Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Artificial intelligence-based detection of lymph node metastases by PET/CT predicts prostate cancer-specific survival

Borrelli, Pablo ; Larsson, Måns ; Ulén, Johannes LU ; Enqvist, Olof LU ; Trägårdh, Elin LU ; Poulsen, Mads Hvid ; Mortensen, Mike Allan ; Kjölhede, Henrik LU ; Høilund-Carlsen, Poul Flemming and Edenbrandt, Lars LU (2021) In Clinical Physiology and Functional Imaging 41(1). p.62-67
Abstract

Introduction: Lymph node metastases are a key prognostic factor in prostate cancer (PCa), but detecting lymph node lesions from PET/CT images is a subjective process resulting in inter-reader variability. Artificial intelligence (AI)-based methods can provide an objective image analysis. We aimed at developing and validating an AI-based tool for detection of lymph node lesions. Methods: A group of 399 patients with biopsy-proven PCa who had undergone 18F-choline PET/CT for staging prior to treatment were used to train (n = 319) and test (n = 80) the AI-based tool. The tool consisted of convolutional neural networks using complete PET/CT scans as inputs. In the test set, the AI-based lymph node detections were compared to... (More)

Introduction: Lymph node metastases are a key prognostic factor in prostate cancer (PCa), but detecting lymph node lesions from PET/CT images is a subjective process resulting in inter-reader variability. Artificial intelligence (AI)-based methods can provide an objective image analysis. We aimed at developing and validating an AI-based tool for detection of lymph node lesions. Methods: A group of 399 patients with biopsy-proven PCa who had undergone 18F-choline PET/CT for staging prior to treatment were used to train (n = 319) and test (n = 80) the AI-based tool. The tool consisted of convolutional neural networks using complete PET/CT scans as inputs. In the test set, the AI-based lymph node detections were compared to those of two independent readers. The association with PCa-specific survival was investigated. Results: The AI-based tool detected more lymph node lesions than Reader B (98 vs. 87/117; p =.045) using Reader A as reference. AI-based tool and Reader A showed similar performance (90 vs. 87/111; p =.63) using Reader B as reference. The number of lymph node lesions detected by the AI-based tool, PSA, and curative treatment was significantly associated with PCa-specific survival. Conclusion: This study shows the feasibility of using an AI-based tool for automated and objective interpretation of PET/CT images that can provide assessments of lymph node lesions comparable with that of experienced readers and prognostic information in PCa patients.

(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, fluorocholine, lymph node metastases, PCa, PET
in
Clinical Physiology and Functional Imaging
volume
41
issue
1
pages
6 pages
publisher
John Wiley & Sons Inc.
external identifiers
  • pmid:32976691
  • scopus:85092607399
ISSN
1475-0961
DOI
10.1111/cpf.12666
language
English
LU publication?
yes
id
97f94aaa-1940-42c7-a7ba-6bd101168876
date added to LUP
2020-11-12 08:23:41
date last changed
2024-04-17 19:15:55
@article{97f94aaa-1940-42c7-a7ba-6bd101168876,
  abstract     = {{<p>Introduction: Lymph node metastases are a key prognostic factor in prostate cancer (PCa), but detecting lymph node lesions from PET/CT images is a subjective process resulting in inter-reader variability. Artificial intelligence (AI)-based methods can provide an objective image analysis. We aimed at developing and validating an AI-based tool for detection of lymph node lesions. Methods: A group of 399 patients with biopsy-proven PCa who had undergone <sup>18</sup>F-choline PET/CT for staging prior to treatment were used to train (n = 319) and test (n = 80) the AI-based tool. The tool consisted of convolutional neural networks using complete PET/CT scans as inputs. In the test set, the AI-based lymph node detections were compared to those of two independent readers. The association with PCa-specific survival was investigated. Results: The AI-based tool detected more lymph node lesions than Reader B (98 vs. 87/117; p =.045) using Reader A as reference. AI-based tool and Reader A showed similar performance (90 vs. 87/111; p =.63) using Reader B as reference. The number of lymph node lesions detected by the AI-based tool, PSA, and curative treatment was significantly associated with PCa-specific survival. Conclusion: This study shows the feasibility of using an AI-based tool for automated and objective interpretation of PET/CT images that can provide assessments of lymph node lesions comparable with that of experienced readers and prognostic information in PCa patients.</p>}},
  author       = {{Borrelli, Pablo and Larsson, Måns and Ulén, Johannes and Enqvist, Olof and Trägårdh, Elin and Poulsen, Mads Hvid and Mortensen, Mike Allan and Kjölhede, Henrik and Høilund-Carlsen, Poul Flemming and Edenbrandt, Lars}},
  issn         = {{1475-0961}},
  keywords     = {{artificial intelligence; fluorocholine; lymph node metastases; PCa; PET}},
  language     = {{eng}},
  number       = {{1}},
  pages        = {{62--67}},
  publisher    = {{John Wiley & Sons Inc.}},
  series       = {{Clinical Physiology and Functional Imaging}},
  title        = {{Artificial intelligence-based detection of lymph node metastases by PET/CT predicts prostate cancer-specific survival}},
  url          = {{http://dx.doi.org/10.1111/cpf.12666}},
  doi          = {{10.1111/cpf.12666}},
  volume       = {{41}},
  year         = {{2021}},
}