Skip to search boxSkip to navigationSkip to main content

An enhanced YOLOv8 framework for MRI brain tumor detection: Integrating dense connectivity and dynamic attention mechanisms

  • Ziyi Wang
    ,
  • Li Li
    ,
  • Zuobin Wang
    ,
  • Fujun Wang
    ,
  • Dayou Li
    ,
  • Lu Wang
Research Output: Chapter in Book/Report/Conference proceeding Conference contribution Peer-review

Abstract

This paper explores core obstacles in the application of object detection models to medical imaging, focusing on issues stemming from scale variation and fuzzy boundaries in MRI brain tumor analysis. We propose an improved detection framework that integrates a lightweight efficient backbone with a high-resolution detection strategy. Research centers on two core directions: optimizing internal feature extraction via dense connectivity and dynamic convolution, and enhancing cross-scale information fusion. Based on the You Only Look Once version 8 (YOLOv8) architecture, we develop a paradigm that replaces the standard C2f module with a fused CSP-DenseNet and KernelWarehouse structure. Subsequently, we introduce a Generalized Feature Pyramid Network (GFPN) embedded with Bi-directional Routing Attention (BRA) to capture long-range dependencies. Furthermore, the framework expands the detection logic to include a fourth highresolution head specifically for micro-tumor identification. Empirical validation on brain tumor datasets demonstrates significant improvements over existing baselines. Major breakthroughs are achieved in small object recall and mean Average Precision (mAP), with the proposed model achieving a 4.7% increase in [email protected] and an 11.2% improvement in micro-lesion recall while maintaining real-time performance. Consequently, this research offers a novel perspective for clinical early diagnosis systems.

Publication Information

Output type

Research Output: Chapter in Book/Report/Conference proceeding Conference contribution Peer-review

Host publication Subtitle

SPIE Digital Library

Original language

English

Article number

141720W

Publication milestones

  • Published - 15/04/2026

Publication status

Published - 15/04/2026

Volume

14172

Publisher

SPIE, United States

Publication series

  • Publication series name: Proceedings of SPIE - The International Society for Optical Engineering
    ISSN (Print): 0277-786X
    ISSN (Electronic): 1996-756X
    Volume: 14172

ISBN (Electronic)

9798902323983

External Publication IDs

  • Scopus: 105039472018

Host publication title

International Conference on Pattern Recognition and Image Analysis, PRIA 2025

Host publication editors

  • Jixin Ma
  • Philippe Fournier-Viger
  • Qian Zheng
  • Deepak Kumar Jain

Access to documents