Histopathologic diagnosis of brain metastases: current trends in management and future considerations

Refining Lung Cancer Brain Metastasis Models for Spatiotemporal Dynamic Research and Personalized Therapy

Lung cancer brain metastasis (LCBM) is a major contributor to cancer-related mortality, with a median survival of 8-16 months following diagnosis, despite advances in therapeutic strategies. The development of clinically relevant animal models is crucial for understanding the metastatic cascade and assessing therapies that can penetrate the blood-brain barrier (BBB). This review critically evaluates five primary LCBM modeling approaches-orthotopic implantation, intracardiac injection, stereotactic intracranial injection, carotid artery injection, and tail vein injection-focusing on their clinical applicability. We systematically compare their ability to replicate human metastatic pathophysiology and highlight emerging technologies for personalized therapy screening. Additionally, we analyze breakthrough strategies in central nervous system (CNS)-targeted drug delivery, including microparticle targeted delivery systems designed to enhance brain accumulation. By incorporating advances in single-cell omics and AI-driven metastasis prediction, this work provides a roadmap for the next generation of LCBM models, aimed at bridging preclinical and clinical research.

Pathological diagnosis of central nervous system tumours in adults: what's new?

In the course of the last decade, the pathological diagnosis of many tumours of the central nervous system (CNS) has transitioned from a purely histological to a combined histological and molecular approach, resulting in a more precise 'histomolecular diagnosis'. Unfortunately, translation of this refinement in CNS tumour diagnostics into more effective treatment strategies is lagging behind. There is hope though that incorporating the assessment of predictive markers in the pathological evaluation of CNS tumours will help to improve this situation. The present review discusses some novel aspects with regard to the pathological diagnosis of the most common CNS tumours in adults. After a brief update on recognition of clinically meaningful subgroups in adult-type diffuse gliomas and the value of assessing predictive markers in these tumours, more detailed information is provided on predictive markers of (potential) relevance for immunotherapy especially for glioblastomas, IDH-wildtype. Furthermore, recommendations for improved grading of meningiomas by using molecular markers are briefly summarised, and an overview is given on (predictive) markers of interest in metastatic CNS tumours. In the last part of this review, some 'emerging new CNS tumour types' that may occur especially in adults are presented in a table. Hopefully, this review provides useful information on 'what's new' for practising pathologists diagnosing CNS tumours in adults.

Radiomics based on brain-to-tumor interface enables prediction of metastatic tumor type of brain metastasis: a proof-of-concept study

BACKGROUND

Early and accurate identification of the metastatic tumor types of brain metastasis (BM) is essential for appropriate treatment and management.

METHODS

A total of 450 patients were enrolled from two centers as a primary cohort who carry 764 BMs originated from non-small cell lung cancer (NSCLC, patient = 173, lesion = 187), small cell lung cancer (SCLC, patient = 84, lesion = 196), breast cancer (BC, patient = 119, lesion = 200), and gastrointestinal cancer (GIC, patient = 74, lesion = 181). A third center enrolled 28 patients who carry 67 BMs (NSCLC = 24, SCLC = 22, BC = 10, and GIC = 11) to form an external test cohort. All patients received contrast-enhanced T1-weighted (T1CE) and T2-weighted (T2W) MRI scans at 3.0 T before treatment. Radiomics features were calculated from BM and brain-to-tumor interface (BTI) region in the MRI image and screened using least absolute shrinkage and selection operator (LASSO) to construct the radiomics signature (RS). Volume of peritumor edema (VPE) was calculated and combined with RS to create a joint model. Performance of the models was assessed by receiver operating characteristic (ROC).

RESULTS

The BTI-based RS showed better performance compared to BM-based RS. The combined models integrating BTI features and VPE can improve identification performance in AUCs in the training (LC/NLC vs. SCLC/NSCLC vs. BC/GIC, 0.803 vs. 0.949 vs. 0.918), internal validation (LC/NLC vs. SCLC/NSCLC vs. BC/GIC, 0.717 vs. 0.854 vs. 0.840), and external test (LC/NLC vs. SCLC/NSCLC vs. BC/GIC, 0.744 vs. 0.839 vs. 0.800) cohorts.

