosomal proteins may enhance the efficacy of GKRS.

Differentiation of glioma and solitary brain metastasis: a multi-parameter magnetic resonance imaging study using histogram analysis.

BACKGROUND: Differentiation of glioma and solitary brain metastasis (SBM), which requires biopsy or multi-disciplinary diagnosis, remains sophisticated clinically. Histogram analysis of MR diffusion or molecular imaging hasn't been fully investigated for the differentiation and may have the potential to improve it. METHODS: A total of 65 patients with newly diagnosed glioma or metastases were enrolled. All patients underwent DWI, IVIM, and APTW, as well as the T1W, T2W, T2FLAIR, and contrast-enhanced T1W imaging. The histogram features of apparent diffusion coefficient (ADC) from DWI, slow diffusion coefficient (Dslow), perfusion fraction (frac), fast diffusion coefficient (Dfast) from IVIM, and MTRasym@3.5ppm from APTWI were extracted from the tumor parenchyma and compared between glioma and SBM. Parameters with significant differences were analyzed with the logistics regression and receiver operator curves to explore the optimal model and compare the differentiation performance. RESULTS: Higher ADCkurtosis (P = 0.022), frackurtosis (P<0.001),and fracskewness (P<0.001) were found for glioma, while higher (MTRasym@3.5ppm)10 (P = 0.045), frac10 (P<0.001),frac90 (P = 0.001), fracmean (P<0.001), and fracentropy (P<0.001) were observed for SBM. frackurtosis (OR = 0.431, 95%CI 0.256-0.723, P = 0.002) was independent factor for SBM differentiation. The model combining (MTRasym@3.5ppm)10, frac10, and frackurtosis showed an AUC of 0.857 (sensitivity: 0.857, specificity: 0.750), while the model combined with frac10 and frackurtosis had an AUC of 0.824 (sensitivity: 0.952, specificity: 0.591). There was no statistically significant difference between AUCs from the two models. (Z = -1.14, P = 0.25). CONCLUSIONS: The frac10 and frackurtosis in enhanced tumor region could be used to differentiate glioma and SBM and (MTRasym@3.5ppm)10 helps improving the differentiation specificity.

A clinically compatible in vitro drug-screening platform identifies therapeutic vulnerabilities in primary cultures of brain metastases.

PURPOSE: Brain metastases represent the most common intracranial tumors in adults and are associated with a poor prognosis. We used a personalized in vitro drug screening approach to characterize individual therapeutic vulnerabilities in brain metastases. METHODS: Short-term cultures of cancer cells isolated from brain metastasis patients were molecularly characterized using next-generation sequencing and functionally evaluated using high-throughput in vitro drug screening to characterize pharmacological treatment sensitivities. RESULTS: Next-generation sequencing identified matched genetic alterations in brain metastasis tissue samples and corresponding short-term cultures, suggesting that short-term cultures of brain metastases are suitable models for recapitulating the genetic profile of brain metastases that may determine their sensitivity to anti-cancer drugs. Employing a high-throughput in vitro drug screening platform, we successfully screened the cultures of five brain metastases for response to 267 anticancer compounds and related drug response to genetic data. Among others, we found that targeted treatment with JAK3, HER2, or FGFR3 inhibitors showed anti-cancer effects in individual brain metastasis cultures. CONCLUSION: Our preclinical study provides a proof-of-concept for combining molecular profiling with in vitro drug screening for predictive evaluation of therapeutic vulnerabilities in brain metastasis patients. This approach could advance the use of patient-derived cancer cells in clinical practice and might eventually facilitate decision-making for personalized drug treatment.

A Nomogram Based on Clinicopathological Characteristics for Estimating the Risk of Brain Metastasis from Advanced Gastric Cancer: A Multi-Center Retrospective Clinical Study.

