Literature DB >> 34882262

Comparison of deep learning-based emission-only attenuation correction methods for positron emission tomography.

Donghwi Hwang1,2,3, Seung Kwan Kang1,2,3,4, Kyeong Yun Kim1,2,4, Hongyoon Choi2, Jae Sung Lee5,6,7,8,9.   

Abstract

PURPOSE: This study aims to compare two approaches using only emission PET data and a convolution neural network (CNN) to correct the attenuation (μ) of the annihilation photons in PET.
METHODS: One of the approaches uses a CNN to generate μ-maps from the non-attenuation-corrected (NAC) PET images (μ-CNNNAC). In the other method, CNN is used to improve the accuracy of μ-maps generated using maximum likelihood estimation of activity and attenuation (MLAA) reconstruction (μ-CNNMLAA). We investigated the improvement in the CNN performance by combining the two methods (μ-CNNMLAA+NAC) and the suitability of μ-CNNNAC for providing the scatter distribution required for MLAA reconstruction. Image data from 18F-FDG (n = 100) or 68 Ga-DOTATOC (n = 50) PET/CT scans were used for neural network training and testing.
RESULTS: The error of the attenuation correction factors estimated using μ-CT and μ-CNNNAC was over 7%, but that of scatter estimates was only 2.5%, indicating the validity of the scatter estimation from μ-CNNNAC. However, CNNNAC provided less accurate bone structures in the μ-maps, while the best results in recovering the fine bone structures were obtained by applying CNNMLAA+NAC. Additionally, the μ-values in the lungs were overestimated by CNNNAC. Activity images (λ) corrected for attenuation using μ-CNNMLAA and μ-CNNMLAA+NAC were superior to those corrected using μ-CNNNAC, in terms of their similarity to λ-CT. However, the improvement in the similarity with λ-CT by combining the CNNNAC and CNNMLAA approaches was insignificant (percent error for lung cancer lesions, λ-CNNNAC = 5.45% ± 7.88%; λ-CNNMLAA = 1.21% ± 5.74%; λ-CNNMLAA+NAC = 1.91% ± 4.78%; percent error for bone cancer lesions, λ-CNNNAC = 1.37% ± 5.16%; λ-CNNMLAA = 0.23% ± 3.81%; λ-CNNMLAA+NAC = 0.05% ± 3.49%).
CONCLUSION: The use of CNNNAC was feasible for scatter estimation to address the chicken-egg dilemma in MLAA reconstruction, but CNNMLAA outperformed CNNNAC.
© 2021. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

Entities:  

Keywords:  Attenuation correction; Deep learning; Scatter correction; Simultaneous reconstruction

Mesh:

Substances:

Year:  2021        PMID: 34882262     DOI: 10.1007/s00259-021-05637-0

Source DB:  PubMed          Journal:  Eur J Nucl Med Mol Imaging        ISSN: 1619-7070            Impact factor:   10.057


  37 in total

1.  Whole-body 18F-FDG PET/CT in the presence of truncation artifacts.

Authors:  Thomas Beyer; Andreas Bockisch; Hilmar Kühl; Maria-Jose Martinez
Journal:  J Nucl Med       Date:  2006-01       Impact factor: 10.057

Review 2.  PET/CT imaging artifacts.

Authors:  Waheeda Sureshbabu; Osama Mawlawi
Journal:  J Nucl Med Technol       Date:  2005-09

Review 3.  Dual-modality imaging: combining anatomy and function.

Authors:  David W Townsend
Journal:  J Nucl Med       Date:  2008-05-15       Impact factor: 10.057

4.  Attenuation correction for a combined 3D PET/CT scanner.

Authors:  P E Kinahan; D W Townsend; T Beyer; D Sashin
Journal:  Med Phys       Date:  1998-10       Impact factor: 4.071

5.  Model-based scatter correction for fully 3D PET.

Authors:  J M Ollinger
Journal:  Phys Med Biol       Date:  1996-01       Impact factor: 3.609

6.  MRI-based attenuation correction for PET/MRI using ultrashort echo time sequences.

Authors:  Vincent Keereman; Yves Fierens; Tom Broux; Yves De Deene; Max Lonneux; Stefaan Vandenberghe
Journal:  J Nucl Med       Date:  2010-05       Impact factor: 10.057

7.  Toward implementing an MRI-based PET attenuation-correction method for neurologic studies on the MR-PET brain prototype.

Authors:  Ciprian Catana; Andre van der Kouwe; Thomas Benner; Christian J Michel; Michael Hamm; Matthias Fenchel; Bruce Fischl; Bruce Rosen; Matthias Schmand; A Gregory Sorensen
Journal:  J Nucl Med       Date:  2010-09       Impact factor: 10.057

8.  MRI-Based Attenuation Correction for PET/MRI Using Multiphase Level-Set Method.

Authors:  Hyun Joon An; Seongho Seo; Hyejin Kang; Hongyoon Choi; Gi Jeong Cheon; Han-Joon Kim; Dong Soo Lee; In Chan Song; Yu Kyeong Kim; Jae Sung Lee
Journal:  J Nucl Med       Date:  2015-12-23       Impact factor: 10.057

9.  Tissue classification as a potential approach for attenuation correction in whole-body PET/MRI: evaluation with PET/CT data.

Authors:  Axel Martinez-Möller; Michael Souvatzoglou; Gaspar Delso; Ralph A Bundschuh; Christophe Chefd'hotel; Sibylle I Ziegler; Nassir Navab; Markus Schwaiger; Stephan G Nekolla
Journal:  J Nucl Med       Date:  2009-03-16       Impact factor: 10.057

10.  Optimization of a fully 3D single scatter simulation algorithm for 3D PET.

Authors:  Roberto Accorsi; Lars-Eric Adam; Matthew E Werner; Joel S Karp
Journal:  Phys Med Biol       Date:  2004-06-21       Impact factor: 3.609

View more
  3 in total

Review 1.  Spatial normalization and quantification approaches of PET imaging for neurological disorders.

Authors:  Teng Zhang; Shuang Wu; Xiaohui Zhang; Yiwu Dai; Anxin Wang; Hong Zhang; Mei Tian
Journal:  Eur J Nucl Med Mol Imaging       Date:  2022-05-28       Impact factor: 10.057

2.  HMGB1 induces radioresistance through PI3K/AKT/ATM pathway in esophageal squamous cell carcinoma.

Authors:  Xueyuan Zhang; Naiyi Zou; Wenzhao Deng; Chunyang Song; Ke Yan; Wenbin Shen; Shuchai Zhu
Journal:  Mol Biol Rep       Date:  2022-10-19       Impact factor: 2.742

3.  Using domain knowledge for robust and generalizable deep learning-based CT-free PET attenuation and scatter correction.

Authors:  Rui Guo; Song Xue; Jiaxi Hu; Hasan Sari; Clemens Mingels; Konstantinos Zeimpekis; George Prenosil; Yue Wang; Yu Zhang; Marco Viscione; Raphael Sznitman; Axel Rominger; Biao Li; Kuangyu Shi
Journal:  Nat Commun       Date:  2022-10-06       Impact factor: 17.694

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.