CONCLUSION

This study indicated that BTI-based radiomics features and VPE are associated with the metastatic tumor types of BM.

Utilizing machine-learning techniques on MRI radiomics to identify primary tumors in brain metastases

Objective

To develop a machine learning-based clinical and/or radiomics model for predicting the primary site of brain metastases using multiparametric magnetic resonance imaging (MRI).

Materials and methods

A total of 202 patients (87 males, 115 females) with 439 brain metastases were retrospectively included, divided into training sets (brain metastases of lung cancer [BMLC] n = 194, brain metastases of breast cancer [BMBC] n = 108, brain metastases of gastrointestinal tumor [BMGiT] n = 48) and test sets (BMLC n = 50, BMBC n = 27, BMGiT n = 12). A total of 3,404 quantitative image features were obtained through semi-automatic segmentation from MRI images (T1WI, T2WI, FLAIR, and T1-CE). Intra-class correlation coefficient (ICC) was used to examine segmentation stability between two radiologists. Radiomics features were selected using analysis of variance (ANOVA), recursive feature elimination (RFE), and Kruskal-Wallis test. Three machine learning classifiers were used to build the radiomics model, which was validated using five-fold cross-validation on the training set. A comprehensive model combining radiomics and clinical features was established, and the diagnostic performance was compared by area under the curve (AUC) and evaluated in an independent test set.

Results

The radiomics model differentiated BMGiT from BMLC (13 features, AUC = 0.915 ± 0.071) or BMBC (20 features, AUC = 0.954 ± 0.064) with high accuracy, while the classification between BMLC and BMBC was unsatisfactory (11 features, AUC = 0.729 ± 0.114). However, the combined model incorporating radiomics and clinical features improved the predictive performance, with AUC values of 0.965 for BMLC vs. BMBC, 0.991 for BMLC vs. BMGiT, and 0.935 for BMBC vs. BMGiT.

Conclusion

The machine learning-based radiomics model demonstrates significant potential in distinguishing the primary sites of brain metastases, and may assist screening of primary tumor when brain metastasis is suspected whereas history of primary tumor is absent.

Application of Machine Learning for Classification of Brain Tumors: A Systematic Review and Meta-Analysis

BACKGROUND

Classifying brain tumors accurately is crucial for treatment and prognosis. Machine learning (ML) shows great promise in improving tumor classification accuracy. This study evaluates ML algorithms for differentiating various brain tumor types.

METHODS

A systematic review and meta-analysis were conducted, searching PubMed, Embase, and Web of Science up to March 14, 2023. Studies that only investigated image segmentation accuracy or brain tumor detection instead of classification were excluded. We extracted binary diagnostic accuracy data, constructing contingency tables to derive sensitivity and specificity.

RESULTS

Fifty-one studies were included. The pooled area under the curve for glioblastoma versus lymphoma and low-grade versus high-grade gliomas were 0.99 (95% confidence interval [CI]: 0.98-1.00) and 0.89, respectively. The pooled sensitivity and specificity for benign versus malignant tumors were 0.90 (95% CI: 0.85-0.93) and 0.93 (95% CI: 0.90-0.95), respectively. The pooled sensitivity and specificity for low-grade versus high-grade gliomas were 0.99 (95% CI: 0.97-1.00) and 0.94, (95% CI: 0.79-0.99), respectively. Primary versus metastatic tumor identification yields sensitivity and specificity of 0.89, (95% CI: 0.83-0.93) and 0.87 (95% CI: 0.82-0.91), correspondingly. The differentiation of gliomas from pituitary tumors yielded the highest results among primary brain tumor classifications: sensitivity of 0.99 (95% CI: 0.99-1.00) and specificity of 0.99 (95% CI: 0.98-1.00).

CONCLUSIONS

ML demonstrated excellent performance in classifying brain tumor images, with near-maximum area under the curves, sensitivity, and specificity.

