生成对抗网络在实验性光声成像中去除伪影的可行性
本研究探索基于深度学习的生成对抗网络(GAN)用于光声断层成像重建中的去噪和伪影去除,以改善稀疏采样和随机噪声导致的图像质量下降。采用U-net变体作为生成器网络,定量评估显示结构相似性指数为0.980 ± 0.043,峰值信噪比为31 ± 0.002 dB,表明所提方案在低质量数据集训练下仍能输出高分辨率图像。
要点
- GAN结合U-net生成器可对光声断层成像进行去噪和伪影去除。
- 定量评估结构相似性指数为0.980 ± 0.043,峰值信噪比为31 ± 0.002 dB。
- 在低质量数据集训练下仍能输出高分辨率图像。
核心结论
- 基于GAN的方法通过去噪和去除稀疏采样伪影改善光声断层成像图像质量,定量指标显示结构相似性指数为0.980 ± 0.043、峰值信噪比为31 ± 0.002 dB,在低质量数据集训练下仍可输出高分辨率图像。
研究设计与样本
- 实验性光声断层成像研究,采用基于深度学习的生成对抗网络(GAN),以U-net变体作为生成器网络,通过定量和定性分析验证性能。
诊断标准与关键数值
- 定量评估指标:结构相似性指数=0.980 ± 0.043,峰值信噪比=31 ± 0.002 dB。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
Photoacoustic tomography (PAT) reconstruction is an expeditiously growing interest among biomedical researchers because of its possible transition from laboratory to clinical pre-eminence. Nonetheless, the PAT inverse problem is yet to achieve an optimal solution in rapid and precise reconstruction under practical constraints. Precisely, the sparse sampling problem and random noise are the main impediments to attaining accuracy but in support of rapid PAT reconstruction. The limitations are associated with acquiring undersampled artifacts that deteriorate the optimality of the reconstruction task. Therefore, the former achievements of fast image formation limit the modality for clinical settings. Delving into the problem, here we explore a deep learning-based generative adversarial network (GAN) to improve the image quality by denoising and removing these artifacts. The specially designed attributes and unique manner of optimizing the problem, such as incorporating the data set limitations and providing stable training performance, constitute the main motivation behind the employment of GAN. Moreover, exploitation of the U-net variant as a generator network offers robust performance in terms of quality and computational cost, which is further validated with the detailed quantitative and qualitative analysis. The quantitatively evaluated structured similarity indexing method = 0.980 ± 0.043 and peak signal-to-noise ratio = 31 ± 0.002 dB state that the proposed solution provides the high-resolution image at the output, even training with a low-quality data set.
引用
- Shahid, Khalid, Yue, et al. Feasibility of a Generative Adversarial Network for Artifact Removal in Experimental Photoacoustic Imaging. Ultrasound Med Biol. 2022. PMID: 35660105. doi:10.1016/j.ultrasmedbio.2022.04.008
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。