Brain tumor detection from MRI scans is a critical step in the diagnostic process, enabling timely and effective treatment for patients. Early and accurate identification of tumors can significantly improve treatment outcomes and patient prognosis, highlighting the importance of leveraging advanced tools for this task. The proposed model presents a deep learning-based solution for brain tumor detection using MRI scans, leveraging the power of the pre-trained ResNet-152 model to achieve accurate tumor classification, combined with a user friendly graphical interface (GUI) for interactive image analysis. The deep learning model, fine-tuned on a custom dataset of brain MRI images, is designed to effectively differentiate between tumor-affected and healthy brain tissue. By utilizing transfer learning and ResNet-152’s pre-trained weights, the model performs exceptionally well on the binary classification task, ensuring high accuracy and precision in tumor detection. According to experimental data, the model is reliable in detecting brain cancers from MRI scans, with an accuracy of 98.44%. The intuitive GUI, built with Python’s Tkinter library, offers two main features of the GUI, which are “Detect Tumor” and “View Tumor Region.” The technology helps doctors better assess tumor size, form, and location by displaying a label (“Tumor Detected”) and a highlighted tumor region using color-coded overlays when a tumor is discovered. This integration of automation and visualization supports a streamlined diagnostic process, providing clinicians with both automatic tumor detection and a clear visual representation of the tumor’s location. The tool aims to enhance clinical workflows, making it a valuable and accessible resource for healthcare settings.