Purpose: Although brain metastasis (BM) from gastric cancer (GC) is relatively uncommon, its incidence has been increasing owing to advancements in treatment modalities. Unfortunately, patients diagnosed with BM from gastric cancer have poor life expectancy. Our study aims to establish a predictive model for brain metastasis in advanced gastric cancer patients, thus enabling the timely diagnosis of brain metastasis. Patients and Methods: The clinicopathological features of a cohort which included 40 GC patients with brain metastasis, 32 of whom from the First Affiliated Hospital of Nanchang University, 2 from Gaoxin Branch of the First Affiliated Hospital of Nanchang University, remaining 6 from Anyang District Hospital, and 80 non-metastatic advanced GC patients from the First Affiliated Hospital of Nanchang University between 2018 and 2022. Data were retrospectively analyzed. Results: Age, tumor size, differentiation, lymph node grade, tumor location, Lauren classification, liver metastasis, carbohydrate antigen 199 (CA199), lactate dehydrogenase (LDH), and human epidermal growth factor receptor 2 (Her-2) were associated with BM. A nomogram integrated with nine risk factors (tumor size, differentiation, lymph node grade, tumor location, Lauren classification, liver metastasis, CA-199, LDH, and Her-2) showed good performance (Area Under Curve 0.95, 95% CI: 0.91-0.98). Conclusion: We developed and validated a nomogram that achieved individualized prediction of the possibility of BM from GC. This model enables personalized imaging review schedules for timely brain metastasis detection in advanced gastric cancer patients.

A Rare Case of Thoracic SMARCA4-Deficient Undifferentiated Tumor With Diffuse Brain Metastasis.

Thoracic SMARCA4-deficient undifferentiated tumor (SMARCA4-UT) is a recently described rare and aggressive malignancy characterized by undifferentiated cell morphology and the loss of the Brahma-related gene 1 (BRG1) protein. Its pathogenesis involves mutational loss of SMARCA4 gene expression, which encodes the BRG1 protein that serves as one of the catalytic subunits of the SWItch/Sucrose Non-Fermentable (SWI/SNF) chromatin remodeling complex. This malignancy of the thorax predominantly affects middle-aged male smokers and commonly metastasizes to lymph nodes, bones, adrenal glands, liver, gastrointestinal tract, central nervous system, and kidney. Cases of brain metastasis have been reported but are less common. We report a case of this tumor initially presenting with diffuse brain metastasis in a 55-year-old male with a significant smoking history. We reviewed the current literature on the diagnostic and therapeutic challenges posed by this highly aggressive thoracic tumor.

Diffusion Tensor Imaging Biomarker Alterations in Brain Metastases and Comparable Tumors: A Systematic Review of DTI and Tractography Findings.

INTRODUCTION: Brain metastases (BM) are the most frequent tumors of the central nervous system (CNS). Diffusion tensor imaging (DTI) is a magnetic resonance imaging (MRI) technique that provides insights into brain microstructural alterations and tensor metrics, and generates tractography to visualize white matter (WM) fiber tracts based on diffusion directionality. This systematic review assessed evidence from DTI biomarker alterations in BMs and comparable tumors such as glioblastoma (GBM). METHODS: PubMed, Scopus, and Web of Science were searched, published between January 2000 and August 2023. The key inclusion criteria were studies reporting DTI metrics in BMs and comparisons with other tumors. Data on study characteristics, tumor types, sample details, and main DTI findings were extracted. RESULTS: 57 studies with 1592 BM patients and 1578 comparable brain tumors were included. Peritumoral fractional anisotropy (FA) consistently differentiates BMs from primary brain tumors, whereas intratumoral FA shows limited discriminatory power. Mean diffusivity (MD) increased in BMs versus comparators. Intratumoral metrics were less consistent, but revealed differences in BM origin. Axial and radial diffusivity (AD and RD, respectively) have provided insights into the effects of radiation, tumor origin, and infiltration. AD/RD differentiated tumor infiltration from vasogenic edema. Tractography revealed anatomical relationships between WM tracts (WMTs) and BMs. In addition, tractography-guided BM surgery and radiotherapy planning are required. Machine learning models incorporating DTI biomarkers/metrics accurately classified BMs versus comparators and improved diagnostic classification. CONCLUSION: DTI metrics provides non-invasive biomarkers for distinguishing BMs from other tumors and predicting outcomes. Key metrics included peritumoral FA and MD.

