Department of Radiological Technology, Radiological Diagnosis, National Cancer Center Hospital, 5-1-1 Tsukiji, Chuo-Ku, Tokyo, 104-0045, Japan.
Clinical Product Specialist Marketing Group, FUJIFILM Corporation, 7-3, Akasaka 9-Chome Minato-Ku, Tokyo, Japan.
Phys Eng Sci Med. 2023 Dec;46(4):1713-1721. doi: 10.1007/s13246-023-01331-7. Epub 2023 Sep 19.
This study aimed to assess the image characteristics of deep-learning-based image processing software (DLIP; FCT PixelShine, FUJIFILM, Tokyo, Japan) and compare it with filtered back projection (FBP), model-based iterative reconstruction (MBIR), and deep-learning-based reconstruction (DLR).
This phantom study assessed the object-specific spatial resolution (task-based transfer function [TTF]), noise characteristics (noise power spectrum [NPS]), and low-contrast detectability (low-contrast object-specific contrast-to-noise ratio [CNR]) at three different output doses (standard: 10 mGy; low: 3.9 mGy; ultralow: 2.0 mGy). The processing strength of DLIP with A1, A4, and A9 was compared with those of FBP, MBIR, and DLR.
The standard dose with high-contrast TTFs of DLIP exceeded that of FBP. Low-contrast TTFs were comparable to or lower than that of FBP. The NPS peak frequency (f) of DLIP shifts to low spatial frequencies of up to 8.6% at ultralow doses compared to the standard FBP dose. MBIR shifted the most f compared to FBP-a marked shift of up to 49%. DLIP showed a CNR equal to or greater than that of DLR in standard or low doses. In contrast, the CNR of the DLIP was equal to or lower than that of the DLR in ultralow doses.
DLIP reduced image noise while maintaining a resolution similar to commercially available MBIR and DLR. The slight spatial frequency shift of f in DLIP contributed to the noise texture degradation suppression. The NPS suppression in the low spatial frequency range effectively improved the low-contrast detectability.
本研究旨在评估基于深度学习的图像处理软件（DLIP；富士胶片，东京，日本）的图像特征，并将其与滤波反投影（FBP）、基于模型的迭代重建（MBIR）和基于深度学习的重建（DLR）进行比较。
本 phantom 研究评估了特定于物体的空间分辨率（基于任务的传递函数[TTF]）、噪声特性（噪声功率谱[NPS]）和低对比度可探测性（特定于低对比度物体的对比度噪声比[CNR]）在三个不同的输出剂量（标准：10 mGy；低：3.9 mGy；超低：2.0 mGy）下。比较了 DLIP 的 A1、A4 和 A9 的处理强度与 FBP、MBIR 和 DLR 的处理强度。
高对比度 TTF 的标准剂量下的 DLIP 超过了 FBP。低对比度 TTF 与 FBP 相当或更低。与标准 FBP 剂量相比，超低剂量下的 DLIP 的 NPS 峰值频率（f）向低空间频率转移，最高可达 8.6%。MBIR 与 FBP 相比，f 的转移最大，高达 49%。在标准或低剂量下，DLIP 的 CNR 等于或大于 DLR。相反，在超低剂量下，DLIP 的 CNR 等于或低于 DLR。
DLIP 降低了图像噪声，同时保持了与商用 MBIR 和 DLR 相似的分辨率。f 在 DLIP 中的微小空间频率偏移有助于抑制噪声纹理退化。在低空间频率范围内抑制 NPS 有效地提高了低对比度的可探测性。
