Glioblastoma (GB) is the most aggressive and recurrent form of brain cancer in adults. We hypothesized that the identification of biomarkers such as certain microRNAs (miRNAs) and the circulating microvesicles (MVs) that transport them could be key to establishing GB progression, recurrence and therapeutic response. For this purpose, circulating MVs were isolated from the plasma of GB patients (before and after surgery) and of healthy subjects and characterized by flow cytometry. OpenArray profiling and the individual quantification of selected miRNAs in plasma and MVs was performed, followed by target genes’ prediction and in silico survival analysis. It was found that MVs’ parameters (number, EGFRvIII and EpCAM) decreased after the surgical resection of GB tumors, but the inter-patient variability was high. The expression of miR-106b-5p, miR-486-3p, miR-766-3p and miR-30d-5p in GB patients’ MVs was restored to control-like levels after surgery: miR-106b-5p, miR-486-3p and miR-766-3p were upregulated, while miR-30d-5p levels were downregulated after surgical resection. MiR-625-5p was only identified in MVs isolated from GB patients before surgery and was not detected in plasma. Target prediction and pathway analysis showed that the selected miRNAs regulate genes involved in cancer pathways, including glioma. In conclusion, miR-625-5p shows potential as a biomarker for GB regression or recurrence, but further in-depth studies are needed.

Background/Objective: This study explores the use of AI-powered radiomics to classify and monitor brain metastasis progression and regression following Gamma Knife radiosurgery (GKRS) based on MRI imaging. A clinical decision support application was developed using Streamlit to provide real-time, AI-driven predictions for treatment monitoring. Methods: MRI scans from 60 patients (3194 images) were analyzed using a transfer learning-enhanced AlexNet deep learning model. Class imbalance was mitigated through dynamic class weighting and data augmentation to ensure equitable performance across all classes. Optimized preprocessing pipelines ensured dataset standardization. Model performance was evaluated using accuracy, precision, recall, F1-scores, and AUC, with 95% confidence intervals. Additionally, a comparative analysis of Gamma Knife radiosurgery (GKRS) outcomes and predictive modeling demonstrated strong correlations between tumor volume evolution and treatment response. The AI predictions and visualizations were integrated into a Streamlit-based application to ensure clinical usability and ease of access. The AI-driven approach effectively classified progression and regression patterns, reinforcing its potential for clinical integration. Results: The transfer learning model achieved flawless classification accuracy (100%; 95% CI: 100–100%) along with perfect precision, recall, and F1-scores. The AUC score of 1.0000 (95% CI: 1.0000–1.0000) indicated excellent discrimination between progression and regression cases. Compared to the baseline AlexNet model (99.53% accuracy; 95% CI: 98.90–100.00%), the TL-enhanced model resolved all misclassifications. Tumor volume analysis identified the baseline size as a key predictor of progression (Pearson r = 0.795, r = 0.795, r = 0.795, p < 0.0001, p < 0.0001, and p < 0.0001). The training time (420.12 s) was faster than ResNet-50 (443.38 s) and EfficientNet-B0 (439.87 s), while achieving equivalent metrics. Despite 100% accuracy, the model requires multi-center validation for generalizability. Conclusions: This study demonstrates that transfer learning with dynamic class weighting provides a highly accurate and reliable framework for monitoring brain metastases post-GKRS. The Streamlit-based AI application enhances clinical decision-making by improving diagnostic precision and reducing variability. Explainable AI techniques, such as Grad-CAM visualizations, improve interpretability and support clinical adoption. These findings emphasize the transformative potential of AI in personalized treatment strategies, extending applications to genomic profiling, survival modeling, and longitudinal follow-ups for brain metastasis management.

Background: The study investigated whether three deep-learning models, namely, the CNN_model (trained from scratch), the TL_model (transfer learning), and the FT_model (fine-tuning), could predict the early response of brain metastases (BM) to radiosurgery using a minimal pre-processing of the MRI images. The dataset consisted of 19 BM patients who underwent stereotactic-radiosurgery (SRS) within 3 months. The images used included axial fluid-attenuated inversion recovery (FLAIR) sequences and high-resolution contrast-enhanced T1-weighted (CE T1w) sequences from the tumor center. The patients were classified as responders (complete or partial response) or non-responders (stable or progressive disease). Methods: A total of 2320 images from the regression class and 874 from the progression class were randomly assigned to training, testing, and validation groups. The DL models were trained using the training-group images and labels, and the validation dataset was used to select the best model for classifying the evaluation images as showing regression or progression. Results: Among the 19 patients, 15 were classified as “responders” and 4 as “non-responders”. The CNN_model achieved good performance for both classes, showing high precision, recall, and F1-scores. The overall accuracy was 0.98, with an AUC of 0.989. The TL_model performed well in identifying the “progression” class, but could benefit from improved precision, while the “regression” class exhibited high precision, but lower recall. The overall accuracy of the TL_model was 0.92, and the AUC was 0.936. The FT_model showed high recall for “progression”, but low precision, and for the “regression” class, it exhibited a high precision, but lower recall. The overall accuracy for the FT_model was 0.83, with an AUC of 0.885. Conclusions: Among the three models analyzed, the CNN_model, trained from scratch, provided the most accurate predictions of SRS responses for unlearned BM images. This suggests that CNN models could potentially predict SRS prognoses from small datasets. However, further analysis is needed, especially in cases where class imbalances exist.

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.

This study assesses the predictive performance of six machine learning models 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. 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.

Background: Autologous fat grafts are widely used for skull base reconstruction following endoscopic endonasal surgery. However, uncertainty regarding their postoperative volumetric evolution may complicate the distinction between expected postoperative changes and residual or recurrent disease on imaging. Methods: We performed a retrospective volumetric imaging analysis of patients undergoing endoscopic endonasal skull base surgery with reconstruction using autologous fat and the 3F technique between 2013 and 2023. Fat graft volumes were measured on postoperative day 1 CT scans and on 3-, 9-, and 15-month postoperative MRI using standardized volumetric segmentation analysis (method described in detail in the main text). It should be noted that baseline measurements were derived from CT, whereas follow-up assessments were performed using MRI. Resorption rates were correlated with demographic, pathological, surgical, and postoperative variables. Results: Thirty-four patients met inclusion criteria. Mean initial fat graft volume was 3.01 ± 2.65 cm³. Overall, fat graft volume demonstrated a consistent temporal decline, with mean reductions of 56.8% at 3 months, 75.3% at 9 months, and 81.8% at 15 months. In subgroup analysis, differences in resorption were observed according to surgical approach, with higher resorption following transsellar compared with transtuberculum approaches (87.4% vs. 74.8% at 15 months, p = 0.042). These findings were closely related to graft compartment, although compartment and surgical approach showed substantial overlap in this cohort. No significant associations were detected between resorption rate and age, sex, comorbidities, postoperative CSF leak, extent of resection, or adjuvant radiotherapy. Conclusions: Autologous fat grafts used for skull base reconstruction demonstrate substantial early postoperative resorption followed by slower progressive volume loss. Recipient anatomical compartment was associated with differences in observed resorption patterns, although this relationship should be interpreted in the context of overlap with surgical approach and limited sample size. These findings may assist in improving interpretation of postoperative imaging by clarifying the expected temporal pattern of fat graft evolution after endoscopic skull base reconstruction.