MRI扫描中股骨分割的深度学习模型性能分析
Performance Analysis of Deep Learning Models for Femur Segmentation in MRI Scan
AI总结：
本文系统比较了U-Net、Attention U-Net、U-KAN和SAM 2在MRI股骨分割中的性能，基于11,164张标注扫描图像，发现Attention U-Net总体表现最佳，而U-KAN在小感兴趣区域上更具优势。
摘要：
卷积神经网络（如U-Net）在医学图像分割中表现优异，而注意力机制和KAN则增强了特征提取能力。Meta的SAM 2利用Vision Transformers实现基于提示的分割，无需微调。然而，这些模型中的偏差会影响其在有限数据下的泛化能力。在本研究中，我们系统评估并比较了三种基于CNN的模型，即U-Net、Attention U-Net和U-KAN，以及一种基于Transformer的模型，即SAM 2，在MRI扫描中分割股骨结构的性能。数据集包含11,164张MRI扫描图像，并带有详细的股骨区域标注。性能采用Dice相似系数进行评估，其范围从0.932到0.954。Attention U-Net取得了最高的总体得分，而U-KAN在感兴趣区域较小的解剖区域中表现出更优的性能，利用其增强的学习能力提高了分割精度。
英文摘要：
Convolutional neural networks like U-Net excel in medical image segmentation, while attention mechanisms and KAN enhance feature extraction. Meta's SAM 2 uses Vision Transformers for prompt-based segmentation without fine-tuning. However, biases in these models impact generalization with limited data. In this study, we systematically evaluate and compare the performance of three CNN-based models, i.e., U-Net, Attention U-Net, and U-KAN, and one transformer-based model, i.e., SAM 2 for segmenting femur bone structures in MRI scan. The dataset comprises 11,164 MRI scans with detailed annotations of femoral regions. Performance is assessed using the Dice Similarity Coefficient, which ranges from 0.932 to 0.954. Attention U-Net achieves the highest overall scores, while U-KAN demonstrated superior performance in anatomical regions with a smaller region of interest, leveraging its enhanced learning capacity to improve segmentation accuracy.
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。
