Olin Anders B, Hansen Adam E, Rasmussen Jacob H, Jakoby Björn, Berthelsen Anne K, Ladefoged Claes N, Kjær Andreas, Fischer Barbara M, Andersen Flemming L
Department of Clinical Physiology, Nuclear Medicine and PET & Cluster for Molecular Imaging, Rigshospitalet, University of Copenhagen, Blegdamsvej 9, 2100, Copenhagen, Denmark.
Faculty of Health and Medical Science, University of Copenhagen, Copenhagen, Denmark.
EJNMMI Phys. 2022 Mar 16;9(1):20. doi: 10.1186/s40658-022-00449-z.
Quantitative whole-body PET/MRI relies on accurate patient-specific MRI-based attenuation correction (AC) of PET, which is a non-trivial challenge, especially for the anatomically complex head and neck region. We used a deep learning model developed for dose planning in radiation oncology to derive MRI-based attenuation maps of head and neck cancer patients and evaluated its performance on PET AC.
Eleven head and neck cancer patients, referred for radiotherapy, underwent CT followed by PET/MRI with acquisition of Dixon MRI. Both scans were performed in radiotherapy position. PET AC was performed with three different patient-specific attenuation maps derived from: (1) Dixon MRI using a deep learning network (PET). (2) Dixon MRI using the vendor-provided atlas-based method (PET). (3) CT, serving as reference (PET). We analyzed the effect of the MRI-based AC methods on PET quantification by assessing the average voxelwise error within the entire body, and the error as a function of distance to bone/air. The error in mean uptake within anatomical regions of interest and the tumor was also assessed.
The average (± standard deviation) PET voxel error was 0.0 ± 11.4% for PET and -1.3 ± 21.8% for PET. The error in mean PET uptake in bone/air was much lower for PET (-4%/12%) than for PET (-15%/84%) and PET also demonstrated a more rapidly decreasing error with distance to bone/air affecting only the immediate surroundings (less than 1 cm). The regions with the largest error in mean uptake were those containing bone (mandible) and air (larynx) for both methods, and the error in tumor mean uptake was -0.6 ± 2.0% for PET and -3.5 ± 4.6% for PET.
The deep learning network for deriving MRI-based attenuation maps of head and neck cancer patients demonstrated accurate AC and exceeded the performance of the vendor-provided atlas-based method both overall, on a lesion-level, and in vicinity of challenging regions such as bone and air.
定量全身PET/MRI依赖于基于患者特异性MRI的PET衰减校正（AC），这是一项具有挑战性的任务，特别是对于解剖结构复杂的头颈部区域。我们使用了一种为放射肿瘤学剂量规划开发的深度学习模型来推导头颈部癌症患者基于MRI的衰减图，并评估其在PET AC方面的性能。
11名头颈部癌症患者因放疗前来就诊，先进行CT扫描，然后进行PET/MRI并采集狄克逊MRI。两次扫描均在放疗体位下进行。使用从以下三种不同的患者特异性衰减图进行PET AC：（1）使用深度学习网络从狄克逊MRI中获取（PET）。（2）使用供应商提供的基于图谱的方法从狄克逊MRI中获取（PET）。（3）CT，作为参考（PET）。我们通过评估全身内平均体素误差以及误差随与骨/空气距离的变化情况，分析基于MRI的AC方法对PET定量的影响。还评估了感兴趣的解剖区域和肿瘤内平均摄取的误差。
PET的平均（±标准差）PET体素误差为0.0±11.4%，PET为-1.3±21.8%。PET在骨/空气中的平均PET摄取误差（-4%/12%）远低于PET（-15%/84%），并且PET的误差也随着与骨/空气距离的增加而下降得更快，仅影响紧邻区域（小于1厘米）。两种方法中平均摄取误差最大的区域是包含骨（下颌骨）和空气（喉）的区域，PET肿瘤平均摄取误差为-0.6±2.0%，PET为-3.5±4.6%。
用于推导头颈部癌症患者基于MRI的衰减图的深度学习网络显示出准确的AC，在总体、病变水平以及在诸如骨和空气等具有挑战性的区域附近均超过了供应商提供的基于图谱的方法的性能。
