Spherical CNN for Medical Imaging Applications: Importance of Equivariance in image reconstruction and denoising
Spherical CNN for Medical Imaging Applications: Importance of Equivariance in image reconstruction and denoising
复制标题
DOI：
10.48550/arxiv.2307.03298
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
Amirreza Hashemi;Yuemeng Feng;H. Sabet
中科院分区：
文献类型：
--
作者：
Amirreza Hashemi;Yuemeng Feng;H. Sabet
这项工作强调了等变网络作为断层扫描应用的高效和高性能方法的重要性。我们的研究建立在传统卷积神经网络（cnn）的局限性之上，它在各种医学成像系统的后处理中显示出前景。然而，传统cnn的效率在很大程度上依赖于一个未减少的和适当的训练集。为了解决这个问题，在本研究中，我们引入了一个等变网络，旨在减少CNN对特定训练集的依赖。我们评估了等变球形cnn （SCNNs）在二维和三维医学成像问题中的效果。我们的研究结果表明，scnn在去噪和重构基准问题方面具有卓越的质量和计算效率。此外，我们提出了一种新的方法，将scnn作为传统图像重建工具的补充，在提高结果的同时减少对训练集的依赖。在所有情况下，我们观察到与cnn相比，使用scnn在保持相同或更高质量的图像处理的同时，计算成本显著降低。此外，我们探索了该网络在更广泛的断层扫描应用中的潜力，特别是那些需要全方位表示的应用。
This work highlights the significance of equivariant networks as efficient and high-performance approaches for tomography applications. Our study builds upon the limitations of conventional Convolutional Neural Networks (CNNs), which have shown promise in post-processing various medical imaging systems. However, the efficiency of conventional CNNs heavily relies on an undiminished and proper training set. To tackle this issue, in this study, we introduce an equivariant network, aiming to reduce CNN’s dependency on specific training sets. We evaluate the efficacy of equivariant spherical CNNs (SCNNs) for 2- and 3-dimensional medical imaging problems. Our results demonstrate superior quality and computational efficiency of SCNNs in denoising and reconstructing benchmark problems. Furthermore, we propose a novel approach to employ SCNNs as a complement to conventional image reconstruction tools, enhancing the outcomes while reducing reliance on the training set. Across all cases, we observe a significant decrease in computational costs while maintaining the same or higher quality of image processing using SCNNs compared to CNNs. Additionally, we explore the potential of this network for broader tomography applications, particularly those requiring omnidirectional representation.