Translation and validation of the Neurological Assessment in Neuro-Oncology scale to Brazilian Portuguese.

Introduction: The Neurological Assessment for Neuro-Oncology (NANO) scale was elaborated to assess neurologic function in integration with radiological criteria to evaluate neuro-oncological patients in clinical setting and enable the standardization of neurological assessment in clinical trials. The objective of this study is the translation to Brazilian Portuguese and transcultural adaptation of NANO scale in patients with the diagnosis of glioblastoma, brain metastasis and low-grade glioma. Methods: Patients with diagnosis of glioblastoma, brain metastasis, and low-grade glioma were prospectively evaluated between July 2019 and July 2021. The process of translating and cross-culturally adapting the NANO scale included: translation from English to Portuguese, synthesis and initial revision by an expert committee, back-translation from Portuguese to English, a second revision by the expert committee, and the application of the NANO scale. Regarding the reliability of the NANO scale, Cronbach's alpha was employed to measure the internal consistency of all scale items and assess the impact of item deletion. Additionally, Spearman's correlation test was used to evaluate the convergent validity between the NANO scale and Karnofsky Performance Scale (KPS). Results: One hundred and seventy-four patients were evaluated. A statistically significant inverse relation (p < 0.001) between KPS and NANO scale was founded. The Cronbach's alpha values founded for NANO scale were 0.803 for glioblastoma, 0.643 for brain metastasis, and 0.482 for low grade glioma. Discussion: The NANO scale Brazilian Portuguese version proves to be reproducible and valid to evaluate neuro-oncological patients with glioblastoma and brain metastasis, presenting a strong correlation with KPS scale. Further studies are warranted to assess the validity and reliability of the scale in patients diagnosed with low-grade glioma.

Predictive risk score for isolated brain metastasis in non-small cell lung cancer.

Background: Brain metastasis is common with non-small cell lung cancer (NSCLC). Patients with some early-stage cancers don't benefit from routine brain imaging. Currently clinical stage alone is used to justify additional brain imaging. Other clinical and demographic characteristics may be associated with isolated brain metastasis (IBM). We aimed to define the most salient clinical features associated with synchronous IBM, hypothesizing that clinical and demographic factors could be used to determine the risk of brain metastasis. Methods: The National Cancer Database was used to identify patients with NSCLC from 2016-2020. Primary outcome was the presence of IBM relative to patients without evidence of any metastasis. Cohorts were divided into test and validation. The test cohort was used to identify risk factors for IBM using multivariable logistic regression. Using the regression, a scoring system was created to estimate the rate of synchronous IBM. The accuracy of the scoring system was evaluated with receiver operating characteristic (ROC) analysis using the validation cohort. Results: Study population consisted of 396,113 patients: 25,907 IBM and 370,206 without metastatic disease. IBM was associated with age, clinical T stage, clinical N stage, Charlson/Deyo comorbidity score, histology, and grade. A scoring system using these factors showed excellent accuracy in the test and validation cohort in ROC analysis (0.806 and 0.805, respectively). Conclusions: Clinical and demographic characteristics can be used to stratify the risk of IBM among patients with NSCLC and provide an evidence-based method to identify patients who require dedicated brain imaging in the absence of other metastatic disease.

Differentiation of glioblastoma from solitary brain metastasis using deep ensembles: Empirical estimation of uncertainty for clinical reliability.

