Mattias Ohlsson
Professor
Automated interpretation of PET/CT images in patients with lung cancer.
Author
Summary, in English
Purpose: To develop a completely automated method based on image processing techniques and artificial neural networks for the interpretation of combined [18F]fluorodeoxyglucose (FDG) positron emission tomography (PET) and computed tomography (CT) images for the diagnosis and staging of lung cancer.
Methods: A total of 87 patients who underwent PET/CT examinations due to suspected lung cancer comprised the training group. The test group consisted of PET/CT images from 49 patients suspected with lung cancer. The consensus interpretations by two experienced physicians were used as the 'gold standard' image interpretation. The training group was used in the development of the automated method. The image processing techniques included algorithms for segmentation of the lungs based on the CT images and detection of lesions in the PET images. Lung boundaries from the CT images were used for localization of lesions in the PET images in the feature extraction process. Eight features from each examination were used as inputs to artificial neural networks trained to classify the images. Thereafter, the performance of the network was evaluated in the test set.
Results: The performance of the automated method measured as the area under the receiver operating characteristic curve, was 0.97 in the test group, with an accuracy of 92%. The sensitivity was 86% at a specificity of 100%.
Conclusions: A completely automated method using artificial neural networks can be used to detect lung cancer with such a high accuracy that the application as a clinical decision support tool appears to have significant potential.
Methods: A total of 87 patients who underwent PET/CT examinations due to suspected lung cancer comprised the training group. The test group consisted of PET/CT images from 49 patients suspected with lung cancer. The consensus interpretations by two experienced physicians were used as the 'gold standard' image interpretation. The training group was used in the development of the automated method. The image processing techniques included algorithms for segmentation of the lungs based on the CT images and detection of lesions in the PET images. Lung boundaries from the CT images were used for localization of lesions in the PET images in the feature extraction process. Eight features from each examination were used as inputs to artificial neural networks trained to classify the images. Thereafter, the performance of the network was evaluated in the test set.
Results: The performance of the automated method measured as the area under the receiver operating characteristic curve, was 0.97 in the test group, with an accuracy of 92%. The sensitivity was 86% at a specificity of 100%.
Conclusions: A completely automated method using artificial neural networks can be used to detect lung cancer with such a high accuracy that the application as a clinical decision support tool appears to have significant potential.
Department/s
- Computational Biology and Biological Physics - Has been reorganised
- Clinical Physiology and Nuclear Medicine, Malmö
- Department of Translational Medicine
Publishing year
2007
Language
English
Pages
79-84
Publication/Series
Nuclear Medicine Communications
Volume
28
Issue
2
Links
Document type
Journal article
Publisher
Lippincott Williams & Wilkins
Topic
- Radiology, Nuclear Medicine and Medical Imaging
Status
Published
Research group
- Clinical Physiology, Malmö
ISBN/ISSN/Other
- ISSN: 1473-5628