Comparative assessment of noise properties for two deep learning CT image reconstruction techniques and filtered back projection
Comparative assessment of noise properties for two deep learning CT image reconstruction techniques and filtered back projection
复制标题
两种深度学习 CT 图像重建技术和滤波反投影噪声特性的比较评估
DOI：
10.1002/mp.15918
复制
发表时间：
2022
期刊：
影响因子：
3.8
通讯作者：
Seto Issei
中科院分区：
文献类型：
--
作者：
Kawashima Hiroki;Ichikawa Katsuhiro;Takata Tadanori;Seto Issei
BackgroundTwo deep learning image reconstruction（DLIR）techniques from two different computed tomography（CT）vendors have recently brought into clinical practice.PurposeTo characterize noise properties of two DLIR techniques with different training methods，using a phantom containing a simple uniform region and a complex non-uniform region.MethodsA water‐bath phantom with a diameter of 300 mm was used as a base phantom.将一个直径为128 mm的毛面体模放置在基础体模中，该体模由两种材料制成，一种相当于水，另一种是12 mg/ml稀释碘，不规则混合以产生复杂纹理（非均匀区域）。使用两台CT扫描仪（Revolution CT with Apex Edition，GE Healthcare; Aquarium One PRISM Edition，Canon Medical Systems）在两个剂量水平（CT剂量指数：5和15 mGy）下进行30次重复体模扫描。使用每个CT系统的滤波反投影（FBP）和DLIR [TrueFidelity（TF），GE Healthcare; Advanced intelligent Clear‐IQ Engine Body Sharp（AC），Canon Medical Systems]重建三种工艺强度的图像。对于噪声的基本特征，测量了均匀（水）区域的标准差（SD）和噪声功率谱（NPS）。通过计算30幅图像中每个像素位置的图像间SD生成噪声幅度图。然后，计算噪声降低图（NRM），其可视化FBP和DLIR之间的噪声幅度的相对差异。NRM值范围为0.0至1.0。较低的NRM值表示较不积极的降噪。NRM值的直方图进行了分析的均匀和非均匀regions.ResultsThe噪声幅度的减少与FBP相比，往往是更大的AC（45%-85%）比TF（32%-65%）。除了低剂量条件和AC的高降噪强度外，TF和AC的平均噪声频率几乎与FBP相当。TF和AC的NRM值在均匀区域中高于非均匀区域。在非均匀区域，TF的平均NRM值（0.21-0.48）倾向于低于AC的（0.39-0.78）。TF的直方图显示均匀区域和非均匀区域之间的小重叠;相比之下，AC的直方图显示更大的重叠。这种差异似乎表明TF处理均匀和非均匀区域的方式比AC更加不同。ConclusionThis study has revealed a distinct difference in characteristics between two DLIR techniques：TF倾向于在非均匀区域中提供不太积极的降噪并保留原始信号，而AC倾向于优先考虑噪声滤波而不是边缘保留，特别是在低剂量和高降噪强度的情况下。
BackgroundTwo deep learning image reconstruction (DLIR) techniques from two different computed tomography (CT) vendors have recently been introduced into clinical practice.PurposeTo characterize the noise properties of two DLIR techniques with different training methods, using a phantom containing a simple uniform and a complex non‐uniform region.MethodsA water‐bath phantom with a diameter of 300 mm was used as a base phantom. A textured phantom with a diameter of 128 mm, which was made of two materials, one equivalent to water and the other being 12 mg/ml diluted iodine, irregularly mixed to create a complex texture (non‐uniform region), was placed in the base phantom. Thirty repeated phantom scans were performed using two CT scanners (Revolution CT with Apex Edition, GE Healthcare; Aquilion One PRISM Edition, Canon Medical Systems) at two dose levels (CT dose index: 5 and 15 mGy). Images were reconstructed with each CT system's filtered back projection (FBP) and DLIR [TrueFidelity (TF), GE Healthcare; Advanced intelligent Clear‐IQ Engine Body Sharp (AC), Canon Medical Systems] for three process strengths. For basic characteristics of noise, the standard deviation (SD) and noise power spectrum (NPS) were measured for the uniform (water) region. A noise magnitude map was generated by calculating the inter‐image SD at each pixel position across the 30 images. Then, a noise reduction map (NRM), which visualizes the relative differences in noise magnitude between FBP and DLIR, was calculated. The NRM values ranged from 0.0 to 1.0. A low NRM value represents a less aggressive noise reduction. The histograms of the NRM value were analyzed for the uniform and non‐uniform regions.ResultsThe reduction in noise magnitude compared with FBP tended to be greater with AC (45%–85%) than with TF (32%–65%). The average NPS frequencies of TF and AC were almost comparable to those of FBP, except for the low‐dose condition and the high noise reduction strength for AC. The NRM values of TF and AC were higher in the uniform region than in the non‐uniform region. In the non‐uniform region, TF's average NRM values (0.21–0.48) tended to be lower than AC's (0.39–0.78). The histograms for TF showed a small overlap between the uniform and the non‐uniform regions; in contrast, those for AC showed a greater overlap. This difference seems to indicate that TF processes the uniform and non‐uniform regions more differently than AC does.ConclusionThis study has revealed a distinct difference in characteristics between the two DLIR techniques: TF tends to offer less aggressive noise reduction in non‐uniform regions and preserve the original signals, whereas AC tends to prioritize noise filtering over edge‐preservation, especially at the low‐dose condition and with the high noise reduction strength.