Investigate the potential benefits of sequential deployment of two deep learning (DL) algorithms namely DL-Enhancement (DLE) and DL-based time-of-flight (ToF) (DLT). DLE aims to enhance the rapidly reconstructed ordered-subset-expectation-maximisation algorithm (OSEM) images towards block-sequential-regularised-expectation-maximisation (BSREM) images, whereas DLT aims to improve the quality of BSREM images reconstructed without ToF. As the algorithms differ in their purpose, sequential application may allow benefits from each to be combined. 20 FDG PET-CT scans were performed on a Discovery 710 (D710) and 20 on Discovery MI (DMI; both GE HealthCare). PET data was reconstructed using five combinations of algorithms:1. ToF-BSREM, 2. ToF-OSEM + DLE, 3. OSEM + DLE + DLT, 4. ToF-OSEM + DLE + DLT, 5. ToF-BSREM + DLT. To assess image noise, 30 mm-diameter spherical VOIs were drawn in both lung and liver to measure standard deviation of voxels within the volume. In a blind clinical reading, two experienced readers rated the images on a five-point Likert scale based on lesion detectability, diagnostic confidence, and image quality. Applying DLE + DLT reduced noise whilst improving lesion detectability, diagnostic confidence, and image reconstruction time. ToF-OSEM + DLE + DLT reconstructions demonstrated an increase in lesion SUVmax of 28 ± 14% (average ± standard deviation) and 11 ± 5% for data acquired on the D710 and DMI, respectively. The same reconstruction scored highest in clinical readings for both lesion detectability and diagnostic confidence for D710. The combination of DLE and DLT increased diagnostic confidence and lesion detectability compared to ToF-BSREM images. As DLE + DLT used input OSEM images, and because DL inferencing was fast, there was a significant decrease in overall reconstruction time. This could have applications to total body PET.

中文翻译：

---

顺序深度学习图像增强模型可提高 PET 中的诊断置信度、病变可检测性和图像重建时间

研究顺序部署两种深度学习 (DL) 算法（即 DL 增强 (DLE) 和基于 DL 的飞行时间 (ToF) (DLT)）的潜在优势。DLE 旨在将快速重建的有序子集期望最大化算法 (OSEM) 图像增强为块顺序正则化期望最大化 (BSREM) 图像，而 DLT 旨在提高无需 ToF 重建的 BSREM 图像的质量。由于算法的目的不同，顺序应用可以将每种算法的优点结合起来。在 Discovery 710 (D710) 上进行了 20 次 FDG PET-CT 扫描，在 Discovery MI (DMI；均为 GE HealthCare) 上进行了 20 次扫描。使用五种算法组合重建 PET 数据：1．ToF-BSREM，2. ToF-OSEM + DLE，3. OSEM + DLE + DLT，4. ToF-OSEM + DLE + DLT，5. ToF-BSREM + DLT。为了评估图像噪声，在肺和肝脏中绘制了 30 毫米直径的球形 VOI，以测量体积内体素的标准偏差。在盲法临床阅片中，两位经验丰富的读者根据病变可检测性、诊断置信度和图像质量，采用五点李克特量表对图像进行评分。应用 DLE + DLT 减少了噪声，同时提高了病变可检测性、诊断置信度和图像重建时间。ToF-OSEM + DLE + DLT 重建表明，在 D710 和 DMI 上获取的数据的病变 SUVmax 分别增加了 28 ± 14%（平均值 ± 标准差）和 11 ± 5%。相同的重建在 D710 的病灶可检测性和诊断置信度的临床读数中得分最高。与 ToF-BSREM 图像相比，DLE 和 DLT 的组合提高了诊断置信度和病变可检测性。由于 DLE + DLT 使用输入 OSEM 图像，并且 DL 推理速度很快，因此总体重建时间显着减少。这可以应用于全身 PET。