Using Radiomics to Differentiate Brain Metastases From Lung Cancer Versus Breast Cancer, Including Predicting Epidermal Growth Factor Receptor and human Epidermal Growth Factor Receptor 2 Status

OBJECTIVE

We evaluated the feasibility of using multiregional radiomics to identify brain metastasis (BM) originating from lung adenocarcinoma (LA) and breast cancer (BC) and assess the epidermal growth factor receptor (EGFR) mutation and human epidermal growth factor receptor 2 (HER2) status.

METHODS

Our experiment included 160 patients with BM originating from LA (n = 70), BC (n = 67), and other tumor types (n = 23), between November 2017 and December 2021. All patients underwent contrast-enhanced T1- and T2-weighted magnetic resonance imaging (MRI) scans. A total of 1967 quantitative MRI features were calculated from the tumoral active area and peritumoral edema area and selected using least absolute shrinkage and selection operator regression with 5-fold cross-validation. We constructed radiomic signatures (RSs) based on the most predictive features for preoperative assessment of the metastatic origins, EGFR mutation, and HER2 status. Prediction performance of the constructed RSs was evaluated based on the receiver operating characteristic curve analysis.

RESULTS

The developed multiregion RSs generated good area under the receiver operating characteristic curve (AUC) for identifying the LA and BC origin in the training (AUCs, RS-LA vs RS-BC, 0.767 vs 0.898) and validation (AUCs, RS-LA vs RS-BC, 0.778 and 0.843) cohort and for predicting the EGFR and HER2 status in the training (AUCs, RS-EGFR vs RS-HER2, 0.837 vs 0.894) and validation (AUCs, RS-EGFR vs RS-HER2, 0.729 vs 0.784) cohorts.

CONCLUSIONS

Our results revealed associations between brain MRI-based radiomics and their metastatic origins, EGFR mutations, and HER2 status. The developed multiregion combined RSs may be considered noninvasive predictive markers for planning early treatment for BM patients.

Novel radiomic features versus deep learning: differentiating brain metastases from pathological lung cancer types in small datasets

OBJECTIVE

Accurate diagnosis and early treatment are crucial for survival in patients with brain metastases. This study aims to expand the capability of radiomics-based classification algorithms with novel features and compare results with deep learning-based algorithms to differentiate the subtypes of lung cancer from MRI of metastatic lesions in the brain.

METHODS

This study includes 75 small cell lung carcinoma, 72 squamous cell carcinoma, and 75 adenocarcinoma segments. For the radiomics-based algorithm, novel features from the original Laplacian of Gaussian filtered and two-dimensional wavelet transformed images were extracted, and a new three-stage feature selection algorithm was proposed for feature selection. Two classification methods were applied to images to identify the subtypes of lung cancer. Additionally, EfficientNet and ResNet with transfer learning were used as classifiers to compare the results of the proposed algorithm.

RESULTS

The sensitivity and specificity values of the radiomics-based classifier are 94.44 and 95.33%, and for the second classifier are 87.67% and 92.62%, respectively. Besides, a one-vs-all approach comparison was made utilizing two deep learning-based classifiers; The sensitivity and specificity values of 94.29 and 94.08% were obtained from ResNet-50. Moreover, mentioned metrics for EfficientNet-b0 are 92.86 and 93.42%. Furthermore, the accuracies of two radiomics-based and two deep learning-based models were 84.68%, 78.37%, 92.34%, and 90.99%, respectively for one-vs-one approach.

CONCLUSION

The results suggest that the proposed radiomics-based algorithm is a helpful diagnostic assistant to improve decision-making for treating patients with brain metastases in small datasets.

ADVANCES IN KNOWLEDGE

Firstly, the proposed method of this study extracts novel features from transformations of the original images, such as wavelet and Laplacian of Gaussian filter for the first time in literature. Secondly, this is the first study that investigates the classification performance of the shallow and deep learning approaches to identify subtypes of lung cancer.

