arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.20299cs.LGcs.AI
收藏

DB-FGA-Net:双主干频率门控注意力网络用于具有Grad-CAM可解释性的多类脑肿瘤分类

DB-FGA-Net: Dual Backbone Frequency Gated Attention Network for Multi-Class Brain Tumor Classification with Grad-CAM Interpretability

Dept. of Electronics and Telecommunication Engineering, Rajshahi University of Engineering and Technology(电子与电信工程系,拉贾沙希工程与技术大学)

Saraf Anzum Shreya, MD. Abu Ismail Siddique, Sharaf Tasnim

AI总结:

本文提出一种双主干网络,结合VGG16和Xception,通过频率门控注意力模块捕捉局部和全局特征,实现无需数据增强的高准确率分类,并通过Grad-CAM可视化提升临床可解释性。

摘要:

脑肿瘤是神经肿瘤学中的挑战性问题,早期和精确的诊断对成功治疗至关重要。基于深度学习的脑肿瘤分类方法通常依赖大量数据增强,这可能限制泛化能力和临床应用的可信度。本文提出一种双主干网络,整合VGG16和Xception,并采用频率门控注意力(FGA)模块以捕捉互补的局部和全局特征。我们的模型在不进行数据增强的情况下实现了高度竞争性的性能,证明了其在可变大小和分布数据集上的鲁棒性。为了进一步提高透明度,Grad-CAM被集成以可视化肿瘤区域,从而在模型预测和临床可解释性之间建立桥梁。所提出的框架在7K-DS数据集上实现了99.24%的准确率(4类设置),同时在3类和2类设置中分别达到98.68%和99.85%。在独立的3K-DS数据集上,模型在相同实验条件下实现了95.77%的准确率,优于几种基线方法。为了进一步支持临床应用,我们开发了一个图形用户界面(GUI),提供实时分类和基于Grad-CAM的肿瘤定位。这些发现表明,无需数据增强、可解释且可部署的深度学习模型,如DB-FGA-Net,具有在脑肿瘤诊断中实现可靠临床转化的强大潜力。

英文摘要:

Brain tumors are a challenging problem in neuro-oncology, where early and precise diagnosis is important for successful treatment. Deep learning-based brain tumor classification methods often rely on heavy data augmentation which can limit generalization and trust in clinical applications. In this paper, we propose a double-backbone network integrating VGG16 and Xception with a Frequency-Gated Attention (FGA) Block to capture complementary local and global features. Our model achieves highly competitive performance without augmentation which demonstrates robustness to variably sized and distributed datasets. For further transparency, Grad-CAM is integrated to visualize the tumor regions based on which the model is giving prediction, bridging the gap between model prediction and clinical interpretability. The proposed framework achieves 99.24% accuracy on the 7K-DS dataset for the 4-class setting, along with 98.68% and 99.85% in the 3-class and 2-class settings, respectively. On the independent 3K-DS dataset, the model generalizes with 95.77% accuracy, outperforming several baseline methods under the same experimental setting. To further support clinical usability, we developed a graphical user interface (GUI) that provides real-time classification and Grad-CAM-based tumor localization. These findings suggest that augmentation-free, interpretable, and deployable deep learning models such as DB-FGA-Net hold strong potential for reliable clinical translation in brain tumor diagnosis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