用于胸部CT分割中多尺度特征学习的强度-空间双掩码自编码器
Intensity-Spatial Dual Masked Autoencoder for Multi-Scale Feature Learning in Chest CT Segmentation
AI总结：
本文提出ISD-MAE双分支掩码自编码器，通过强度与空间掩码及对比学习增强胸部CT多尺度组织和边界特征表示，在二维肺炎与纵隔肿瘤分割中性能领先。
摘要：
在医学图像分割领域，病灶特征不明显、边界模糊以及多尺度特性等挑战长期存在。本文提出了一种名为强度-空间双掩码自编码器（Intensity-Spatial Dual Masked AutoEncoder，ISD-MAE）的改进方法。该方法以组织对比度半掩码自编码器为基础，引入一个掩码自编码器（Masked AutoEncoder，MAE）分支，对胸部CT图像执行强度掩码和空间掩码操作，以用于多尺度特征学习和分割任务。该模型利用双分支结构和对比学习来增强学习组织特征与边界细节的能力。实验在多个二维和三维数据集上进行。结果表明，ISD-MAE在二维肺炎和纵隔肿瘤分割任务中显著优于其他方法。例如，在COVID19 LESION数据集上Dice分数达到90.10%，且性能相对稳定。然而，其在三维数据集上仍有提升空间。针对这一点，本文提出了改进方向，包括优化损失函数、使用增强的三维卷积块以及从多个视角处理数据集。我们的代码可在https://github.com/prowontheus/ISD-MAE获取。
英文摘要：
In the field of medical image segmentation, challenges such as indistinct lesion features, ambiguous boundaries,and multi-scale characteristics have long revailed. This paper proposes an improved method named Intensity-Spatial Dual Masked AutoEncoder (ISD-MAE). Based on the tissue-contrast semi-masked autoencoder, a Masked AutoEncoder (MAE) branch is introduced to perform intensity masking and spatial masking operations on chest CT images for multi-scale feature learning and segmentation tasks. The model utilizes a dual-branch structure and contrastive learning to enhance the ability to learn tissue features and boundary details. Experiments are conducted on multiple 2D and 3D datasets. The results show that ISD-MAE significantly outperforms other methods in 2D pneumonia and mediastinal tumor segmentation tasks. For example, the Dice score reaches 90.10% on the COVID19 LESION dataset, and the performance is relatively stable. However, there is still room for improvement on 3D datasets. In response to this, improvement directions are proposed, including optimizing the loss function, using enhanced 3D convolution blocks, and processing datasets from multiple perspectives.Our code is available at:https://github.com/prowontheus/ISD-MAE.
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。
