Scatter correction based on an artificial neural network for 99mTc and 123I dual-isotope SPECT in myocardial and brain imaging
Scatter correction based on an artificial neural network for 99mTc and 123I dual-isotope SPECT in myocardial and brain imaging
复制标题
DOI：
10.1007/bf03033996
复制
发表时间：
2007-01-01
影响因子：
2.6
通讯作者：
Kubo, Atsushi
中科院分区：
文献类型：
--
作者：
Bai, Jingming;Hashimoto, Jun;Kubo, Atsushi
本研究的目的是阐明在Tc-99 m和I-123双同位素SPECT中使用人工神经网络（ANN）进行散射校正的临床实用性。方法：两种算法的ANN散射校正进行了测试：ANN-10和ANN-3采用10和3个能量窗口的数据采集，分别。3例患者接受了心肌或脑SPECT，给予以下放射性药物组合之一：Tc-99 m-替曲膦和I-123-间碘苄胍（MIBG）、Tc-99 m-甲氧基异丁基异腈（MIBI）和I-123-β-甲基-对碘苯基-十五烷酸（BMIPP）或Tc-99 m-乙基-西司他丁二聚体（ECD）和I-123-碘马替尼。这些患者还接受了结合传统三能窗（TEW）散射校正的单同位素成像。串扰和散射校正的Tc-99 m和I-123-SPECT图像在双同位素采集与人工神经网络进行了比较，在单同位素采集。结果：人工神经网络方法能很好地分离I-123和Tc-99 m的原光子。虽然ANN-10产生的图像质量差，ANN-3提供了可比的图像质量与单同位素扫描没有显着增加的采集时间。结论：所提出的方法在临床上是有用的，因为它提供了各种组合的信息，而没有解剖配准与一个采集。
The aim of this study was to elucidate the clinical usefulness of scatter correction with an artificial neural network (ANN) in Tc-99m and I-123 dual-isotope SPECT. Methods: Two algorithms for ANN scatter correction were tested: ANN-10 and ANN-3 employing 10 and 3 energy windows for data acquisition, respectively. Three patients underwent myocardial or brain SPECT with one of the following combinations of radiopharmaceuticals administered: Tc-99m-tetrofosmin and I-123-metaiodobenzylguanidine (MIBG), Tc-99m-methoxyisobutylisonitrile (MIBI) and I-123-beta-methyl-paraiodophenyl-pentadecanoic acid (BMIPP), or Tc-99m-ethyl-cistainate dimmer (ECD) and I-123-iomazenil. The patients were also referred for single-isotope imaging incorporating conventional triple-energy window (TEW) scatter correction. Crosstalk- and scatter-corrected Tc-99m- and I-123-SPECT images in dual-isotope acquisition with ANN were compared with those in single-isotope acquisition. Results: The ANN method well separated I-123 and Tc-99m primary photons. Although ANN-10 yielded images of poor quality, ANN-3 offered comparable image quality with the single-isotope scan without significant increase of acquisition time. Conclusion: The proposed method is clinically useful because it provides various combinations of information without anatomical misregistration with one acquisition.