Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

coPERCIST : AI-assisted PET-CT response assessment

Trägårdh, Elin LU orcid ; Larsson, Måns ; Enqvist, Olof ; Gillberg, Tony ; Hildebrandt, Malene Grubbe and Edenbrandt, Lars LU (2025) In European Journal of Nuclear Medicine and Molecular Imaging
Abstract

Purpose: The PET Response Criteria in Solid Tumours (PERCIST) 1.0 provides a standardized framework for evaluating treatment response using [18F]fluorodeoxyglucose ([18F]FDG) positron emission tomography – computed tomography (PET-CT), but its clinical use is hindered by manual complexity. This study presents coPERCIST, an artificial intelligence (AI)-assisted module integrated into the RECOMIA platform that semi-automates and streamlines PERCIST analysis. Methods: coPERCIST performs organ segmentation and automates key steps of the PERCIST workflow, including background activity quantification, lesion detection, SULpeak calculation, and longitudinal lesion comparison. A novel image alignment method using... (More)

Purpose: The PET Response Criteria in Solid Tumours (PERCIST) 1.0 provides a standardized framework for evaluating treatment response using [18F]fluorodeoxyglucose ([18F]FDG) positron emission tomography – computed tomography (PET-CT), but its clinical use is hindered by manual complexity. This study presents coPERCIST, an artificial intelligence (AI)-assisted module integrated into the RECOMIA platform that semi-automates and streamlines PERCIST analysis. Methods: coPERCIST performs organ segmentation and automates key steps of the PERCIST workflow, including background activity quantification, lesion detection, SULpeak calculation, and longitudinal lesion comparison. A novel image alignment method using organ-specific transformations and uncertainty estimation enables accurate lesion tracking over time. The system was evaluated in 58 oncological patients, each with two PET-CT scans. Up to three measurable lesions per patient were analysed. Results: The AI-suggested liver and aorta volume of interest for threshold calculation were correct in all baseline and follow-up studies. Follow-up studies were classified as progressive metabolic disease (PMD) in 38 cases, stable metabolic disease (SMD) in 16, and partial metabolic response (PMR) in 4. Of 130 lesions evaluated, anatomical alignment was accurate in all cases, and pairwise SULpeak quantification was accurate in 95%. Pairwise SULpeak quantification failed in seven lesion pairs due to proximity to other lesions or misclassified physiological uptake. Review time was less than one minute for most cases. Conclusion: This study demonstrates the feasibility of AI-assisted PERCIST evaluation for [18F]FDG PET-CT, showing promising accuracy. coPERCIST offers potential for reproducible response assessment and supports future multicentre validation. It is freely available to researchers via the RECOMIA platform.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
epub
subject
keywords
Cancer, PERCIST 1.0, PET-CT, Treatment response
in
European Journal of Nuclear Medicine and Molecular Imaging
publisher
Springer
external identifiers
  • scopus:105019350581
ISSN
1619-7070
DOI
10.1007/s00259-025-07614-3
language
English
LU publication?
yes
additional info
Publisher Copyright: © The Author(s) 2025.
id
c1aeb400-85ad-450a-bfa5-3cde95a75471
date added to LUP
2026-01-19 14:22:00
date last changed
2026-01-19 14:43:51
@article{c1aeb400-85ad-450a-bfa5-3cde95a75471,
  abstract     = {{<p>Purpose: The PET Response Criteria in Solid Tumours (PERCIST) 1.0 provides a standardized framework for evaluating treatment response using [<sup>18</sup>F]fluorodeoxyglucose ([<sup>18</sup>F]FDG) positron emission tomography – computed tomography (PET-CT), but its clinical use is hindered by manual complexity. This study presents coPERCIST, an artificial intelligence (AI)-assisted module integrated into the RECOMIA platform that semi-automates and streamlines PERCIST analysis. Methods: coPERCIST performs organ segmentation and automates key steps of the PERCIST workflow, including background activity quantification, lesion detection, SULpeak calculation, and longitudinal lesion comparison. A novel image alignment method using organ-specific transformations and uncertainty estimation enables accurate lesion tracking over time. The system was evaluated in 58 oncological patients, each with two PET-CT scans. Up to three measurable lesions per patient were analysed. Results: The AI-suggested liver and aorta volume of interest for threshold calculation were correct in all baseline and follow-up studies. Follow-up studies were classified as progressive metabolic disease (PMD) in 38 cases, stable metabolic disease (SMD) in 16, and partial metabolic response (PMR) in 4. Of 130 lesions evaluated, anatomical alignment was accurate in all cases, and pairwise SULpeak quantification was accurate in 95%. Pairwise SULpeak quantification failed in seven lesion pairs due to proximity to other lesions or misclassified physiological uptake. Review time was less than one minute for most cases. Conclusion: This study demonstrates the feasibility of AI-assisted PERCIST evaluation for [<sup>18</sup>F]FDG PET-CT, showing promising accuracy. coPERCIST offers potential for reproducible response assessment and supports future multicentre validation. It is freely available to researchers via the RECOMIA platform.</p>}},
  author       = {{Trägårdh, Elin and Larsson, Måns and Enqvist, Olof and Gillberg, Tony and Hildebrandt, Malene Grubbe and Edenbrandt, Lars}},
  issn         = {{1619-7070}},
  keywords     = {{Cancer; PERCIST 1.0; PET-CT; Treatment response}},
  language     = {{eng}},
  publisher    = {{Springer}},
  series       = {{European Journal of Nuclear Medicine and Molecular Imaging}},
  title        = {{coPERCIST : AI-assisted PET-CT response assessment}},
  url          = {{http://dx.doi.org/10.1007/s00259-025-07614-3}},
  doi          = {{10.1007/s00259-025-07614-3}},
  year         = {{2025}},
}