Brain tumor classification is highly effective in identifying and diagnosing the exact location of the tumor in the brain. The medical imaging system reported that early diagnosis and classification of the tumor increases the life of the human. Among various imaging modalities, magnetic resonance imaging (MRI) is highly used by clinical experts, as it offers contrast information of brain tumors. An effective classification method named fractional-chicken swarm optimization (fractional-CSO) is introduced to perform the severity-level tumor classification. Here, the chicken swarm behavior is merged with the derivative factor to enhance the accuracy of severity level classification. The optimal solution is obtained by updating the position of the rooster, which updates their location based on better fitness value. The brain images are pre-processed and the features are effectively extracted, and the cancer classification is carried out. Moreover, the severity level of tumor classification is performed using the deep recurrent neural network, which is trained by the proposed fractional-CSO algorithm. Moreover, the performance of the proposed fractional-CSO attained better performance in terms of the evaluation metrics, such as accuracy, specificity and sensitivity with the values of 93.35, 96 and 95% using simulated BRATS dataset, respectively.

中文翻译：

---

使用分数-鸡群优化算法的基于 MRI 图像的脑肿瘤严重程度分类

脑肿瘤分类在识别和诊断肿瘤在脑中的确切位置方面非常有效。医学影像系统报告说，肿瘤的早期诊断和分类可以延长人类的寿命。在各种成像方式中，磁共振成像 (MRI) 被临床专家高度使用，因为它提供了脑肿瘤的对比信息。引入了一种称为分数鸡群优化（分数-CSO）的有效分类方法来执行严重程度的肿瘤分类。在这里，鸡群行为与导数因子相结合，以提高严重程度分类的准确性。最优解是通过更新公鸡的位置来获得的，公鸡根据更好的适应度值更新它们的位置。对脑部图像进行预处理，有效提取特征，进行癌症分类。此外，肿瘤分类的严重程度是使用深度递归神经网络执行的，该网络由所提出的分数 CSO 算法训练。此外，所提出的分数 CSO 的性能在评估指标方面取得了更好的性能，例如使用模拟 BRATS 数据集的准确性、特异性和敏感性分别为 93.35、96 和 95%。