DenseNet_ HybWWoA: A DenseNet-Based Brain Metastasis Classification with a Hybrid Metaheuristic Feature Selection Strategy

Brain metastases (BM) are the most severe consequence of malignancy in the brain, resulting in substantial illness and death. The most common primary tumors that progress to BM are lung, breast, and melanoma. Historically, BM patients had poor clinical outcomes, with limited treatment options including surgery, stereotactic radiation therapy (SRS), whole brain radiation therapy (WBRT), systemic therapy, and symptom control alone. Magnetic Resonance Imaging (MRI) is a valuable tool for detecting cerebral tumors, though it is not infallible, as cerebral matter is interchangeable. This study offers a novel method for categorizing differing brain tumors in this context. This research additionally presents a combination of optimization algorithms called the Hybrid Whale and Water Waves Optimization Algorithm (HybWWoA), which is used to identify features by reducing the size of recovered features. This algorithm combines whale optimization and water waves optimization. The categorization procedure is consequently carried out using a DenseNet algorithm. The suggested cancer categorization method is evaluated on a number of factors, including precision, specificity, and sensitivity. The final assessment findings showed that the suggested approach exceeded the authors' expectations, with an F1-score of 97% and accuracy, precision, memory, and recollection of 92.1%, 98.5%, and 92.1%, respectively.

A deep learning approach with subregion partition in MRI image analysis for metastatic brain tumor

Purpose

To propose a deep learning network with subregion partition for predicting metastatic origins and EGFR/HER2 status in patients with brain metastasis.

Methods

We retrospectively enrolled 140 patients with clinico-pathologically confirmed brain metastasis originated from primary NSCLC (n = 60), breast cancer (BC, n = 60) and other tumor types (n = 20). All patients underwent contrast-enhanced brain MRI scans. The brain metastasis was subdivided into phenotypically consistent subregions using patient-level and population-level clustering. A residual network with a global average pooling layer (RN-GAP) was proposed to calculate deep learning-based features. Features from each subregion were selected with least absolute shrinkage and selection operator (LASSO) to build logistic regression models (LRs) for predicting primary tumor types (LR-NSCLC for the NSCLC origin and LR-BC for the BC origin), EGFR mutation status (LR-EGFR) and HER2 status (LR-HER2).

Results

The brain metastasis can be partitioned into a marginal subregion (S1) and an inner subregion (S2) in the MRI image. The developed models showed good predictive performance in the training (AUCs, LR-NSCLC vs. LR-BC vs. LR-EGFR vs. LR-HER2, 0.860 vs. 0.909 vs. 0.850 vs. 0.900) and validation (AUCs, LR-NSCLC vs. LR-BC vs. LR-EGFR vs. LR-HER2, 0.819 vs. 0.872 vs. 0.750 vs. 0.830) set.

Conclusion

Our proposed deep learning network with subregion partitions can accurately predict metastatic origins and EGFR/HER2 status of brain metastasis, and hence may have the potential to be non-invasive and preoperative new markers for guiding personalized treatment plans in patients with brain metastasis.

Raman hyperspectral imaging coupled to three-dimensional discriminant analysis: Classification of meningiomas brain tumour grades

Meningiomas remains a clinical dilemma. They are the commonest "benign" types of brain tumours and, although being typically benign, they are divided into three WHO grades categories (I, II and III) which are associated with the tumour growth rate and likelihood of recurrence. Recurrence depends on extend of surgery as well as histopathological diagnosis. There is a marked variation amongst surgeons in the follow-up arrangements for their patients even within the same unit which has a significant clinical, and financial implication. Knowing the tumour grade rapidly is an important factor to predict surgical outcomes and adequate patient treatment. Clinical follow up sometimes is haphazard and not based on clear evidence. Spectrochemical techniques are a powerful tool for cancer diagnostics. Raman hyperspectral imaging is able to generate spatially-distributed spectrochemical signatures with great sensitivity. Using this technique, 95 brain tissue samples (66 meningiomas WHO grade I, 24 meningiomas WHO grade II and 5 meningiomas that reoccurred) were analysed in order to discriminate grade I and grade II samples. Newly-developed three-dimensional discriminant analysis algorithms were used to process the hyperspectral imaging data in a 3D fashion. Three-dimensional principal component analysis quadratic discriminant analysis (3D-PCA-QDA) was able to distinguish grade I and grade II meningioma samples with 96% test accuracy (100% sensitivity and 95% specificity). This technique is here shown to be a high-throughput, reagent-free, non-destructive, and can give accurate predictive information regarding the meningioma tumour grade, hence, having enormous clinical potential with regards to being developed for intra-operative real-time assessment of disease.

