Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.
Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.
Z Med Phys. 2024 May;34(2):258-269. doi: 10.1016/j.zemedi.2023.07.005. Epub 2023 Aug 4.
This research aims to develop a feature-guided deep learning approach and compare it with an optimized conventional post-processing algorithm in order to enhance the image quality of diffusion-weighted liver images and, in particular, to reduce the pulsation-induced signal loss occurring predominantly in the left liver lobe.
Data from 40 patients with liver lesions were used. For the conventional approach, the best-suited out of five examined algorithms was chosen. For the deep learning approach, a U-Net was trained. Instead of learning "gold-standard" target images, the network was trained to optimize four image features (lesion CNR, vessel darkness, data consistency, and pulsation artifact reduction), which could be assessed quantitatively using manually drawn ROIs. A quality score was calculated from these four features. As an additional quality assessment, three radiologists rated different features of the resulting images.
The conventional approach could substantially increase the lesion CNR and reduce the pulsation-induced signal loss. However, the vessel darkness was reduced. The deep learning approach increased the lesion CNR and reduced the signal loss to a slightly lower extent, but it could additionally increase the vessel darkness. According to the image quality score, the quality of the deep-learning images was higher than that of the images obtained using the conventional approach. The radiologist ratings were mostly consistent with the quantitative scores, but the overall quality ratings differed among the readers.
Unlike the conventional algorithm, the deep-learning algorithm increased the vessel darkness. Therefore, it may be a viable alternative to conventional algorithms.
本研究旨在开发一种基于特征的深度学习方法，并将其与经过优化的传统后处理算法进行比较，以提高扩散加权肝脏图像的质量，特别是降低主要发生在左肝叶的搏动伪影引起的信号丢失。
使用了 40 名肝脏病变患者的数据。对于传统方法，选择了五种检查算法中最合适的一种。对于深度学习方法，训练了一个 U-Net。与学习“金标准”目标图像不同，该网络被训练为优化四个图像特征（病变对比度噪声比、血管暗化、数据一致性和搏动伪影减少），这可以使用手动绘制的 ROI 进行定量评估。从这四个特征计算出一个质量分数。作为附加的质量评估，三位放射科医生对生成图像的不同特征进行了评分。
传统方法可以显著提高病变对比度噪声比，并减少搏动引起的信号丢失。然而，血管暗化程度降低了。深度学习方法在稍低的程度上提高了病变对比度噪声比并减少了信号丢失，但它还可以增加血管暗化程度。根据图像质量评分，深度学习图像的质量高于传统方法获得的图像。放射科医生的评分与定量评分大多一致，但总体质量评分在读者之间存在差异。
与传统算法不同，深度学习算法增加了血管暗化程度。因此，它可能是传统算法的一种可行替代方案。
