使用图形模型改进的多能CT材料分解 CNN
Zaifeng Shi1,2, Fanning Kong3, Ming Cheng3
1School of Microelectronics, Tianjin University, Tianjin, 300072, China. shizaifeng@tju.edu.cn.
Medical & biological engineering & computing
|December 30, 2023
概括
这项研究引入了一种基于图形的U-net,用于光谱CT多材料分解,通过减少噪音和文物显著提高图像质量. 通过更好的组织组成估计,GECCU-net提高了疾病诊断的准确性.
科学领域:
- 医疗成像医学成像
- 人工智能的人工智能
- 图像处理 图像处理
背景情况:
- 在光谱CT中精确地估计组织成分依赖于物质分解,这对于疾病诊断至关重要.
- 传统的卷积神经网络 (CNN) 难以捕捉精确材料分解所必需的非局部特征.
- 现有的方法在为多材料分解 (MMD) 提取全面图像特征方面存在局限性.
研究的目的:
- 开发一种新的多材料分解 (MMD) 方法,使用基于图形的U-net架构 (GECCU-net) 来提高光谱CT材料的图像质量.
- 改善局部和非局部特征的提取,以便更准确地分析组织成分.
- 减少光谱CT图像中的噪音和人工物,从而提高诊断准确度.
主要方法:
- 提出了一种新的GECCU-net,包括一个多级编码器和本地和非本地特征聚合 (LNFA) 块.
- 在非欧几里德空间上利用图形边缘条件的卷积来有效地提取非局部特征.
- 实现了混合损失函数来处理多尺度输入,并防止结果过度平滑.
主要成果:
- 与基线CNN模型相比,GECCU-net生成的材料图像噪声和文物减少.
- 该方法成功地保留了更详细的组织信息.
- 达到了高的结构相似性 (SSIM) 值 (腹部为0.9976,胸部为0.9990) 和低的RMSE (腹部为0.1218 g/cm3,胸部为0.4903 g/cm3).
结论:
- 拟议的GECCU-net方法显著提高了光谱CT成像中的多材料分解 (MMD) 性能.
- 该技术提供了更好的图像质量,对于准确的疾病诊断至关重要.
- GECCU-net显示了在先进的医学成像分析中广泛应用的潜力.
相关概念视频
01:10Computed Tomography
4.5K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
4.5K
01:20Deconvolution
162
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
162