Radiomics as an emerging tool in the management of brain metastases

Brain metastases (BM) are associated with significant morbidity and mortality in patients with advanced cancer. Despite significant advances in surgical, radiation, and systemic therapy in recent years, the median overall survival of patients with BM is less than 1 year. The acquisition of medical images, such as computed tomography (CT) and magnetic resonance imaging (MRI), is critical for the diagnosis and stratification of patients to appropriate treatments. Radiomic analyses have the potential to improve the standard of care for patients with BM by applying artificial intelligence (AI) with already acquired medical images to predict clinical outcomes and direct the personalized care of BM patients. Herein, we outline the existing literature applying radiomics for the clinical management of BM. This includes predicting patient response to radiotherapy and identifying radiation necrosis, performing virtual biopsies to predict tumor mutation status, and determining the cancer of origin in brain tumors identified via imaging. With further development, radiomics has the potential to aid in BM patient stratification while circumventing the need for invasive tissue sampling, particularly for patients not eligible for surgical resection.

Non-small cell lung cancer with multiple brain metastases remains relapse-free for more than 13 years: A case report

Brain metastasis (BM) in patients with non-small cell lung cancer (NSCLC) is usually associated with a poor prognosis. A 55-year-old Japanese man visited Tokyo Dental College Ichikawa General Hospital with complaints of motor aphasia and fatigue. Enhanced magnetic resonance imaging of the brain revealed multiple tumors. The patient's medical history included lung cancer surgery performed at another hospital 3 months prior to his visit to our hospital. Total resection of the left frontal tumor revealed BM from lung adenocarcinoma. Stereotactic radiosurgery (SRS) was performed for the remaining three BMs. At 9 months after SRS, another new BM was discovered, and SRS was again performed. More than 13 years have elapsed since the last SRS was performed, and the patient has remained relapse-free. To the best of our knowledge, this is the first case report describing a patient with NSCLC with multiple BMs who has remained relapse-free for >13 years with no neurological dysfunction, including cognitive deficit.

Multimodal evaluation of hypoxia in brain metastases of lung cancer and interest of hypoxia image-guided radiotherapy

Lung cancer patients frequently develop brain metastases (BM). Despite aggressive treatment including neurosurgery and external-radiotherapy, overall survival remains poor. There is a pressing need to further characterize factors in the microenvironment of BM that may confer resistance to radiotherapy (RT), such as hypoxia. Here, hypoxia was first evaluated in 28 biopsies from patients with non‑small cell lung cancer (NSCLC) BM, using CA-IX immunostaining. Hypoxia characterization (pimonidazole, CA-IX and HIF-1α) was also performed in different preclinical NSCLC BM models induced either by intracerebral injection of tumor cells (H2030-Br3M, H1915) into the cortex and striatum, or intracardial injection of tumor cells (H2030-Br3M). Additionally, [18F]-FMISO-PET and oxygen-saturation-mapping-MRI (SatO2-MRI) were carried out in the intracerebral BM models to further characterize tumor hypoxia and evaluate the potential of Hypoxia-image-guided-RT (HIGRT). The effect of RT on proliferation of BM ([18F]-FLT-PET), tumor volume and overall survival was determined. We showed that hypoxia is a major yet heterogeneous feature of BM from lung cancer both preclinically and clinically. HIGRT, based on hypoxia heterogeneity observed between cortical and striatal metastases in the intracerebrally induced models, showed significant potential for tumor control and animal survival. These results collectively highlight hypoxia as a hallmark of BM from lung cancer and the value of HIGRT in better controlling tumor growth.

