International Conference on Computer and Knowledge Engineering

Home / 15th International Conference on Computer and Knowledge Engineering

Advancing Brain Tumor Detection via ViRCNN: A Fusion of Vision Transformers and Faster R-CNN

Authors :

Mehrshad Momen-Tayefeh¹ S. AmirAli GH. Ghahramani² Ali Mohammad Afshin Hemmatyar³

1- Department of Computer Engineering, Sharif University of Technology, Tehran, Iran. 2- Department of Computer Engineering, Sharif University of Technology, International Campus Kish Island, Iran. 3- Department of Computer Engineering, Sharif University of Technology, Tehran, Iran

Keywords :

Deep learning،Vision Transformer،Faster R-CNN،Brain Tumor

Abstract :

Accurate brain tumor detection is vital for effective diagnosis and treatment. This paper presents ViRCNN, a hybrid model that integrates Faster R-CNN and Vision Transformers (ViT) to enhance MRI-based tumor detection. Using the Br35H dataset of 801 MRI images, ViRCNN achieves a 0.9% improve- ment in MAP50 while maintaining a compact 19M-parameter architecture. Compared to existing models exceeding 80M pa- rameters, ViRCNN offers improved detection precision with significantly lower computational demands, making it suitable for real-time clinical deployment