Literature DB >> 33006022

A convolutional neural network for fully automated blood SUV determination to facilitate SUR computation in oncological FDG-PET.

Pavel Nikulin1, Frank Hofheinz2, Jens Maus2, Yimin Li3, Rebecca Bütof4,5,6, Catharina Lange7, Christian Furth7, Sebastian Zschaeck8,9, Michael C Kreissl10, Jörg Kotzerke11, Jörg van den Hoff2,11.   

Abstract

PURPOSE: The standardized uptake value (SUV) is widely used for quantitative evaluation in oncological FDG-PET but has well-known shortcomings as a measure of the tumor's glucose consumption. The standard uptake ratio (SUR) of tumor SUV and arterial blood SUV (BSUV) possesses an increased prognostic value but requires image-based BSUV determination, typically in the aortic lumen. However, accurate manual ROI delineation requires care and imposes an additional workload, which makes the SUR approach less attractive for clinical routine. The goal of the present work was the development of a fully automated method for BSUV determination in whole-body PET/CT.
METHODS: Automatic delineation of the aortic lumen was performed with a convolutional neural network (CNN), using the U-Net architecture. A total of 946 FDG PET/CT scans from several sites were used for network training (N = 366) and testing (N = 580). For all scans, the aortic lumen was manually delineated, avoiding areas affected by motion-induced attenuation artifacts or potential spillover from adjacent FDG-avid regions. Performance of the network was assessed using the fractional deviations of automatically and manually derived BSUVs in the test data.
RESULTS: The trained U-Net yields BSUVs in close agreement with those obtained from manual delineation. Comparison of manually and automatically derived BSUVs shows excellent concordance: the mean relative BSUV difference was (mean ± SD) = (- 0.5 ± 2.2)% with a 95% confidence interval of [- 5.1,3.8]% and a total range of [- 10.0, 12.0]%. For four test cases, the derived ROIs were unusable (< 1 ml).
CONCLUSION: CNNs are capable of performing robust automatic image-based BSUV determination. Integrating automatic BSUV derivation into PET data processing workflows will significantly facilitate SUR computation without increasing the workload in the clinical setting.

Entities:  

Keywords:  Convolutional neural network; FDG-PET; SUR; SUV; Standardized uptake ratio; Standardized uptake value

Year:  2020        PMID: 33006022     DOI: 10.1007/s00259-020-04991-9

Source DB:  PubMed          Journal:  Eur J Nucl Med Mol Imaging        ISSN: 1619-7070            Impact factor:   9.236


  16 in total

1.  Anatomy of SUV. Standardized uptake value.

Authors:  S C Huang
Journal:  Nucl Med Biol       Date:  2000-10       Impact factor: 2.408

2.  Multi-atlas-based segmentation with local decision fusion--application to cardiac and aortic segmentation in CT scans.

Authors:  Ivana Isgum; Marius Staring; Annemarieke Rutten; Mathias Prokop; Max A Viergever; Bram van Ginneken
Journal:  IEEE Trans Med Imaging       Date:  2009-01-06       Impact factor: 10.048

3.  Automated aorta segmentation in low-dose chest CT images.

Authors:  Yiting Xie; Jennifer Padgett; Alberto M Biancardi; Anthony P Reeves
Journal:  Int J Comput Assist Radiol Surg       Date:  2013-07-23       Impact factor: 2.924

4.  Confirmation of the prognostic value of pretherapeutic tumor SUR and MTV in patients with esophageal squamous cell carcinoma.

Authors:  Frank Hofheinz; Yimin Li; Ingo G Steffen; Qin Lin; Chen Lili; Wu Hua; Jörg van den Hoff; Sebastian Zschaeck
Journal:  Eur J Nucl Med Mol Imaging       Date:  2019-04-04       Impact factor: 9.236

5.  SUV: standard uptake or silly useless value?

Authors:  J W Keyes
Journal:  J Nucl Med       Date:  1995-10       Impact factor: 10.057

6.  Test-Retest Variability in Lesion SUV and Lesion SUR in 18F-FDG PET: An Analysis of Data from Two Prospective Multicenter Trials.

Authors:  Frank Hofheinz; Ivayla Apostolova; Liane Oehme; Jörg Kotzerke; Jörg van den Hoff
Journal:  J Nucl Med       Date:  2017-05-04       Impact factor: 10.057

7.  Prognostic Value of Pretherapeutic Tumor-to-Blood Standardized Uptake Ratio in Patients with Esophageal Carcinoma.

Authors:  Rebecca Bütof; Frank Hofheinz; Klaus Zöphel; Tobias Stadelmann; Julia Schmollack; Christina Jentsch; Steffen Löck; Jörg Kotzerke; Michael Baumann; Jörg van den Hoff
Journal:  J Nucl Med       Date:  2015-06-18       Impact factor: 10.057

8.  The dose uptake ratio as an index of glucose metabolism: useful parameter or oversimplification?

Authors:  L M Hamberg; G J Hunter; N M Alpert; N C Choi; J W Babich; A J Fischman
Journal:  J Nucl Med       Date:  1994-08       Impact factor: 10.057

9.  Comparative evaluation of SUV, tumor-to-blood standard uptake ratio (SUR), and dual time point measurements for assessment of the metabolic uptake rate in FDG PET.

Authors:  Frank Hofheinz; Jörg van den Hoff; Ingo G Steffen; Alexandr Lougovski; Kilian Ego; Holger Amthauer; Ivayla Apostolova
Journal:  EJNMMI Res       Date:  2016-06-22       Impact factor: 3.138

10.  An investigation of the relation between tumor-to-liver ratio (TLR) and tumor-to-blood standard uptake ratio (SUR) in oncological FDG PET.

Authors:  Frank Hofheinz; Rebecca Bütof; Ivayla Apostolova; Klaus Zöphel; Ingo G Steffen; Holger Amthauer; Jörg Kotzerke; Michael Baumann; Jörg van den Hoff
Journal:  EJNMMI Res       Date:  2016-03-02       Impact factor: 3.138

View more
  1 in total

Review 1.  PET/CT for Predicting Occult Lymph Node Metastasis in Gastric Cancer.

Authors:  Danyu Ma; Ying Zhang; Xiaoliang Shao; Chen Wu; Jun Wu
Journal:  Curr Oncol       Date:  2022-09-11       Impact factor: 3.109

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.