Accurate segmentation and classification of brain tumors from Magnetic Resonance Imaging (MRI) remain key challenges in medical image analysis, largely due to the lack of high-quality, balanced, and diverse datasets. In this work, we present a new curated MRI dataset designed specifically for brain tumor segmentation and classification tasks. The dataset comprises 6,000 contrast-enhanced T1-weighted MRI scans annotated by certified radiologists and physicians, spanning three major tumor types-glioma, meningioma, and pituitary-as well as non-tumorous cases. Each sample includes high-resolution labels and is categorized across axial, sagittal, and coronal imaging planes to facilitate robust model development and cross-view generalization. To demonstrate the utility of the dataset, we propose a transformer-based segmentation model and benchmark it against established baselines. Our method achieves the highest weighted mean Intersection-over-Union (IoU) of 82.3%, with improvements observed across all tumor categories. Importantly, this study serves primarily as an introduction to the dataset, establishing foundational benchmarks for future research. We envision this dataset as a valuable resource for advancing machine learning applications in neuro-oncology, supporting both academic research and clinical decision-support development. datasetlink:this https URL
View on arXiv@article{fateh2025_2506.14318,
title={ BRISC: Annotated Dataset for Brain Tumor Segmentation and Classification with Swin-HAFNet },
author={ Amirreza Fateh and Yasin Rezvani and Sara Moayedi and Sadjad Rezvani and Fatemeh Fateh and Mansoor Fateh },
journal={arXiv preprint arXiv:2506.14318},
year={ 2025 }
}