• The transorbital approach combining eyebrow incision and crescent-shaped craniotomy increases the surgical freedom to access the anterior and middle skull-base. • The technic allows the use of both endoscope and microscope. • The concept is at the crossroad between the supraorbital keyhole and endoscopic trans-orbital approach.

Melanoma, a malignant skin tumor, is the third skin tumor and the third cause of brain metastases. The development and introduction of systemic therapies, such as Braf inhibitors and checkpoint inhibitors, have guaranteed an increase in overall survival. The appearance of brain metastases, which determines a median survival of less than 5 months, represents a sign of systemic disease progression and tumor instability. In this view, in addition to systemic therapy, the therapeutic options can be surgery, stereotactic surgery, and whole-brain radiation therapy. However, it has been observed that the response to systemic therapies of brain metastatic lesions, compared to extracerebral ones, does not guarantee complete local tumor control, thus increasing the mortality and morbidity of patients. This phenomenon, tumor escape, makes systemic therapy partly ineffective. How melanoma cells migrate, cross the blood–brain barrier, and invade brain tissue is still being studied. The melanocytic metastatic brain tumor microenvironment and its assay seem to have a key role in the response and therefore in the progression of metastatic lesions. Through this work, the intent is to underline the importance of the brain tumor microenvironment and how it can influence tumor growth, its response to therapy, and the patient’s overall survival.

Background: Transorbital approaches (TOAs) provide minimally invasive access to anterior and middle cranial fossa lesions. However, orbital retraction remains a challenge, as narrow corridors limit maneuverability and excessive retraction increase complication risk. Conventional rigid or malleable retractors may obstruct the corridor or exert uneven pressure on delicate tissues. We present a handmade, semi-rigid plastic retractor as a low-cost, effective solution to optimize orbital retraction in TOAs. Methods: The retractor was fashioned from a cylindrical plastic drill bit container, cut into two semicircular pieces with rounded edges. Its application is described within the transorbital eyebrow lacrimal keyhole approach (TELKA). During the bony phase, one piece is placed on the orbital roof for periorbital retraction and protection, while a second may be positioned laterally to protect the temporalis muscle when required. Once adequate working space is achieved, the lateral retractor is removed and the medial one maintained throughout the procedure. Technical details are illustrated through representative clinical cases, supported by anatomical dissection and an operative video. Results: Across thirteen TELKA procedures, the semi-rigid retractor provided stable, low-intensity retraction with even pressure distribution, minimizing corridor obstruction and facilitating both microscopic and endoscopic maneuverability. No orbital or visual complications related to retraction were observed; periorbital structures were preserved, with no postoperative proptosis or aesthetic defects. Conclusions: This handmade, semi-rigid retractor is a safe, customizable, and reproducible tool that enhances surgical freedom while minimizing orbital morbidity in TOAs. It is particularly advantageous in keyhole procedures such as TELKA, representing a promising alternative to conventional retraction systems.

Background: Glioblastoma (GB) remains one of the most aggressive brain tumors, with limited survival and high recurrence rates. In most cases, GB recurrence occurs locally, either on the residual tumor after surgery or within 2 cm of the resection cavity—but in rarer cases, tumor cells can spread beyond this margin, leading to distant recurrence. By spread , we refer to the spatial dissemination of tumor cells beyond the typical local site, which can involve distant brain regions or even the leptomeninges, significantly impacting treatment planning and surgical decision-making. This study proposes the application of Machine Learning (ML) and Deep Learning (DL) approaches to MRI data from GB patients in the preoperative phases, aiming to develop predictive models to predict the extent of recurrence spread, on the integrated analysis of clinical, imaging, and instrumental data. Additionally, we plan to design a (semi) automatic segmentation tool for tumor delineation in MRI, which will support both the implementation of the study and serve as a standalone instrument to standardize volume measurement in neuroimaging. Methods and analytics: A multicenter retrospective collection of clinical and radiological variables will be performed for all eligible GB patients. Variables will include demographic, surgical, pathological, and preoperative MRI features. Predictive modelling will use classical ML algorithms (e.g., Random Forest, SVM, Multilayer perceptron, etc.) and a 3D U-Net architecture for DL-based image segmentation. Dimensionality reduction (PCA, LASSO, etc.) will be used to prevent overfitting and improve model generalizability. Model performance will be assessed through Area Under the Curve (AUC), P-R curve, F-score, accuracy, sensitivity, specificity, confusion matrix, and Dice score for segmentation. Discussion: The development of Artificial Intelligence (AI)-based predictive models for GB is expected to provide a major contribution to outcome prediction, early targeted interventions, and personalized care. These tools may support optimized resource allocation, reduce healthcare costs, and improve patient and family outcomes. The findings from this study will serve as a foundation for a future prospective multicenter validation study.