Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Artificial intelligence-based measurements of PET/CT imaging biomarkers are associated with disease-specific survival of high-risk prostate cancer patients

Polymeri, Eirini ; Kjölhede, Henrik ; Enqvist, Olof ; Ulén, Johannes ; Poulsen, Mads H. ; Simonsen, Jane A. ; Borrelli, Pablo ; Trägårdh, Elin LU ; Johnsson, Åse A. and Høilund–Carlsen, Poul Flemming , et al. (2021) In Scandinavian Journal of Urology 55(6). p.427-433
Abstract

Objective: Artificial intelligence (AI) offers new opportunities for objective quantitative measurements of imaging biomarkers from positron-emission tomography/computed tomography (PET/CT). Clinical image reporting relies predominantly on observer-dependent visual assessment and easily accessible measures like SUVmax, representing lesion uptake in a relatively small amount of tissue. Our hypothesis is that measurements of total volume and lesion uptake of the entire tumour would better reflect the disease`s activity with prognostic significance, compared with conventional measurements. Methods: An AI-based algorithm was trained to automatically measure the prostate and its tumour content in PET/CT of 145 patients. The... (More)

Objective: Artificial intelligence (AI) offers new opportunities for objective quantitative measurements of imaging biomarkers from positron-emission tomography/computed tomography (PET/CT). Clinical image reporting relies predominantly on observer-dependent visual assessment and easily accessible measures like SUVmax, representing lesion uptake in a relatively small amount of tissue. Our hypothesis is that measurements of total volume and lesion uptake of the entire tumour would better reflect the disease`s activity with prognostic significance, compared with conventional measurements. Methods: An AI-based algorithm was trained to automatically measure the prostate and its tumour content in PET/CT of 145 patients. The algorithm was then tested retrospectively on 285 high-risk patients, who were examined using 18F-choline PET/CT for primary staging between April 2008 and July 2015. Prostate tumour volume, tumour fraction of the prostate gland, lesion uptake of the entire tumour, and SUVmax were obtained automatically. Associations between these measurements, age, PSA, Gleason score and prostate cancer-specific survival were studied, using a Cox proportional-hazards regression model. Results: Twenty-three patients died of prostate cancer during follow-up (median survival 3.8 years). Total tumour volume of the prostate (p = 0.008), tumour fraction of the gland (p = 0.005), total lesion uptake of the prostate (p = 0.02), and age (p = 0.01) were significantly associated with disease-specific survival, whereas SUVmax (p = 0.2), PSA (p = 0.2), and Gleason score (p = 0.8) were not. Conclusion: AI-based assessments of total tumour volume and lesion uptake were significantly associated with disease-specific survival in this patient cohort, whereas SUVmax and Gleason scores were not. The AI-based approach appears well-suited for clinically relevant patient stratification and monitoring of individual therapy.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
F-choline-PET/CT, Artificial intelligence, disease-specific survival, imaging biomarkers, prostate cancer
in
Scandinavian Journal of Urology
volume
55
issue
6
pages
427 - 433
publisher
Taylor & Francis
external identifiers
  • scopus:85115714317
  • pmid:34565290
ISSN
2168-1805
DOI
10.1080/21681805.2021.1977845
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
id
42f27128-7133-405b-9c0a-b9bf524cfcc4
date added to LUP
2021-10-20 11:05:35
date last changed
2024-06-15 18:30:28
@article{42f27128-7133-405b-9c0a-b9bf524cfcc4,
  abstract     = {{<p>Objective: Artificial intelligence (AI) offers new opportunities for objective quantitative measurements of imaging biomarkers from positron-emission tomography/computed tomography (PET/CT). Clinical image reporting relies predominantly on observer-dependent visual assessment and easily accessible measures like SUV<sub>max</sub>, representing lesion uptake in a relatively small amount of tissue. Our hypothesis is that measurements of total volume and lesion uptake of the entire tumour would better reflect the disease`s activity with prognostic significance, compared with conventional measurements. Methods: An AI-based algorithm was trained to automatically measure the prostate and its tumour content in PET/CT of 145 patients. The algorithm was then tested retrospectively on 285 high-risk patients, who were examined using <sup>18</sup>F-choline PET/CT for primary staging between April 2008 and July 2015. Prostate tumour volume, tumour fraction of the prostate gland, lesion uptake of the entire tumour, and SUV<sub>max</sub> were obtained automatically. Associations between these measurements, age, PSA, Gleason score and prostate cancer-specific survival were studied, using a Cox proportional-hazards regression model. Results: Twenty-three patients died of prostate cancer during follow-up (median survival 3.8 years). Total tumour volume of the prostate (p = 0.008), tumour fraction of the gland (p = 0.005), total lesion uptake of the prostate (p = 0.02), and age (p = 0.01) were significantly associated with disease-specific survival, whereas SUV<sub>max</sub> (p = 0.2), PSA (p = 0.2), and Gleason score (p = 0.8) were not. Conclusion: AI-based assessments of total tumour volume and lesion uptake were significantly associated with disease-specific survival in this patient cohort, whereas SUV<sub>max</sub> and Gleason scores were not. The AI-based approach appears well-suited for clinically relevant patient stratification and monitoring of individual therapy.</p>}},
  author       = {{Polymeri, Eirini and Kjölhede, Henrik and Enqvist, Olof and Ulén, Johannes and Poulsen, Mads H. and Simonsen, Jane A. and Borrelli, Pablo and Trägårdh, Elin and Johnsson, Åse A. and Høilund–Carlsen, Poul Flemming and Edenbrandt, Lars}},
  issn         = {{2168-1805}},
  keywords     = {{F-choline-PET/CT; Artificial intelligence; disease-specific survival; imaging biomarkers; prostate cancer}},
  language     = {{eng}},
  number       = {{6}},
  pages        = {{427--433}},
  publisher    = {{Taylor & Francis}},
  series       = {{Scandinavian Journal of Urology}},
  title        = {{Artificial intelligence-based measurements of PET/CT imaging biomarkers are associated with disease-specific survival of high-risk prostate cancer patients}},
  url          = {{http://dx.doi.org/10.1080/21681805.2021.1977845}},
  doi          = {{10.1080/21681805.2021.1977845}},
  volume       = {{55}},
  year         = {{2021}},
}