BACKGROUND AND OBJECTIVES: To develop a clinically reliable deep learning model to differentiate glioblastoma (GBM) from solitary brain metastasis (SBM) by providing predictive uncertainty estimates and interpretability. METHODS: A total of 469 patients (300 GBM, 169 SBM) were enrolled in the institutional training set. Deep ensembles based on DenseNet121 were trained on multiparametric MRI. The model performance was validated in the external test set consisting of 143 patients (101 GBM, 42 SBM). Entropy values for each input were evaluated for uncertainty measurement; based on entropy values, the datasets were split to high- and low-uncertainty groups. In addition, entropy values of out-of-distribution (OOD) data from unknown class (257 patients with meningioma) were compared to assess uncertainty estimates of the model. The model interpretability was further evaluated by localization accuracy of the model. RESULTS: On external test set, the area under the curve (AUC), accuracy, sensitivity and specificity of the deep ensembles were 0.83 (95 % confidence interval [CI] 0.76-0.90), 76.2 %, 54.8 % and 85.2 %, respectively. The performance was higher in the low-uncertainty group than in the high-uncertainty group, with AUCs of 0.91 (95 % CI 0.83-0.98) and 0.58 (95 % CI 0.44-0.71), indicating that assessment of uncertainty with entropy values ascertained reliable prediction in the low-uncertainty group. Further, deep ensembles classified a high proportion (90.7 %) of predictions on OOD data to be uncertain, showing robustness in dataset shift. Interpretability evaluated by localization accuracy provided further reliability in the "low-uncertainty and high-localization accuracy" subgroup, with an AUC of 0.98 (95 % CI 0.95-1.00). CONCLUSIONS: Empirical assessment of uncertainty and interpretability in deep ensembles provides evidence for the robustness of prediction, offering a clinically reliable model in differentiating GBM from SBM.

Comprehensive analysis of stereotactic Radiosurgery outcomes in triple-negative breast cancer patients with brain metastases: The influence of immunotherapy and prognostic factors.

INTRODUCTION: Breast cancer stands as the second most common solid tumors with a propensity for brain metastasis. Among metastatic breast cancer cases, the brain metastasis incidence ranges from 10 % to 30 %, with triple-negative breast cancer (TNBC) displaying a heightened risk and poorer prognosis. SRS has emerged as an effective local treatment modality for brain metastases; however, data on its outcomes specifically in pure triple-negative subtype remain scarce. METHOD: We retrospectively reviewed the electronic medical records of all brain metastasis (BM) TNBC patients treated with SRS. Patient, tumour characteristics and treatment details data were collected. This retrospective cohort study aimed to evaluate local control (LC), distant brain metastasis free survival (DBMFS), and overall survival (OS) outcomes in TNBC patients undergoing SRS for brain metastases while identifying potential prognostic factors. RESULT: Forty-three patients with TNBC and brain metastases treated with SRS between January 2017 and 2023 were included. The study found rates of LC (99 % at 1 year) and DBMFS (76 % at 1 year) after SRS, with brain metastasis count (p = 0,003) and systemic treatment modality (p = 0,001) being significant predictors of DBMFS. The median OS following SRS was 19.5 months, with neurological deficit (p = 0.003) and systemic treatment modality (p = 0.019) identified as significant predictors of OS. CONCLUSION: SRS demonstrates favourable outcomes in terms of local control and distant brain metastasis-free survival in TNBC. Neurological deficit and systemic treatment significantly influence overall survival, emphasizing the importance of personalized treatment approaches and (magnetic resonance imaging) MRI surveillance based on these factors.

Melanoma Management: Exploring Staging, Prognosis, and Treatment Innovations.

