Awasthi Vishal, Tiwari Mamta, Yadav Amit, Thakur Gesu, Panda Mamata Mayee, Kumar Hemant, Tripathi Shivneet
Department of Electronics and Communication Engineering, Chhatrapati Shahu Ji Maharaj University, Kanpur, India.
Department of Computer Application, Chhatrapati Shahu Ji Maharaj University, Kanpur, India.
MethodsX. 2025 Mar 7;14:103255. doi: 10.1016/j.mex.2025.103255. eCollection 2025 Jun.
This study presents an automated framework for brain tumor classification aimed at accurately distinguishing tumor types in MRI images. The proposed model integrates InceptionResNetV2 for feature extraction with Deep Stacked Autoencoders (DSAEs) for classification, enhanced by sparsity regularization and the SwiGLU activation function. InceptionResNetV2, pre-trained on ImageNet, was fine-tuned to extract multi-scale features, while the DSAE structure compressed these features to highlight critical attributes essential for classification. The approach achieved high performance, reaching an overall accuracy of 99.53 %, precision of 98.27 %, recall of 99.21 %, specificity of 98.73 %, and an F1-score of 98.74 %. These results demonstrate the model's efficacy in accurately categorizing glioma, meningioma, pituitary tumors, and non-tumor cases, with minimal misclassifications. Despite its success, limitations include the model's dependency on pre-trained weights and significant computational resources. Future studies should address these limitations by enhancing interpretability, exploring domain-specific transfer learning, and validating on diverse datasets to strengthen the model's utility in real-world settings. Overall, the InceptionResNetV2 integrated with DSAEs, sparsity regularization, and SwiGLU offers a promising solution for reliable and efficient brain tumor diagnosis in clinical environments.•Leveraging a pre-trained InceptionResNetV2 model to capture multi-scale features from MRI data.•Utilizing Deep Stacked Autoencoders with sparsity regularization to emphasize critical attributes for precise classification.•Incorporating the SwiGLU activation function to capture complex, non-linear patterns within the data.
本研究提出了一种用于脑肿瘤分类的自动化框架，旨在准确区分MRI图像中的肿瘤类型。所提出的模型将用于特征提取的InceptionResNetV2与用于分类的深度堆叠自动编码器（DSAE）集成在一起，并通过稀疏正则化和SwiGLU激活函数进行增强。在ImageNet上预训练的InceptionResNetV2经过微调以提取多尺度特征，而DSAE结构则压缩这些特征以突出对分类至关重要的关键属性。该方法取得了高性能，总体准确率达到99.53%，精确率为98.27%，召回率为99.21%，特异性为98.73%，F1分数为98.74%。这些结果证明了该模型在准确分类胶质瘤、脑膜瘤、垂体瘤和非肿瘤病例方面的有效性，错误分类极少。尽管取得了成功，但局限性包括该模型对预训练权重的依赖以及大量的计算资源。未来的研究应通过增强可解释性、探索特定领域的迁移学习以及在不同数据集上进行验证来解决这些局限性，以加强该模型在现实世界环境中的实用性。总体而言，与DSAE、稀疏正则化和SwiGLU集成的InceptionResNetV2为临床环境中可靠且高效的脑肿瘤诊断提供了一个有前景的解决方案。
•利用预训练的InceptionResNetV2模型从MRI数据中捕获多尺度特征。
•使用带有稀疏正则化的深度堆叠自动编码器来强调用于精确分类的关键属性。
•纳入SwiGLU激活函数以捕获数据中的复杂非线性模式。
