<p>Early diagnosis of brain tumors is critical, as it increases the likelihood of successful treatment and improves overall patient outcomes. In the biomedical field, non-invasive imaging techniques such as Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) are widely used for brain tumor detection. Recently, Deep Learning (DL), a branch of Artificial Intelligence (AI), has shown great promise in rapidly analyzing MR images, significantly reducing diagnosis time and improving diagnostic accuracy. Navigated Transcranial Magnetic Stimulation (nTMS) is another effective non-invasive method, often used preoperatively to identify functionally essential regions in patients with tumors located in motor-eloquent areas. This research proposes an Integrated Risk-Stratification Score with Navigated Transcranial Magnetic Stimulation (IntRSS) for Brain Tumor Detection (BTD) using a Deep Convolutional Neural Network (DCNN) model. The goal is to predict postoperative motor outcomes in glioma surgery by combining nTMS-derived neurophysiological data with deep learning-based classification. The approach incorporates multiple DL architectures—CNN, ResNet-40, VGG-19, and InceptionV3—in an ensemble model designed to capture diverse feature representations and reduce overfitting. The model was trained and tested on a real-world dataset collected from Shri Amrithum Super Specialty Hospital (SASSH), Raipur (C.G.), consisting of 3000 MR images from 51 patients diagnosed with lower-grade gliomas. Tumors were classified into Grades I, II, III, and IV. The ensemble approach outperformed individual models in terms of accuracy, precision, sensitivity, specificity, recall, and F1-score. Overall, the proposed IntRSS-DCNN model offers strong potential as a reliable secondary diagnostic aid for radiologists in the accurate detection and classification of brain tumors.</p>