Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Freely Available, Fully Automated AI-Based Analysis of Primary Tumour and Metastases of Prostate Cancer in Whole-Body [18F]-PSMA-1007 PET-CT

Trägårdh, Elin LU ; Enqvist, Olof LU ; Ulén, Johannes ; Jögi, Jonas LU orcid ; Bitzén, Ulrika LU ; Hedeer, Fredrik LU ; Valind, Kristian LU orcid ; Garpered, Sabine LU ; Hvittfeldt, Erland LU orcid and Borrelli, Pablo , et al. (2022) In Diagnostics 12(9).
Abstract
Here, we aimed to develop and validate a fully automated artificial intelligence (AI)-based method for the detection and quantification of suspected prostate tumour/local recurrence, lymph node metastases, and bone metastases from [18F]PSMA-1007 positron emission tomography-computed tomography (PET-CT) images. Images from 660 patients were included. Segmentations by one expert reader were ground truth. A convolutional neural network (CNN) was developed and trained on a training set, and the performance was tested on a separate test set of 120 patients. The AI method was compared with manual segmentations performed by several nuclear medicine physicians. Assessment of tumour burden (total lesion volume (TLV) and total lesion uptake (TLU))... (More)
Here, we aimed to develop and validate a fully automated artificial intelligence (AI)-based method for the detection and quantification of suspected prostate tumour/local recurrence, lymph node metastases, and bone metastases from [18F]PSMA-1007 positron emission tomography-computed tomography (PET-CT) images. Images from 660 patients were included. Segmentations by one expert reader were ground truth. A convolutional neural network (CNN) was developed and trained on a training set, and the performance was tested on a separate test set of 120 patients. The AI method was compared with manual segmentations performed by several nuclear medicine physicians. Assessment of tumour burden (total lesion volume (TLV) and total lesion uptake (TLU)) was performed. The sensitivity of the AI method was, on average, 79% for detecting prostate tumour/recurrence, 79% for lymph node metastases, and 62% for bone metastases. On average, nuclear medicine physicians’ corresponding sensitivities were 78%, 78%, and 59%, respectively. The correlations of TLV and TLU between AI and nuclear medicine physicians were all statistically significant and ranged from R = 0.53 to R = 0.83. In conclusion, the development of an AI-based method for prostate cancer detection with sensitivity on par with nuclear medicine physicians was possible. The developed AI tool is freely available for researchers. (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
in
Diagnostics
volume
12
issue
9
article number
2101
publisher
MDPI AG
external identifiers
  • pmid:36140502
  • scopus:85138616007
ISSN
2075-4418
DOI
10.3390/diagnostics12092101
language
English
LU publication?
yes
id
b8bcddc6-fd38-4e5f-9416-caab19d46f60
date added to LUP
2022-11-20 10:26:22
date last changed
2023-10-05 08:06:34
@article{b8bcddc6-fd38-4e5f-9416-caab19d46f60,
  abstract     = {{Here, we aimed to develop and validate a fully automated artificial intelligence (AI)-based method for the detection and quantification of suspected prostate tumour/local recurrence, lymph node metastases, and bone metastases from [18F]PSMA-1007 positron emission tomography-computed tomography (PET-CT) images. Images from 660 patients were included. Segmentations by one expert reader were ground truth. A convolutional neural network (CNN) was developed and trained on a training set, and the performance was tested on a separate test set of 120 patients. The AI method was compared with manual segmentations performed by several nuclear medicine physicians. Assessment of tumour burden (total lesion volume (TLV) and total lesion uptake (TLU)) was performed. The sensitivity of the AI method was, on average, 79% for detecting prostate tumour/recurrence, 79% for lymph node metastases, and 62% for bone metastases. On average, nuclear medicine physicians’ corresponding sensitivities were 78%, 78%, and 59%, respectively. The correlations of TLV and TLU between AI and nuclear medicine physicians were all statistically significant and ranged from R = 0.53 to R = 0.83. In conclusion, the development of an AI-based method for prostate cancer detection with sensitivity on par with nuclear medicine physicians was possible. The developed AI tool is freely available for researchers.}},
  author       = {{Trägårdh, Elin and Enqvist, Olof and Ulén, Johannes and Jögi, Jonas and Bitzén, Ulrika and Hedeer, Fredrik and Valind, Kristian and Garpered, Sabine and Hvittfeldt, Erland and Borrelli, Pablo and Edenbrandt, Lars}},
  issn         = {{2075-4418}},
  language     = {{eng}},
  month        = {{08}},
  number       = {{9}},
  publisher    = {{MDPI AG}},
  series       = {{Diagnostics}},
  title        = {{Freely Available, Fully Automated AI-Based Analysis of Primary Tumour and Metastases of Prostate Cancer in Whole-Body [18F]-PSMA-1007 PET-CT}},
  url          = {{http://dx.doi.org/10.3390/diagnostics12092101}},
  doi          = {{10.3390/diagnostics12092101}},
  volume       = {{12}},
  year         = {{2022}},
}