Melanoma, a malignant neoplasm originating from melanocytes, stands as one of the most prevalent cancers globally, ranking fifth in terms of estimated new cases in recent years. Its aggressive nature and propensity for metastasis pose significant challenges in oncology. Recent advancements have led to a notable shift towards targeted therapies, driven by a deeper understanding of cutaneous tumor pathogenesis. Immunotherapy and tyrosine kinase inhibitors have emerged as promising strategies, demonstrating the potential to improve clinical outcomes across all disease stages, including neoadjuvant, adjuvant, and metastatic settings. Notably, there has been a groundbreaking development in the treatment of brain metastasis, historically associated with poor prognosis in oncology but showcasing impressive results in melanoma patients. This review article provides a comprehensive synthesis of the most recent knowledge on staging and prognostic factors while highlighting emerging therapeutic modalities, with a particular focus on neoadjuvant and adjuvant strategies, notably immunotherapy and targeted therapies, including the ongoing trials.

Magnetic Particle Imaging Reveals that Iron-Labeled Extracellular Vesicles Accumulate in Brains of Mice with Metastases.

The incidence of breast cancer remains high worldwide and is associated with a significant risk of metastasis to the brain that can be fatal; this is due, in part, to the inability of therapeutics to cross the blood-brain barrier (BBB). Extracellular vesicles (EVs) have been found to cross the BBB and further have been used to deliver drugs to tumors. EVs from different cell types appear to have different patterns of accumulation and retention as well as the efficiency of bioactive cargo delivery to recipient cells in the body. Engineering EVs as delivery tools to treat brain metastases, therefore, will require an understanding of the timing of EV accumulation and their localization relative to metastatic sites. Magnetic particle imaging (MPI) is a sensitive and quantitative imaging method that directly detects superparamagnetic iron. Here, we demonstrate MPI as a novel tool to characterize EV biodistribution in metastatic disease after labeling EVs with superparamagnetic iron oxide (SPIO) nanoparticles. Iron-labeled EVs (FeEVs) were collected from iron-labeled parental primary 4T1 tumor cells and brain-seeking 4T1BR5 cells, followed by injection into the mice with orthotopic tumors or brain metastases. MPI quantification revealed that FeEVs were retained for longer in orthotopic mammary carcinomas compared to SPIOs. MPI signal due to iron could only be detected in brains of mice bearing brain metastases after injection of FeEVs, but not SPIOs, or FeEVs when mice did not have brain metastases. These findings indicate the potential use of EVs as a therapeutic delivery tool in primary and metastatic tumors.

Predicting Tumor Dynamics Post-Staged GKRS: Machine Learning Models in Brain Metastases Prognosis.

This study assesses the predictive performance of six machine learning models and a 1D Convolutional Neural Network (CNN) in forecasting tumor dynamics within three months following Gamma Knife radiosurgery (GKRS) in 77 brain metastasis (BM) patients. The analysis meticulously evaluates each model before and after hyperparameter tuning, utilizing accuracy, AUC, and other metrics derived from confusion matrices. The CNN model showcased notable performance with an accuracy of 98% and an AUC of 0.97, effectively complementing the broader model analysis. Initial findings highlighted that XGBoost significantly outperformed other models with an accuracy of 0.95 and an AUC of 0.95 before tuning. Post-tuning, the Support Vector Machine (SVM) demonstrated the most substantial improvement, achieving an accuracy of 0.98 and an AUC of 0.98. Conversely, XGBoost showed a decline in performance after tuning, indicating potential overfitting. The study also explores feature importance across models, noting that features like "control at one year", "age of the patient", and "beam-on time for volume V1 treated" were consistently influential across various models, albeit their impacts were interpreted differently depending on the model's underlying mechanics. This comprehensive evaluation not only underscores the importance of model selection and hyperparameter tuning but also highlights the practical implications in medical diagnostic scenarios, where the accuracy of positive predictions can be crucial. Our research explores the effects of staged Gamma Knife radiosurgery (GKRS) on larger tumors, revealing no significant outcome differences across protocols. It uniquely considers the impact of beam-on time and fraction intervals on treatment efficacy. However, the investigation is limited by a small patient cohort and data from a single institution, suggesting the need for future multicenter research.