Header

UZH-Logo

Maintenance Infos

Automated detection of lung cancer at ultralow dose PET/CT by deep neural networks - Initial results


Schwyzer, Moritz; Ferraro, Daniela A; Muehlematter, Urs J; Curioni-Fontecedro, Alessandra; Huellner, Martin W; von Schulthess, Gustav K; Kaufmann, Philipp A; Burger, Irene A; Messerli, Michael (2018). Automated detection of lung cancer at ultralow dose PET/CT by deep neural networks - Initial results. Lung Cancer, 126:170-173.

Abstract

OBJECTIVES
We evaluated whether machine learning may be helpful for the detection of lung cancer in FDG-PET imaging in the setting of ultralow dose PET scans.

MATERIALS AND METHODS
We studied the performance of an artificial neural network discriminating lung cancer patients (n = 50) from controls (n = 50) without pulmonary malignancies. A total of 3936 PET slices including images in which the lung tumor is visually present and image slices of patients with no lung cancer were exported. The diagnostic performance of the artificial neural network based on clinical standard dose PET images (PET) as well as with a tenfold (PET) and thirtyfold (PET) reduced radiation dose (∼0.11 mSv) was assessed.

RESULTS
The area under the curve of the deep learning algorithm for lung cancer detection was 0.989, 0.983 and 0.970 for standard dose images (PET), and reduced dose PET, and PET reconstruction, respectively. The artificial neural network achieved a sensitivity of 95.9% and 91.5% and a specificity of 98.1% and 94.2%, at standard dose and ultralow dose PET, respectively.

CONCLUSION
Our results suggest that machine learning algorithms may aid fully automated lung cancer detection even at very low effective radiation doses of 0.11 mSv. Further improvement of this technology might improve the specificity of lung cancer screening efforts and could lead to new applications of FDG-PET.

Abstract

OBJECTIVES
We evaluated whether machine learning may be helpful for the detection of lung cancer in FDG-PET imaging in the setting of ultralow dose PET scans.

MATERIALS AND METHODS
We studied the performance of an artificial neural network discriminating lung cancer patients (n = 50) from controls (n = 50) without pulmonary malignancies. A total of 3936 PET slices including images in which the lung tumor is visually present and image slices of patients with no lung cancer were exported. The diagnostic performance of the artificial neural network based on clinical standard dose PET images (PET) as well as with a tenfold (PET) and thirtyfold (PET) reduced radiation dose (∼0.11 mSv) was assessed.

RESULTS
The area under the curve of the deep learning algorithm for lung cancer detection was 0.989, 0.983 and 0.970 for standard dose images (PET), and reduced dose PET, and PET reconstruction, respectively. The artificial neural network achieved a sensitivity of 95.9% and 91.5% and a specificity of 98.1% and 94.2%, at standard dose and ultralow dose PET, respectively.

CONCLUSION
Our results suggest that machine learning algorithms may aid fully automated lung cancer detection even at very low effective radiation doses of 0.11 mSv. Further improvement of this technology might improve the specificity of lung cancer screening efforts and could lead to new applications of FDG-PET.

Statistics

Citations

Dimensions.ai Metrics
4 citations in Web of Science®
7 citations in Scopus®
Google Scholar™

Altmetrics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:04 Faculty of Medicine > University Hospital Zurich > Clinic for Nuclear Medicine
04 Faculty of Medicine > University Hospital Zurich > Clinic for Oncology and Hematology
Dewey Decimal Classification:610 Medicine & health
Language:English
Date:December 2018
Deposited On:05 Feb 2019 11:33
Last Modified:28 Oct 2019 08:01
Publisher:Elsevier
ISSN:0169-5002
OA Status:Closed
Publisher DOI:https://doi.org/10.1016/j.lungcan.2018.11.001
PubMed ID:30527183

Download

Full text not available from this repository.
View at publisher

Get full-text in a library