Scholarlink

<p>The brain’s unchecked and fast cell development is what fuels a tumor. It may prove lethal if left untreated in the early stages. Even with a lot of work and positive outcomes, accurate segmentation and classification are still challenging. It is quite difficult to diagnose brain tumors because of the variations in tumor position, form, and size. Worldwide, ―Brain Tumors (BTs) are growing extremely quickly. Deadly brain tumors claim thousands of lives each year. For this reason, proper identification and categorization are crucial to brain tumor therapy. Many methods based on ―Deep Learning (DL) and classical ―Machine Learning (ML) have been developed for BT categorization and detection. It takes a lot of effort to create the hand-crafted features needed by the classical ML classifiers. Conversely, Deep Learning (DL) has become a popular tool for detection and classification due to its strong feature extraction capabilities. As a result, we suggested a fusion-based CNN model in this work that uses four distinct classifications to classify brain cancer. Deep and shallow feature fusion and the addition of an attention module improved the feature extraction capabilities. Additionally, several tasks were carried out to improve the classification performance, including parameter fine-tuning, data augmentation, and pre-training. Our fusion model is compatible with ConvNeXt_S and a baseline EfficientNetV2M shows an accuracy of 99.88%.</p>

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

Comparison based on transfer learning and fusion of deep learning models for brain cancer classification

  • 期刊论文

  • 发表日期：

    2025年5月10日

查看全文
  • Yogendra Narayan,
  • Ajay Prakash Pasupulla,
  • Divesh Kumar,
  • Kothapalli Ramesh Chandra,
  • Ram Murat Singh,
  • Piyush Charan,
  • Davinder Paul Singh

摘要

The brain’s unchecked and fast cell development is what fuels a tumor. It may prove lethal if left untreated in the early stages. Even with a lot of work and positive outcomes, accurate segmentation and classification are still challenging. It is quite difficult to diagnose brain tumors because of the variations in tumor position, form, and size. Worldwide, ―Brain Tumors (BTs) are growing extremely quickly. Deadly brain tumors claim thousands of lives each year. For this reason, proper identification and categorization are crucial to brain tumor therapy. Many methods based on ―Deep Learning (DL) and classical ―Machine Learning (ML) have been developed for BT categorization and detection. It takes a lot of effort to create the hand-crafted features needed by the classical ML classifiers. Conversely, Deep Learning (DL) has become a popular tool for detection and classification due to its strong feature extraction capabilities. As a result, we suggested a fusion-based CNN model in this work that uses four distinct classifications to classify brain cancer. Deep and shallow feature fusion and the addition of an attention module improved the feature extraction capabilities. Additionally, several tasks were carried out to improve the classification performance, including parameter fine-tuning, data augmentation, and pre-training. Our fusion model is compatible with ConvNeXt_S and a baseline EfficientNetV2M shows an accuracy of 99.88%.