Identification of the origin of brain metastases based on the relative methylation orderings of CpG sites

Accurate diagnosis of the origin of brain metastases (BMs) is crucial for tailoring an effective therapy to improve patients' prognosis. BMs of unknown origin account for approximately 2-14% of patients with BMs. Hence, the aim of this study was to identify the original cancer type of BMs based on their DNA methylation profiles. The DNA methylation profiles of glioma (GM), BM, and seven other types of primary cancers were collected. In comparison with GM, the reversal CpG site pairs were identified for each of the seven other types of primary cancers based on the within-sample relative methylation orderings (RMOs) of the CpG sites. Then, using the reversal CpG site pairs, GMs were distinguished from BMs and the seven other types of primary cancers. All 61 of the GM samples were correctly identified as GM. The cancer type was also identified for the non-GM samples. For the seven other types of primary cancers, greater than 93% of samples of each cancer type were correctly identified as their corresponding cancer type, except for breast cancer, which had an 88% accuracy. For 133 BM samples, 132 BM samples were identified as non-GM, and 95% of the 133 BM samples were correctly classified into their corresponding original cancer types. The RMO-based method can accurately identify the origin of BMs, which is important for precision treatment.

Differentiating the pathological subtypes of primary lung cancer for patients with brain metastases based on radiomics features from brain CT images

OBJECTIVES

It is of high clinical importance to identify the primary lesion and its pathological types for patients with brain metastases (BM). The purpose of this study is to investigate the feasibility and accuracy of differentiating the primary adenocarcinoma (AD) and squamous cell carcinoma (SCC) of non-small-cell lung cancer (NSCLC) for patients with BM based on radiomics from brain contrast-enhanced computer tomography (CECT) images.

METHODS

A total of 144 BM patients (94 male, 50 female) were enrolled in this study with 102 with primary lung AD and 42 with SCC, respectively. Radiomics features from manually contoured tumors were extracted using python. Mann-Whitney U test and the least absolute shrinkage and selection operator (LASSO) logistic regression were applied to select relative radiomics features. Binary logistic regression and support vector machines (SVM) were applied to build models with radiomics features alone and with radiomics features plus age and sex.

RESULTS

Fourteen features were selected from a total of 105 radiomics features for the final model building. The area under the curves (AUCs) and accuracy of SVM and binary logistic regression models were 0.765 vs. 0.769, 0.795 vs.0.828, and 0.716 vs. 0.726, 0.768 vs. 0.758, respectively, for models with radiomics features alone and models with radiomics features plus sex and age.

CONCLUSIONS

Brain CECT radiomics are promising in differentiating primary AD and SCC to achieve optimal therapeutic management in patients with BM from NSCLC.

KEY POINTS

• It is of high clinical importance to identify the primary lesion and its pathological types for patients with brain metastases (BM) to define the prognosis and treatment. • Few studies had investigated the feasibility and accuracy of differentiating the pathological subtypes of primary non-small-cell lung cancer between adenocarcinoma (AD) and squamous cell carcinoma (SCC) for patients with BM based on radiomics from brain contrast-enhanced CT (CECT) images, although CECT images are often the initial imaging modality to screen for metastases and are recommended on equal footing with MRI for the detection of cerebral metastases. • Brain CECT radiomics are promising in differentiating primary AD and SCC to achieve optimal therapeutic management in patients with BM from NSCLC with a highest area under the curve (AUC) of 0.828 and an accuracy of 0.758, respectively.

Melanoma brain metastases: review of histopathological features and immune-molecular aspects

Patients with melanoma brain metastases (MBM) have a dismal prognosis, but the unprecedented advances in systemic therapy alone or in combination with local therapy have now extended the 1-year overall survival rate from 20–25% to nearing 80–85%, mainly in asymptomatic patients. The histopathological and molecular characterization of MBM and the understanding of the microenvironment are critical to more effectively manage patients with advanced melanoma and to design biologically driven clinical trials. This review aims to give an overview of the main histopathological features and the immune-molecular aspects of MBM.

Spectral classification for diagnosis involving numerous pathologies in a complex clinical setting: A neuro-oncology example

Much effort is currently being placed into developing new blood tests for cancer diagnosis in the hope of moving cancer diagnosis earlier and by less invasive means than current techniques, e.g., biopsy. Current methods are expected to diagnose and begin treatment of cancer within 62 days of patient presentation, though due to high volume and pressures within the NHS in the UK any technique that can reduce time to diagnosis would allow reduction in the time to treat for patients. The use of vibrational spectroscopy, notably infrared (IR) spectroscopy, has been under investigation for many years with varying success. This technique holds promise as is would combine a generally well accepted test (a blood test) with analysis that is reagent free and cheap to run. It has been demonstrated that, when asked simple clinical questions (i.e., cancer vs. no cancer), results from spectroscopic studies are promising. However, in order to become a clinically useful tool, it is important that the test differentiates a variety of cancer types from healthy patients. This study has analysed plasma samples with attenuated total reflection Fourier-transform IR spectroscopy (ATR-FTIR), to establish if the technique is able to distinguish normal from primary or metastatic brain tumours. We have shown that when asked specific questions, i.e., high-grade glioma vs. low-grade glioma, the results show a significantly high accuracy (100%). Crucially, when combined with meningiomas and metastatic lesions, the accuracy remains high (88-100%) with only minimal overlap between the two metastatic adenocarcinoma groups. Therefore in a clinical setting, this novel technique demonstrates potential benefit when used in conjuction with existing diagnostic methods.

Epigenetic profiling for the molecular classification of metastatic brain tumors

Optimal treatment of brain metastases is often hindered by limitations in diagnostic capabilities. To meet this challenge, here we profile DNA methylomes of the three most frequent types of brain metastases: melanoma, breast, and lung cancers (n = 96). Using supervised machine learning and integration of DNA methylomes from normal, primary, and metastatic tumor specimens (n = 1860), we unravel epigenetic signatures specific to each type of metastatic brain tumor and constructed a three-step DNA methylation-based classifier (BrainMETH) that categorizes brain metastases according to the tissue of origin and therapeutically relevant subtypes. BrainMETH predictions are supported by routine histopathologic evaluation. We further characterize and validate the most predictive genomic regions in a large cohort of brain tumors (n = 165) using quantitative-methylation-specific PCR. Our study highlights the importance of brain tumor-defining epigenetic alterations, which can be utilized to further develop DNA methylation profiling as a critical tool in the histomolecular stratification of patients with brain metastases.

Adjuvant radiotherapy and outcomes of presumed hemorrhagic melanoma brain metastases without malignant cells

Background

Patients with melanoma can present with a hemorrhagic intracranial lesion. Upon resection, pathology reports may not detect any malignant cells. However, the hemorrhage may obscure their presence and so physicians may still decide whether adjuvant radiotherapy should be applied. Here, we report on the outcomes of a series of patients with melanoma with hemorrhagic brain lesions that returned with no tumor cells.

Methods

All melanoma patients who had craniotomies from 2008 to 2017 at a single institution for hemorrhagic brain lesions were identified through retrospective chart review. Those who had pathology reports with no malignant cells were analyzed. Recurrence at the former site of hemorrhage and resection was the primary outcome.

Results

Ten patients met inclusion criteria, and the median follow-up time was 8.5 (1.8-27.3) months. At the time of craniotomy, the median number of brain lesions was 3 (1-25). Two patients had prior craniotomies, eight had prior radiation, and six had prior immunotherapy to the lesion of interest. After surgery, one patient received stereotactic radiosurgery (SRS) to the resection bed. Only one patient developed subsequent melanoma at the resection site; this patient developed the lesion recurrence once and had not received postoperative SRS.

Conclusion

Although small foci of metastatic disease as a source of bleeding for some patients cannot be excluded, melanoma patients with a suspected hemorrhagic brain metastasis that shows no tumor cells on pathology may benefit from close observation. The local recurrence risk in such cases appears to be low, even without adjuvant radiation.

