Limited capability of MRI radiomics to predict primary tumor histology of brain metastases in external validation.

Background: Growing research demonstrates the ability to predict histology or genetic information of various malignancies using radiomic features extracted from imaging data. This study aimed to investigate MRI-based radiomics in predicting the primary tumor of brain metastases through internal and external validation, using oversampling techniques to address the class imbalance. Methods: This IRB-approved retrospective multicenter study included brain metastases from lung cancer, melanoma, breast cancer, colorectal cancer, and a combined heterogenous group of other primary entities (5-class classification). Local data were acquired between 2003 and 2021 from 231 patients (545 metastases). External validation was performed with 82 patients (280 metastases) and 258 patients (809 metastases) from the publicly available Stanford BrainMetShare and the University of California San Francisco Brain Metastases Stereotactic Radiosurgery datasets, respectively. Preprocessing included brain extraction, bias correction, coregistration, intensity normalization, and semi-manual binary tumor segmentation. Two-thousand five hundred and twenty-eight radiomic features were extracted from T1w (±â€…contrast), fluid-attenuated inversion recovery (FLAIR), and wavelet transforms for each sequence (8 decompositions). Random forest classifiers were trained with selected features on original and oversampled data (5-fold cross-validation) and evaluated on internal/external holdout test sets using accuracy, precision, recall, F1 score, and area under the receiver-operating characteristic curve (AUC). Results: Oversampling did not improve the overall unsatisfactory performance on the internal and external test sets. Incorrect data partitioning (oversampling before train/validation/test split) leads to a massive overestimation of model performance. Conclusions: Radiomics models' capability to predict histologic or genomic data from imaging should be critically assessed; external validation is essential.

Brain metastasis resection: the impact of fluorescence guidance (MetResect study).

OBJECTIVE: Maximal resection of brain metastases (BMs) improves both progression-free survival and overall survival (OS). Fluorescein sodium (FL) in combination with the YELLOW 560-nm filter is a safe and feasible method for visualizing residual tumor tissue during BM resection. The authors of this study aimed to show that use of FL would positively influence the volumetric extent of resection (EOR) and thus the survival outcome in patients undergoing BM resection. METHODS: Analyzing their institution's prospective brain tumor registry, the authors identified 539 consecutive patients with BMs (247 women, mean age 62.8 years) by using preoperative high-quality MR images for volumetric analysis. BMs were resected under white light (WL) in 293 patients (54.4%; WL group) and under FL guidance in 246 patients (45.6%; FL group). Sex, age, presurgical Karnofsky Performance Status (KPS), recursive partitioning analysis class, and adjuvant treatment modalities were well balanced between the two groups. Volumetric analysis was performed in a blinded fashion by quantifying pre- and postoperative tumor volume based on gadolinium-enhanced T1-weighted sequences. RESULTS: In the FL group, the postoperative tumor volume was significantly smaller (p = 0.01), and hence the quantitative EOR was significantly larger (p = 0.024) and OS was significantly longer (p = 0.0001) (log-rank testing). Multivariate Cox regression modeling showed that age, presurgical KPS, metastasis status, and FL-guided resection are independent prognostic factors for survival. CONCLUSIONS: Compared with WL resection, FL-guided BM resection increased resection quality, significantly improved EOR, and prolonged OS.

Fluorescein-guided resection of newly diagnosed high-grade glioma: Impact on extent of resection and outcome.

Introduction: Maximal resection of high-grade glioma (HGG) improves progression-free survival (PFS) and overall survival (OS). Fluorescein sodium (FL) in combination with the YELLOW 560 â€‹nm filter (Carl Zeiss Meditec, Germany) is a safe and feasible method of visualizing residual tumor tissue during brain tumor resection. Research question: We hypothesized that use of FL positively influenced the volumetric extent of resection (EOR), PFS, and OS in patients undergoing resection of a newly diagnosed HGG. Materials and method: Using a prospective HGG registry, we identified 347 patients (median age 62.4 years; 141 women) with preoperative high-quality magnetic resonance images for volumetric analysis. Resection was performed under white light in n â€‹= â€‹151 (43.5%, white-light group) and under FL-guidance in n â€‹= â€‹196 (56.5%, FL group). Sex, age, presurgical Karnofsky Performance Index (KPI), O6-Methylguanin-DNA-Methyltransferase-Gene (MGMT) status, and adjuvant treatment modalities were well balanced between the groups. Volumetric analysis was performed by quantifying pre- and postoperative tumor volume based on gadolinium-enhanced T1 sequences in a blinded fashion. Results: In the FL group, postoperative tumor volume was significantly smaller (p â€‹= â€‹0.003); accordingly, quantitative EOR was significantly larger (p â€‹= â€‹0.003). Significantly more complete resections were achieved in the FL group than in the white-light group (p â€‹= â€‹0.003). The FL group showed significantly longer PFS (p â€‹= â€‹0.020) and OS (p â€‹= â€‹0.015, log rank testing). Multivariate Cox regression modelling showed age, presurgical KPI, MGMT status, and FL-guided resection to be independent prognostic factors for survival. Discussion and conclusion: Compared to white-light resection, FL-guided resection of newly diagnosed HGG significantly improved EOR and prolonged OS.

Factors associated with short-term local recurrence of liver cancer after percutaneous ablation using irreversible electroporation: a prospective single-center study.

PURPOSE: To evaluate the risk factors associated with short-term local recurrence of malignant liver lesions after irreversible electroporation (IRE). MATERIALS AND METHODS: Thirty-nine consecutive patients (79 malignant liver lesions) were treated with IRE, of whom 14 were excluded from the analysis (including 12 without 6 mo of follow-up and two with incomplete ablation). The remaining 25 patients (aged 59.4 y ± 11.2) had 48 malignant liver lesions, including 22 hepatocellular carcinomas (HCCs), six cholangiocellular carcinomas, and 20 metastatic liver cancers. Multivariate analyses were used to evaluate the associations of risk factors with early recurrence. The characteristics of patients, lesions, and IRE procedures were assessed by logistic regression. RESULTS: Fourteen of the 48 treated lesions (29.2%) showed early local recurrence after 6 months. Tumor volume (< 5 cm(3) vs ≥ 5 cm(3); P = .022) and underlying disease type (HCC, cholangiocellular carcinoma, or metastatic disease; P = .023) were independently associated with early local recurrence. However, distances to the surrounding portal veins (< 0.5 cm vs ≥ 0.5 cm; P = .810), hepatic veins (P = .170), hepatic arteries (P = .761), and bile ducts (P = .226) were not significantly associated with local recurrence. CONCLUSIONS: Because short distances to the surrounding vessels were not associated with early local recurrence, percutaneous IRE might provide an alternative treatment option for perivascular tumors. However, patients with larger tumor volumes appeared to be poor candidates for percutaneous IRE. Regarding the different types of treated lesions, patients with HCC had significantly better outcomes.