Journal article
Automated detection of lung cancer at ultralow dose PET/CT by deep neural networks - Initial results.
- Schwyzer M Department of Nuclear Medicine, University Hospital Zurich, University of Zurich, Switzerland; Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Switzerland.
- Ferraro DA Department of Nuclear Medicine, University Hospital Zurich, University of Zurich, Switzerland.
- Muehlematter UJ Department of Nuclear Medicine, University Hospital Zurich, University of Zurich, Switzerland; Institute of Diagnostic and Interventional Radiology, University Hospital Zurich, University of Zurich, Switzerland.
- Curioni-Fontecedro A Department of Medical Oncology, University Hospital Zurich, University of Zurich, Switzerland.
- Huellner MW Department of Nuclear Medicine, University Hospital Zurich, University of Zurich, Switzerland.
- von Schulthess GK Department of Nuclear Medicine, University Hospital Zurich, University of Zurich, Switzerland.
- Kaufmann PA Department of Nuclear Medicine, University Hospital Zurich, University of Zurich, Switzerland.
- Burger IA Department of Nuclear Medicine, University Hospital Zurich, University of Zurich, Switzerland.
- Messerli M Department of Nuclear Medicine, University Hospital Zurich, University of Zurich, Switzerland. Electronic address: michael.messerli@usz.ch.
- 2018-12-12
Published in:
- Lung cancer (Amsterdam, Netherlands). - 2018
Artificial intelligence
Deep learning
Low dose
Lung cancer
PET/CT
Early Detection of Cancer
Humans
Lung Neoplasms
Neural Networks, Computer
Positron Emission Tomography Computed Tomography
ROC Curve
Reproducibility of Results
Retrospective Studies
English
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 (PET100%) as well as with a tenfold (PET10%) and thirtyfold (PET3.3%) 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 (PET100%), and reduced dose PET10%, and PET3.3% 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 PET3.3%, 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.
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 (PET100%) as well as with a tenfold (PET10%) and thirtyfold (PET3.3%) 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 (PET100%), and reduced dose PET10%, and PET3.3% 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 PET3.3%, 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.
- Language
-
- English
- Open access status
- closed
- Identifiers
-
- DOI 10.1016/j.lungcan.2018.11.001
- PMID 30527183
- Persistent URL
- https://folia.unifr.ch/global/documents/48031
Statistics
Document views: 39
File downloads: