Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

RepVGG-GELAN: Enhanced GELAN with VGG-STYLE ConvNets for Brain Tumour Detection

Thennarasi Balakrishnan, Sandeep Singh Sengar

TL;DR

This work tackles brain-tumor detection in medical imagery by leveraging a YOLO-based detector enhanced with RepVGG reparameterized convolutions and GELAN backbones. The authors introduce RepVGG-GELAN, which combines RepVGG blocks, RepNCSPELAN4, and GELAN-inspired multi-scale feature fusion to improve precision and localization while maintaining efficiency, evidenced by higher precision ($$0.982$$) and AP$_{50}$ ($$0.970$$) on Br35H with 25.4M parameters. An ablation study confirms the contribution of RepVGG to performance gains, underscoring the value of reparameterized convolution and GELAN fusion for robust brain-tumor detection. The approach demonstrates strong potential for real-time, accurate medical image analysis, with publicly available code supporting reproducibility and deployment.

Abstract

Object detection algorithms particularly those based on YOLO have demonstrated remarkable efficiency in balancing speed and accuracy. However, their application in brain tumour detection remains underexplored. This study proposes RepVGG-GELAN, a novel YOLO architecture enhanced with RepVGG, a reparameterized convolutional approach for object detection tasks particularly focusing on brain tumour detection within medical images. RepVGG-GELAN leverages the RepVGG architecture to improve both speed and accuracy in detecting brain tumours. Integrating RepVGG into the YOLO framework aims to achieve a balance between computational efficiency and detection performance. This study includes a spatial pyramid pooling-based Generalized Efficient Layer Aggregation Network (GELAN) architecture which further enhances the capability of RepVGG. Experimental evaluation conducted on a brain tumour dataset demonstrates the effectiveness of RepVGG-GELAN surpassing existing RCS-YOLO in terms of precision and speed. Specifically, RepVGG-GELAN achieves an increased precision of 4.91% and an increased AP50 of 2.54% over the latest existing approach while operating at 240.7 GFLOPs. The proposed RepVGG-GELAN with GELAN architecture presents promising results establishing itself as a state-of-the-art solution for accurate and efficient brain tumour detection in medical images. The implementation code is publicly available at https://github.com/ThensiB/RepVGG-GELAN.

RepVGG-GELAN: Enhanced GELAN with VGG-STYLE ConvNets for Brain Tumour Detection

TL;DR

This work tackles brain-tumor detection in medical imagery by leveraging a YOLO-based detector enhanced with RepVGG reparameterized convolutions and GELAN backbones. The authors introduce RepVGG-GELAN, which combines RepVGG blocks, RepNCSPELAN4, and GELAN-inspired multi-scale feature fusion to improve precision and localization while maintaining efficiency, evidenced by higher precision () and AP () on Br35H with 25.4M parameters. An ablation study confirms the contribution of RepVGG to performance gains, underscoring the value of reparameterized convolution and GELAN fusion for robust brain-tumor detection. The approach demonstrates strong potential for real-time, accurate medical image analysis, with publicly available code supporting reproducibility and deployment.

Abstract

Object detection algorithms particularly those based on YOLO have demonstrated remarkable efficiency in balancing speed and accuracy. However, their application in brain tumour detection remains underexplored. This study proposes RepVGG-GELAN, a novel YOLO architecture enhanced with RepVGG, a reparameterized convolutional approach for object detection tasks particularly focusing on brain tumour detection within medical images. RepVGG-GELAN leverages the RepVGG architecture to improve both speed and accuracy in detecting brain tumours. Integrating RepVGG into the YOLO framework aims to achieve a balance between computational efficiency and detection performance. This study includes a spatial pyramid pooling-based Generalized Efficient Layer Aggregation Network (GELAN) architecture which further enhances the capability of RepVGG. Experimental evaluation conducted on a brain tumour dataset demonstrates the effectiveness of RepVGG-GELAN surpassing existing RCS-YOLO in terms of precision and speed. Specifically, RepVGG-GELAN achieves an increased precision of 4.91% and an increased AP50 of 2.54% over the latest existing approach while operating at 240.7 GFLOPs. The proposed RepVGG-GELAN with GELAN architecture presents promising results establishing itself as a state-of-the-art solution for accurate and efficient brain tumour detection in medical images. The implementation code is publicly available at https://github.com/ThensiB/RepVGG-GELAN.
Paper Structure (12 sections, 2 equations, 3 figures, 2 tables)

This paper contains 12 sections, 2 equations, 3 figures, 2 tables.

Table of Contents

  1. INTRODUCTION
  2. LITERATURE REVIEW
  3. RepVGG/RepConv ShuffleNet
  4. Generalized Efficient Layer Aggregation Network (GELAN)
  5. METHODOLOGY
  6. EXPERIMENTS AND RESULTS
  7. Data Collection
  8. Implementation details
  9. Evaluation metrics
  10. Results
  11. Ablation study
  12. CONCLUSION

Figures (3)

  • Figure 1: The RepVGG architecture. (a) during the training phase, (b) during the inference phase (or deployed). Source: (RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection, 2023)
  • Figure 2: Generalized Efficient Layer Aggregation Network Architecture Source: (YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information, 2024)
  • Figure 3: Proposed RepVGG-GELAN. The architecture of RepVGG-GELAN is mainly comprised of RepVGG and RepNCSPELAN4.