Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Freely available artificial intelligence for pelvic lymph node metastases in PSMA PET-CT that performs on par with nuclear medicine physicians

Trägårdh, Elin LU ; Enqvist, Olof ; Ulén, Johannes ; Hvittfeldt, Erland LU orcid ; Garpered, Sabine LU ; Belal, Sarah Lindgren LU orcid ; Bjartell, Anders LU and Edenbrandt, Lars LU (2022) In European Journal of Nuclear Medicine and Molecular Imaging 49(10). p.3412-3418
Abstract

Purpose: The aim of this study was to develop and validate an artificial intelligence (AI)-based method using convolutional neural networks (CNNs) for the detection of pelvic lymph node metastases in scans obtained using [18F]PSMA-1007 positron emission tomography-computed tomography (PET-CT) from patients with high-risk prostate cancer. The second goal was to make the AI-based method available to other researchers. Methods: [18F]PSMA PET-CT scans were collected from 211 patients. Suspected pelvic lymph node metastases were marked by three independent readers. A CNN was developed and trained on a training and validation group of 161 of the patients. The performance of the AI method and the inter-observer agreement... (More)

Purpose: The aim of this study was to develop and validate an artificial intelligence (AI)-based method using convolutional neural networks (CNNs) for the detection of pelvic lymph node metastases in scans obtained using [18F]PSMA-1007 positron emission tomography-computed tomography (PET-CT) from patients with high-risk prostate cancer. The second goal was to make the AI-based method available to other researchers. Methods: [18F]PSMA PET-CT scans were collected from 211 patients. Suspected pelvic lymph node metastases were marked by three independent readers. A CNN was developed and trained on a training and validation group of 161 of the patients. The performance of the AI method and the inter-observer agreement between the three readers were assessed in a separate test group of 50 patients. Results: The sensitivity of the AI method for detecting pelvic lymph node metastases was 82%, and the corresponding sensitivity for the human readers was 77% on average. The average number of false positives was 1.8 per patient. A total of 5–17 false negative lesions in the whole cohort were found, depending on which reader was used as a reference. The method is available for researchers at www.recomia.org. Conclusion: This study shows that AI can obtain a sensitivity on par with that of physicians with a reasonable number of false positives. The difficulty in achieving high inter-observer sensitivity emphasizes the need for automated methods. On the road to qualifying AI tools for clinical use, independent validation is critical and allows performance to be assessed in studies from different hospitals. Therefore, we have made our AI tool freely available to other researchers.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Artificial intelligence, Convolutional neural network, Deep learning, Prostate cancer, PSMA
in
European Journal of Nuclear Medicine and Molecular Imaging
volume
49
issue
10
pages
3412 - 3418
publisher
Springer
external identifiers
  • scopus:85128809696
  • pmid:35475912
ISSN
1619-7070
DOI
10.1007/s00259-022-05806-9
language
English
LU publication?
yes
id
48246f6e-b77b-466b-87b6-a975b920ced7
date added to LUP
2022-07-04 13:56:14
date last changed
2024-06-09 20:36:40
@article{48246f6e-b77b-466b-87b6-a975b920ced7,
  abstract     = {{<p>Purpose: The aim of this study was to develop and validate an artificial intelligence (AI)-based method using convolutional neural networks (CNNs) for the detection of pelvic lymph node metastases in scans obtained using [<sup>18</sup>F]PSMA-1007 positron emission tomography-computed tomography (PET-CT) from patients with high-risk prostate cancer. The second goal was to make the AI-based method available to other researchers. Methods: [<sup>18</sup>F]PSMA PET-CT scans were collected from 211 patients. Suspected pelvic lymph node metastases were marked by three independent readers. A CNN was developed and trained on a training and validation group of 161 of the patients. The performance of the AI method and the inter-observer agreement between the three readers were assessed in a separate test group of 50 patients. Results: The sensitivity of the AI method for detecting pelvic lymph node metastases was 82%, and the corresponding sensitivity for the human readers was 77% on average. The average number of false positives was 1.8 per patient. A total of 5–17 false negative lesions in the whole cohort were found, depending on which reader was used as a reference. The method is available for researchers at www.recomia.org. Conclusion: This study shows that AI can obtain a sensitivity on par with that of physicians with a reasonable number of false positives. The difficulty in achieving high inter-observer sensitivity emphasizes the need for automated methods. On the road to qualifying AI tools for clinical use, independent validation is critical and allows performance to be assessed in studies from different hospitals. Therefore, we have made our AI tool freely available to other researchers.</p>}},
  author       = {{Trägårdh, Elin and Enqvist, Olof and Ulén, Johannes and Hvittfeldt, Erland and Garpered, Sabine and Belal, Sarah Lindgren and Bjartell, Anders and Edenbrandt, Lars}},
  issn         = {{1619-7070}},
  keywords     = {{Artificial intelligence; Convolutional neural network; Deep learning; Prostate cancer; PSMA}},
  language     = {{eng}},
  number       = {{10}},
  pages        = {{3412--3418}},
  publisher    = {{Springer}},
  series       = {{European Journal of Nuclear Medicine and Molecular Imaging}},
  title        = {{Freely available artificial intelligence for pelvic lymph node metastases in PSMA PET-CT that performs on par with nuclear medicine physicians}},
  url          = {{http://dx.doi.org/10.1007/s00259-022-05806-9}},
  doi          = {{10.1007/s00259-022-05806-9}},
  volume       = {{49}},
  year         = {{2022}},
}