Scholarlink

Brain tumors are a leading cause of cancer-related deaths worldwide, and their early detection is crucial for effective treatment and improved patient outcomes. This study presents a novel approach for the automatic detection of brain tumors using YOLOv8, a state-of-the-art object detection algorithm. Our dataset consists of 1101 MRI images, divided into 703 training, 175 validation, and 223 testing samples. We fine-tuned the YOLOv8 model to detect brain tumors and achieved an impressive detection accuracy of 0.85. The results demonstrate that the YOLOv8-based approach can effectively identify brain tumors, even in complex cases. The proposed method has the potential to assist radiologists and clinicians in diagnosing brain tumors, thereby improving patient care and treatment outcomes. The high accuracy and efficiency of our approach make it a promising tool for clinical applications, enabling timely and precise diagnosis of brain tumors.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Deep Learning-Based Brain Tumor Detection Using YOLOv8 on MRI Images

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Othmane Zougari,
  • Wafae Abbaoui,
  • Driss Rami,
  • Younes Assini,
  • Assia El Motaoukel,
  • Najib Al Idrissi,
  • Wajih Rhalem

摘要

Brain tumors are a leading cause of cancer-related deaths worldwide, and their early detection is crucial for effective treatment and improved patient outcomes. This study presents a novel approach for the automatic detection of brain tumors using YOLOv8, a state-of-the-art object detection algorithm. Our dataset consists of 1101 MRI images, divided into 703 training, 175 validation, and 223 testing samples. We fine-tuned the YOLOv8 model to detect brain tumors and achieved an impressive detection accuracy of 0.85. The results demonstrate that the YOLOv8-based approach can effectively identify brain tumors, even in complex cases. The proposed method has the potential to assist radiologists and clinicians in diagnosing brain tumors, thereby improving patient care and treatment outcomes. The high accuracy and efficiency of our approach make it a promising tool for clinical applications, enabling timely and precise diagnosis of brain tumors.