Improving sensitivity through data augmentation with synthetic lymph node metastases for AI-based analysis of PSMA PET-CT images
(2024) In Clinical Physiology and Functional Imaging- Abstract
Background: We developed a fully automated artificial intelligence (AI)AI-based-based method for detecting suspected lymph node metastases in prostate-specific membrane antigen (PSMA)(PSMA) positron emission tomography-computed tomography (PET-CT)(PET-CT) images of prostate cancer patients by using data augmentation that adds synthetic lymph node metastases to the images to expand the training set. Methods: Synthetic data were derived from original training images to which new synthetic lymph node metastases were added. Thus, the original training set from a previous study (n = 420) was expanded by one synthetic image for every original image (n = 840), which was used to train an AI model. The performance of the AI model was compared to... (More)
Background: We developed a fully automated artificial intelligence (AI)AI-based-based method for detecting suspected lymph node metastases in prostate-specific membrane antigen (PSMA)(PSMA) positron emission tomography-computed tomography (PET-CT)(PET-CT) images of prostate cancer patients by using data augmentation that adds synthetic lymph node metastases to the images to expand the training set. Methods: Synthetic data were derived from original training images to which new synthetic lymph node metastases were added. Thus, the original training set from a previous study (n = 420) was expanded by one synthetic image for every original image (n = 840), which was used to train an AI model. The performance of the AI model was compared to that of nuclear medicine physicians and a previously developed AI model. The human readers were alternately used as a reference and compared to either another reading or AI model. Results: The new AI model had an average sensitivity of 84% for detecting lymph node metastases compared with 78% for human readings. Our previously developed AI method without synthetic data had an average sensitivity of 79%. The number of false positive lesions were slightly higher for the new AI model (average 3.3 instances per patient) compared to human readings and the previous AI model (average 2.8 instances per patient), while the number of false negative lesions was lower. Conclusions: Creating synthetic lymph node metastases, as a form of data augmentation, on [18F]PSMA-1007F]PSMA-1007 PETPET-CT-CT images improved the sensitivity of an AI model for detecting suspected lymph node metastases. However, the number of false positive lesions increased somewhat.
(Less)
- author
- Trägårdh, Elin LU ; Ulén, Johannes ; Enqvist, Olof ; Edenbrandt, Lars and Larsson, Måns
- organization
- publishing date
- 2024
- type
- Contribution to journal
- publication status
- epub
- subject
- keywords
- artificial intelligence, machine learning, PET-CT, prostate cancer, PSMA, synthetic data
- in
- Clinical Physiology and Functional Imaging
- publisher
- John Wiley & Sons Inc.
- external identifiers
-
- scopus:85189805730
- pmid:38563413
- ISSN
- 1475-0961
- DOI
- 10.1111/cpf.12879
- language
- English
- LU publication?
- yes
- id
- 12bb51e5-1fe8-4216-bccc-62f93012b6f1
- date added to LUP
- 2024-04-23 14:49:33
- date last changed
- 2024-06-18 19:52:13
@article{12bb51e5-1fe8-4216-bccc-62f93012b6f1,
abstract = {{<p>Background: We developed a fully automated artificial intelligence (AI)AI-based-based method for detecting suspected lymph node metastases in prostate-specific membrane antigen (PSMA)(PSMA) positron emission tomography-computed tomography (PET-CT)(PET-CT) images of prostate cancer patients by using data augmentation that adds synthetic lymph node metastases to the images to expand the training set. Methods: Synthetic data were derived from original training images to which new synthetic lymph node metastases were added. Thus, the original training set from a previous study (n = 420) was expanded by one synthetic image for every original image (n = 840), which was used to train an AI model. The performance of the AI model was compared to that of nuclear medicine physicians and a previously developed AI model. The human readers were alternately used as a reference and compared to either another reading or AI model. Results: The new AI model had an average sensitivity of 84% for detecting lymph node metastases compared with 78% for human readings. Our previously developed AI method without synthetic data had an average sensitivity of 79%. The number of false positive lesions were slightly higher for the new AI model (average 3.3 instances per patient) compared to human readings and the previous AI model (average 2.8 instances per patient), while the number of false negative lesions was lower. Conclusions: Creating synthetic lymph node metastases, as a form of data augmentation, on [18F]PSMA-1007F]PSMA-1007 PETPET-CT-CT images improved the sensitivity of an AI model for detecting suspected lymph node metastases. However, the number of false positive lesions increased somewhat.</p>}},
author = {{Trägårdh, Elin and Ulén, Johannes and Enqvist, Olof and Edenbrandt, Lars and Larsson, Måns}},
issn = {{1475-0961}},
keywords = {{artificial intelligence; machine learning; PET-CT; prostate cancer; PSMA; synthetic data}},
language = {{eng}},
publisher = {{John Wiley & Sons Inc.}},
series = {{Clinical Physiology and Functional Imaging}},
title = {{Improving sensitivity through data augmentation with synthetic lymph node metastases for AI-based analysis of PSMA PET-CT images}},
url = {{http://dx.doi.org/10.1111/cpf.12879}},
doi = {{10.1111/cpf.12879}},
year = {{2024}},
}