arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.03300eess.IVcs.CV

Spach Transformer：基于局部与全局自注意力的空间与通道 Transformer，用于 PET 图像去噪

Spach Transformer: Spatial and Channel-wise Transformer Based on Local and Global Self-attentions for PET Image Denoising

Gordon Center for Medical Imaging（戈登医学影像中心）；Center for Advanced Medical Computing and Analysis（高级医学计算与分析中心）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；University of Florida（佛罗里达大学）；University of Texas MD Anderson Cancer Center（德克萨斯大学MD安德森癌症中心）；Johns Hopkins University（约翰斯·霍普金斯大学）

Se-In Jang, Tinsu Pan, Ye Li, Pedram Heidari, Junyu Chen, Quanzheng Li, Kuang Gong

备注：
15 pages
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对 PET 图像噪声及三维全局自注意力计算成本高的问题，提出融合局部与全局 MSA 的空间通道编解码 Transformer，并在多示踪剂数据集上验证其去噪性能优于现有深度学习架构。

摘要：

正电子发射断层成像（PET）因其定量优势和高灵敏度而被广泛应用于临床和研究，但其信噪比较低（SNR）。近年来，卷积神经网络（CNN）已被广泛用于改善 PET 图像质量。尽管 CNN 在局部特征提取方面成功且高效，但由于感受野有限，它不能很好地捕捉长程依赖关系。全局多头自注意力（MSA）是捕捉长程信息的常用方法。然而，针对三维图像计算全局 MSA 具有很高的计算成本。在本工作中，我们提出了一种高效的空间与通道编解码 Transformer——Spach Transformer，它能够基于局部和全局 MSA 利用空间与通道信息。我们基于不同 PET 示踪剂（即 ¹⁸F-FDG、¹⁸F-ACBC、¹⁸F-DCFPyL 和 ⁶⁸Ga-DOTATATE）的数据集开展实验，以评估所提出的框架。定量结果表明，所提出的 Spach Transformer 框架优于最先进的深度学习架构。我们的代码可在 https://github.com/sijang/SpachTransformer 获取。

英文摘要：

Position emission tomography (PET) is widely used in clinics and research due to its quantitative merits and high sensitivity, but suffers from low signal-to-noise ratio (SNR). Recently convolutional neural networks (CNNs) have been widely used to improve PET image quality. Though successful and efficient in local feature extraction, CNN cannot capture long-range dependencies well due to its limited receptive field. Global multi-head self-attention (MSA) is a popular approach to capture long-range information. However, the calculation of global MSA for 3D images has high computational costs. In this work, we proposed an efficient spatial and channel-wise encoder-decoder transformer, Spach Transformer, that can leverage spatial and channel information based on local and global MSAs. Experiments based on datasets of different PET tracers, i.e., $^{18}$F-FDG, $^{18}$F-ACBC, $^{18}$F-DCFPyL, and $^{68}$Ga-DOTATATE, were conducted to evaluate the proposed framework. Quantitative results show that the proposed Spach Transformer framework outperforms state-of-the-art deep learning architectures. Our codes are available at https://github.com/sijang/SpachTransformer

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。

↑