Direct reconstruction for simultaneous dual-tracer PET imaging based on multi-task learning

EJNMMI Research

Original Research

Huafeng Liu¹  Fuzhen Zeng¹  Jingwan Fang¹  Amanjule Muhashi¹ 

[1] State Key Laboratory of Modern Optical Instrumentation, College of Optical Science and Engineering, Zhejiang University, Hangzhou, China;

关键词: Dual-tracer PET;    Reconstruction;    Signal separation;    Multi-task learning;   

DOI  :  10.1186/s13550-023-00955-w

 received in 2022-11-08, accepted in 2023-01-17,  发布年份 2023

来源: Springer

【 摘 要 】

BackgroundSimultaneous dual-tracer positron emission tomography (PET) imaging can observe two molecular targets in a single scan, which is conducive to disease diagnosis and tracking. Since the signals emitted by different tracers are the same, it is crucial to separate each single tracer from the mixed signals. The current study proposed a novel deep learning-based method to reconstruct single-tracer activity distributions from the dual-tracer sinogram.MethodsWe proposed the Multi-task CNN, a three-dimensional convolutional neural network (CNN) based on a framework of multi-task learning. One common encoder extracted features from the dual-tracer dynamic sinogram, followed by two distinct and parallel decoders which reconstructed the single-tracer dynamic images of two tracers separately. The model was evaluated by mean squared error (MSE), multiscale structural similarity (MS-SSIM) index and peak signal-to-noise ratio (PSNR) on simulated data and real animal data, and compared to the filtered back-projection method based on deep learning (FBP-CNN).ResultsIn the simulation experiments, the Multi-task CNN reconstructed single-tracer images with lower MSE, higher MS-SSIM and PSNR than FBP-CNN, and was more robust to the changes in individual difference, tracer combination and scanning protocol. In the experiment of rats with an orthotopic xenograft glioma model, the Multi-task CNN reconstructions also showed higher qualities than FBP-CNN reconstructions.ConclusionsThe proposed Multi-task CNN could effectively reconstruct the dynamic activity images of two single tracers from the dual-tracer dynamic sinogram, which was potential in the direct reconstruction for real simultaneous dual-tracer PET imaging data in future.

【 授权许可】

CC BY   
© The Author(s) 2023

【 图 表 】

Fig. 1

12302_2023_718_Article_IEq50.gif

40854_2023_458_Article_IEq14.gif

12302_2023_718_Article_IEq49.gif

Fig. 2

Fig. 1

12302_2023_718_Article_IEq44.gif

Fig. 1

Fig. 1

Fig. 5

Fig. 2

Fig. 3

Fig. 1

Fig. 6

Fig. 6

Fig. 9

Fig. 5

Fig. 7

Fig. 1

Fig. 3

40798_2023_559_Article_IEq1.gif

12302_2023_718_Article_IEq20.gif

Fig. 6

Fig. 3

Fig. 5

Fig. 8

Fig. 2

Fig. 2

Fig. 2

Fig. 4

Fig. 1

Fig. 1

Fig. 1

Fig. 8

Fig. 4

Fig. 2

Fig. 3

Fig. 2

Fig. 4

40708_2023_184_Article_IEq16.gif

Fig. 1

Fig. 5

Fig. 1

Fig. 1

Fig. 2

Fig. 3

Fig. 7

Fig. 7

Fig. 1

Fig. 5

Fig. 6

Fig. 4

Fig. 3

Fig. 2

Fig. 3

Fig. 2

Fig. 5

Fig. 2

Fig. 4

40854_2023_456_Article_IEq31.gif

Fig. 1

Fig. 2

40854_2022_419_Article_IEq5.gif

Fig. 4

40517_2023_248_Article_IEq41.gif

40517_2023_248_Article_IEq40.gif

Fig. 1

40517_2023_248_Article_IEq35.gif

40517_2023_248_Article_IEq34.gif

40517_2023_248_Article_IEq33.gif

40517_2023_248_Article_IEq31.gif

40517_2023_248_Article_IEq30.gif

40517_2023_248_Article_IEq29.gif

40517_2023_248_Article_IEq27.gif

40517_2023_248_Article_IEq26.gif

40517_2023_248_Article_IEq25.gif

40517_2023_248_Article_IEq24.gif

40854_2023_456_Article_IEq6.gif

40517_2023_248_Article_IEq23.gif

40517_2023_248_Article_IEq22.gif

40517_2023_248_Article_IEq21.gif

40517_2023_248_Article_IEq20.gif

40517_2023_248_Article_IEq19.gif

40517_2023_248_Article_IEq18.gif

40517_2023_248_Article_IEq17.gif

40517_2023_248_Article_IEq16.gif

40517_2023_248_Article_IEq15.gif

40517_2023_248_Article_IEq14.gif

40517_2023_248_Article_IEq13.gif

40517_2023_248_Article_IEq12.gif

40517_2023_248_Article_IEq11.gif

40517_2023_248_Article_IEq9.gif

40517_2023_248_Article_IEq8.gif

40517_2023_248_Article_IEq7.gif

40517_2023_248_Article_IEq6.gif

40517_2023_248_Article_IEq5.gif

40517_2023_248_Article_IEq4.gif

40517_2023_248_Article_IEq3.gif

40517_2023_248_Article_IEq2.gif

40517_2023_248_Article_IEq1.gif

Fig. 9

Fig. 1

Fig. 13

Fig. 12

12936_2023_4464_Article_IEq13.gif

Fig. 2

Fig. 5

Fig. 11

Fig. 1

Fig. 10

40854_2023_460_Article_IEq15.gif

12936_2023_4464_Article_IEq7.gif

Fig. 9

Fig. 4

Fig. 8

Fig. 1

Fig. 7

Fig. 3

Fig. 13

Fig. 7

Fig. 6

Fig. 5

Fig. 1

Fig. 1

Fig. 2

Fig. 1

Fig. 5

Fig. 1

Fig. 12

Fig. 2

Fig. 2

Fig. 4

Fig. 1

Fig. 2

Fig. 8

13690_2023_1046_Article_IEq4.gif

Fig. 1

Fig. 6

Fig. 3

Fig. 5