arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.13335cs.CV
收藏

利用有限标注样本进行脑膜瘤分析与诊断

Meningioma Analysis and Diagnosis using Limited Labeled Samples

Shaanxi University of Science and Technology(陕西科技大学);Department of Neurosurgery, The First Affiliated Hospital of Xi'an Jiaotong University(西安交通大学第一附属医院神经外科);Department of Neurosurgery, The First Affiliated Hospital of Fujian Medical University(福建医科大学第一附属医院神经外科);Department of Radiotherapy, University of Groningen, University Medical Center Groningen(格罗宁根大学放射治疗科,格罗宁根大学医学中心);Department of Nephrology, Chenggong Hospital Affiliated to Xiamen University(厦门大学附属晋江医院肾内科)

Jiamiao Lu, Wei Wu, Ke Gao, Ping Mao, Weichuan Zhang, Tuo Wang, Lingkun Ma, Jiapan Guo, Zanyi Wu, Yuqing Hu, Changming Sun

AI总结:

本文提出了一种基于特征融合和自适应权重的少样本脑膜瘤学习方法,通过引入新的MRI数据集验证了其在脑膜瘤分类中的优越性能。

摘要:

脑膜瘤的生物学行为和治疗反应取决于其分级,因此准确的诊断对于治疗计划和预后评估至关重要。我们观察到,空间频域特征的加权融合显著影响脑膜瘤分类性能。值得注意的是,通过离散小波变换获得的特定频率带的贡献在不同图像中变化较大。本文提出了一种具有不同频率带信息和空间域信息自适应权重的特征融合架构,用于少样本脑膜瘤学习。为验证所提方法的有效性,引入了一个新的脑膜瘤MRI数据集。实验结果表明,所提方法在三个数据集上均优于现有最先进的方法。代码将在:https://github.com/ICL-SUST/AMSF-Net 上提供。

英文摘要:

The biological behavior and treatment response of meningiomas depend on their grade, making an accurate diagnosis essential for treatment planning and prognosis assessment. We observed that the weighted fusion of spatial-frequency domain features significantly influences meningioma classification performance. Notably, the contribution of specific frequency bands obtained by discrete wavelet transform varies considerably across different images. A feature fusion architecture with adaptive weights of different frequency band information and spatial domain information is proposed for few-shot meningioma learning. To verify the effectiveness of the proposed method, a new MRI dataset of meningiomas is introduced. The experimental results demonstrate the superiority of the proposed method compared with existing state-of-the-art methods in three datasets. The code will be available at: https://github.com/ICL-SUST/AMSF-Net

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。

↑