Mechanisms and Therapy for Cancer Metastasis to the Brain

Advances in chemotherapy and targeted therapies have improved survival in cancer patients with an increase of the incidence of newly diagnosed brain metastases (BMs). Intracranial metastases are symptomatic in 60–70% of patients. Magnetic resonance imaging (MRI) with gadolinium is more sensitive than computed tomography and advanced neuroimaging techniques have been increasingly used in the detection, treatment planning, and follow-up of BM. Apart from the morphological analysis, the most effective tool for characterizing BM is immunohistochemistry. Molecular alterations not always reflect those of the primary tumor. More sophisticated methods of tumor analysis detecting circulating biomarkers in fluids (liquid biopsy), including circulating DNA, circulating tumor cells, and extracellular vesicles, containing tumor DNA and macromolecules (microRNA), have shown promise regarding tumor treatment response and progression. The choice of therapeutic approaches is guided by prognostic scores (Recursive Partitioning Analysis and diagnostic-specific Graded Prognostic Assessment-DS-GPA). The survival benefit of surgical resection seems limited to the subgroup of patients with controlled systemic disease and good performance status. Leptomeningeal disease (LMD) can be a complication, especially in posterior fossa metastases undergoing a “piecemeal” resection. Radiosurgery of the resection cavity may offer comparable survival and local control as postoperative whole-brain radiotherapy (WBRT). WBRT alone is now the treatment of choice only for patients with single or multiple BMs not amenable to surgery or radiosurgery, or with poor prognostic factors. To reduce the neurocognitive sequelae of WBRT intensity modulated radiotherapy with hippocampal sparing, and pharmacological approaches (memantine and donepezil) have been investigated. In the last decade, a multitude of molecular abnormalities have been discovered. Approximately 33% of patients with non-small cell lung cancer (NSCLC) tumors and epidermal growth factor receptor mutations develop BMs, which are targetable with different generations of tyrosine kinase inhibitors (TKIs: gefitinib, erlotinib, afatinib, icotinib, and osimertinib). Other “druggable” alterations seen in up to 5% of NSCLC patients are the rearrangements of the “anaplastic lymphoma kinase” gene TKI (crizotinib, ceritinib, alectinib, brigatinib, and lorlatinib). In human epidermal growth factor receptor 2-positive, breast cancer targeted therapies have been widely used (trastuzumab, trastuzumab-emtansine, lapatinib-capecitabine, and neratinib). Novel targeted and immunotherapeutic agents have also revolutionized the systemic management of melanoma (ipilimumab, nivolumab, pembrolizumab, and BRAF inhibitors dabrafenib and vemurafenib).

Classifying brain metastases by their primary site of origin using a radiomics approach based on texture analysis: a feasibility study

OBJECTIVE

To examine the capability of MRI texture analysis to differentiate the primary site of origin of brain metastases following a radiomics approach.

METHODS

Sixty-seven untreated brain metastases (BM) were found in 3D T1-weighted MRI of 38 patients with cancer: 27 from lung cancer, 23 from melanoma and 17 from breast cancer. These lesions were segmented in 2D and 3D to compare the discriminative power of 2D and 3D texture features. The images were quantized using different number of gray-levels to test the influence of quantization. Forty-three rotation-invariant texture features were examined. Feature selection and random forest classification were implemented within a nested cross-validation structure. Classification was evaluated with the area under receiver operating characteristic curve (AUC) considering two strategies: multiclass and one-versus-one.

RESULTS

In the multiclass approach, 3D texture features were more discriminative than 2D features. The best results were achieved for images quantized with 32 gray-levels (AUC = 0.873 ± 0.064) using the top four features provided by the feature selection method based on the p-value. In the one-versus-one approach, high accuracy was obtained when differentiating lung cancer BM from breast cancer BM (four features, AUC = 0.963 ± 0.054) and melanoma BM (eight features, AUC = 0.936 ± 0.070) using the optimal dataset (3D features, 32 gray-levels). Classification of breast cancer and melanoma BM was unsatisfactory (AUC = 0.607 ± 0.180).

CONCLUSION

Volumetric MRI texture features can be useful to differentiate brain metastases from different primary cancers after quantizing the images with the proper number of gray-levels.

KEY POINTS

• Texture analysis is a promising source of biomarkers for classifying brain neoplasms. • MRI texture features of brain metastases could help identifying the primary cancer. • Volumetric texture features are more discriminative than traditional 2D texture features.