Display options
Share it on

EJNMMI Phys. 2020 Dec 14;7(1):76. doi: 10.1186/s40658-020-00346-3.

Automated quantification of baseline imaging PET metrics on FDG PET/CT images of pediatric Hodgkin lymphoma patients.

EJNMMI physics

Amy J Weisman, Jihyun Kim, Inki Lee, Kathleen M McCarten, Sandy Kessel, Cindy L Schwartz, Kara M Kelly, Robert Jeraj, Steve Y Cho, Tyler J Bradshaw

Affiliations

  1. Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, USA.
  2. Department of Radiology, University of Wisconsin-Madison, Madison, WI, USA.
  3. Department of Nuclear Medicine Korea Cancer Centre Hospital, Korea Institute of Radiological and Medical Sciences, Seoul, Korea.
  4. IROC-Rhode Island, Lincoln, RI, USA.
  5. Medical College of Wisconsin, Milwaukee, WI, USA.
  6. Department of Pediatrics, Roswell Park Comprehensive Cancer Center, University at Buffalo Jacobs School of Medicine and Biomedical Sciences, Buffalo, NY, USA.
  7. University of Wisconsin Carbone Comprehensive Cancer Center, Madison, WI, USA.
  8. Department of Radiology, University of Wisconsin-Madison, Madison, WI, USA. [email protected].

PMID: 33315178 PMCID: PMC7736382 DOI: 10.1186/s40658-020-00346-3

Abstract

RESULTS: Median Dice similarity coefficient of patient contours between automated and physician contours was 0.86 (IQR 0.78-0.91). Automated SUV

CONCLUSIONS: An automated method using an ensemble of multi-resolution pathway 3D CNNs was able to quantify PET imaging features of lymphoma on baseline FDG PET/CT images with excellent agreement to reference physician PET segmentation. Automated methods with faster throughput for PET quantitation, such as MTV and TLG, show promise in more accessible clinical and research applications.

Keywords: Convolutional neural networks; Imaging biomarkers; PET; Pediatric lymphoma

References

  1. Nucl Med Commun. 2007 Oct;28(10):798-803 - PubMed
  2. Comput Med Imaging Graph. 2017 Sep;60:3-10 - PubMed
  3. J Clin Oncol. 2014 Sep 20;32(27):3059-68 - PubMed
  4. Med Image Anal. 2017 Feb;36:61-78 - PubMed
  5. J Clin Oncol. 2014 Nov 10;32(32):3651-8 - PubMed
  6. Mol Imaging Biol. 2020 Aug;22(4):1102-1110 - PubMed
  7. Blood. 2009 Sep 3;114(10):2051-9 - PubMed
  8. Blood. 2018 Jan 4;131(1):84-94 - PubMed
  9. Eur J Nucl Med Mol Imaging. 2010 Feb;37(2):319-29 - PubMed
  10. Br J Haematol. 2019 Oct;187(1):39-48 - PubMed
  11. Eur J Nucl Med Mol Imaging. 2018 Sep;45(10):1672-1679 - PubMed
  12. Int J Comput Assist Radiol Surg. 2019 Oct;14(10):1715-1724 - PubMed
  13. Radiat Oncol. 2012 Jan 19;7:5 - PubMed
  14. BMC Cancer. 2018 May 3;18(1):521 - PubMed
  15. CA Cancer J Clin. 2014 Mar-Apr;64(2):83-103 - PubMed
  16. J Nucl Med. 2020 Jan;61(1):40-45 - PubMed
  17. Radiology. 2020 Feb;294(2):445-452 - PubMed
  18. Cancer Sci. 2013 Dec;104(12):1656-61 - PubMed
  19. Eur J Nucl Med Mol Imaging. 2014 Sep;41(9):1735-43 - PubMed
  20. Ann Nucl Med. 2012 Jan;26(1):58-66 - PubMed
  21. Blood. 2017 Nov 16;130(20):2196-2203 - PubMed
  22. Blood. 2018 Mar 29;131(13):1456-1463 - PubMed

Publication Types

Grant support