摘要
PurposeThe goal of this work is to demonstrate the feasibility of directly generating attenuation-corrected PET images from non-attenuation-corrected (NAC) PET images for both rest and stress-state static or dynamic [N-13]ammonia MP PET based on a generative adversarial network.MethodsWe recruited 60 subjects for rest-only scans and 14 subjects for rest-stress scans, all of whom underwent [N-13]ammonia cardiac PET/CT examinations to acquire static and dynamic frames with both 3D NAC and CT-based AC (CTAC) PET images. We developed a 3D pix2pix deep learning AC (DLAC) framework via a U-net + ResNet-based generator and a convolutional neural network-based discriminator. Paired static or dynamic NAC and CTAC PET images from 60 rest-only subjects were used as network inputs and labels for static (S-DLAC) and dynamic (D-DLAC) training, respectively. The pre-trained S-DLAC network was then fine-tuned by paired dynamic NAC and CTAC PET frames of 60 rest-only subjects to derive an improved D-DLAC-FT for dynamic PET images. The 14 rest-stress subjects were used as an internal testing dataset and separately tested on different network models without training. The proposed methods were evaluated using visual quality and quantitative metrics.ResultsThe proposed S-DLAC, D-DLAC, and D-DLAC-FT methods were consistent with clinical CTAC in terms of various images and quantitative metrics. The S-DLAC (slope = 0.9423, R-2 = 0.947) showed a higher correlation with the reference static CTAC as compared to static NAC (slope = 0.0992, R-2 = 0.654). D-DLAC-FT yielded lower myocardial blood flow (MBF) errors in the whole left ventricular myocardium than D-DLAC, but with no significant difference, both for the 60 rest-state subjects (6.63 & PLUSMN; 5.05% vs. 7.00 & PLUSMN; 6.84%, p = 0.7593) and the 14 stress-state subjects (1.97 & PLUSMN; 2.28% vs. 3.21 & PLUSMN; 3.89%, p = 0.8595).ConclusionThe proposed S-DLAC, D-DLAC, and D-DLAC-FT methods achieve comparable performance with clinical CTAC. Transfer learning shows promising potential for dynamic MP PET.
学科与关键词
- DeTransUnet: attenuation correction of gated cardiac images without structural informationWang, Bo; Lu, Lijun*; Liu, Huafeng*Physics in Medicine and Biology, 2022, 67(16): 165007.被引 2
- INVERTIBLE AC-FLOW: DIRECT ATTENUATION CORRECTION OF PET IMAGES WITHOUT CT OR MR IMAGESWang, Bo; Lu, Lijun*; Liu, Huafeng*19th IEEE International Symposium on Biomedical Imaging (IEEE ISBI), Kolkata, INDIA, 2022-03-28 To 2022-03-31.被引 1
- Deep-learning-based methods of attenuation correction for SPECT and PETChen, Xiongchao; Liu, Chi*Journal of Nuclear Cardiology, 2023, 30(5): 1859-1878.被引 13
