Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Metabolic tumour volume in Hodgkin lymphoma—A comparison between manual and AI-based analysis

Sadik, May ; Barrington, Sally F. ; Trägårdh, Elin LU ; Saboury, Babak ; Nielsen, Anne L. ; Jakobsen, Annika L. ; Gongora, Jose L.L. ; Urdaneta, Jesus L. ; Kumar, Rajender and Edenbrandt, Lars (2023) In Clinical Physiology and Functional Imaging
Abstract

Aim: To compare total metabolic tumour volume (tMTV), calculated using two artificial intelligence (AI)-based tools, with manual segmentation by specialists as the reference. Methods: Forty-eight consecutive Hodgkin lymphoma (HL) patients staged with [18F] fluorodeoxyglucose positron emission tomography/computed tomography were included. The median age was 35 years (range: 7–75), 46% female. The tMTV was automatically measured using the AI-based tools positron emission tomography assisted reporting system (PARS) (from Siemens) and RECOMIA (recomia.org) without any manual adjustments. A group of eight nuclear medicine specialists manually segmented lesions for tMTV calculations; each patient was independently segmented by two... (More)

Aim: To compare total metabolic tumour volume (tMTV), calculated using two artificial intelligence (AI)-based tools, with manual segmentation by specialists as the reference. Methods: Forty-eight consecutive Hodgkin lymphoma (HL) patients staged with [18F] fluorodeoxyglucose positron emission tomography/computed tomography were included. The median age was 35 years (range: 7–75), 46% female. The tMTV was automatically measured using the AI-based tools positron emission tomography assisted reporting system (PARS) (from Siemens) and RECOMIA (recomia.org) without any manual adjustments. A group of eight nuclear medicine specialists manually segmented lesions for tMTV calculations; each patient was independently segmented by two specialists. Results: The median of the manual tMTV was 146 cm3 (interquartile range [IQR]: 79–568 cm3) and the median difference between two tMTV values segmented by different specialists for the same patient was 26 cm3 (IQR: 10–86 cm3). In 22 of the 48 patients, the manual tMTV value was closer to the RECOMIA tMTV value than to the manual tMTV value segmented by the second specialist. In 11 of the remaining 26 patients, the difference between the RECOMIA tMTV and the manual tMTV was small (<26 cm3, which was the median difference between two manual tMTV values from the same patient). The corresponding numbers for PARS were 18 and 10 patients, respectively. Conclusion: The results of this study indicate that RECOMIA and Siemens PARS AI tools could be used without any major manual adjustments in 69% (33/48) and 58% (28/48) of HL patients, respectively. This demonstrates the feasibility of using AI tools to support physicians measuring tMTV for assessment of prognosis in clinical practice.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
in press
subject
keywords
convolutional neural networks, haematological disease, quantification, staging, [18F]FDG PET/CT
in
Clinical Physiology and Functional Imaging
publisher
John Wiley & Sons Inc.
external identifiers
  • pmid:38011940
  • scopus:85178451303
ISSN
1475-0961
DOI
10.1111/cpf.12868
language
English
LU publication?
yes
id
e3484936-5a40-4522-ae45-bdf8d6a0d9f6
date added to LUP
2024-01-02 15:29:32
date last changed
2024-04-17 14:42:51
@article{e3484936-5a40-4522-ae45-bdf8d6a0d9f6,
  abstract     = {{<p>Aim: To compare total metabolic tumour volume (tMTV), calculated using two artificial intelligence (AI)-based tools, with manual segmentation by specialists as the reference. Methods: Forty-eight consecutive Hodgkin lymphoma (HL) patients staged with [18F] fluorodeoxyglucose positron emission tomography/computed tomography were included. The median age was 35 years (range: 7–75), 46% female. The tMTV was automatically measured using the AI-based tools positron emission tomography assisted reporting system (PARS) (from Siemens) and RECOMIA (recomia.org) without any manual adjustments. A group of eight nuclear medicine specialists manually segmented lesions for tMTV calculations; each patient was independently segmented by two specialists. Results: The median of the manual tMTV was 146 cm<sup>3</sup> (interquartile range [IQR]: 79–568 cm<sup>3</sup>) and the median difference between two tMTV values segmented by different specialists for the same patient was 26 cm<sup>3</sup> (IQR: 10–86 cm<sup>3</sup>). In 22 of the 48 patients, the manual tMTV value was closer to the RECOMIA tMTV value than to the manual tMTV value segmented by the second specialist. In 11 of the remaining 26 patients, the difference between the RECOMIA tMTV and the manual tMTV was small (&lt;26 cm<sup>3</sup>, which was the median difference between two manual tMTV values from the same patient). The corresponding numbers for PARS were 18 and 10 patients, respectively. Conclusion: The results of this study indicate that RECOMIA and Siemens PARS AI tools could be used without any major manual adjustments in 69% (33/48) and 58% (28/48) of HL patients, respectively. This demonstrates the feasibility of using AI tools to support physicians measuring tMTV for assessment of prognosis in clinical practice.</p>}},
  author       = {{Sadik, May and Barrington, Sally F. and Trägårdh, Elin and Saboury, Babak and Nielsen, Anne L. and Jakobsen, Annika L. and Gongora, Jose L.L. and Urdaneta, Jesus L. and Kumar, Rajender and Edenbrandt, Lars}},
  issn         = {{1475-0961}},
  keywords     = {{convolutional neural networks; haematological disease; quantification; staging; [18F]FDG PET/CT}},
  language     = {{eng}},
  publisher    = {{John Wiley & Sons Inc.}},
  series       = {{Clinical Physiology and Functional Imaging}},
  title        = {{Metabolic tumour volume in Hodgkin lymphoma—A comparison between manual and AI-based analysis}},
  url          = {{http://dx.doi.org/10.1111/cpf.12868}},
  doi          = {{10.1111/cpf.12868}},
  year         = {{2023}},
}