Scholarlink

For prompt diagnosis and therapy, brain tumor detection is essential. In the current study, a more sophisticated framework for object localization based on YOLOv8 is designed to be employed in conjunction with a Convolutional Neural Network based on ResNet for the particular categorization of MRI images. In exchange, a model is created that incorporates the advantages of ResNet50 feature extraction and YOLOv8 object recognition to determine whether a tumor is present in the patient and where it is located. All of these factors help the model perform better than current CNN techniques, detecting more accurately and producing fewer false positives. The experimental results suggest that this model may provide real-time diagnostic support and has immense advantages for early detection with minimal inaccuracy in a clinical setting.

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

Enhanced Brain Tumor Detection Using YOLOv8 and ResNet-Based CNN

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • B. Hanisha,
  • Ch. Nanda Krishna,
  • G. Teja,
  • K. Kesava

摘要

For prompt diagnosis and therapy, brain tumor detection is essential. In the current study, a more sophisticated framework for object localization based on YOLOv8 is designed to be employed in conjunction with a Convolutional Neural Network based on ResNet for the particular categorization of MRI images. In exchange, a model is created that incorporates the advantages of ResNet50 feature extraction and YOLOv8 object recognition to determine whether a tumor is present in the patient and where it is located. All of these factors help the model perform better than current CNN techniques, detecting more accurately and producing fewer false positives. The experimental results suggest that this model may provide real-time diagnostic support and has immense advantages for early detection with minimal inaccuracy in a clinical setting.