Convolutional Neural Networks Promising in Lung Cancer T-Parameter Assessment on Baseline FDG-PET/CT
Open Access
- 30 October 2018
- journal article
- research article
- Published by Wiley in Contrast Media & Molecular Imaging
- Vol. 2018, 1-6
Abstract
Aim. To develop an algorithm, based on convolutional neural network (CNN), for the classification of lung cancer lesions as T1-T2 or T3-T4 on staging fluorodeoxyglucose positron emission tomography (FDG-PET)/CT images. Methods. We retrospectively selected a cohort of 472 patients (divided in the training, validation, and test sets) submitted to staging FDG-PET/CT within 60 days before biopsy or surgery. TNM system seventh edition was used as reference. Postprocessing was performed to generate an adequate dataset. The input of CNNs was a bounding box on both PET and CT images, cropped around the lesion centre. The results were classified as Correct (concordance between reference and prediction) and Incorrect (discordance between reference and prediction). Accuracy (Correct/[Correct + Incorrect]), recall (Correctly predicted T3-T4/[all T3-T4]), and specificity (Correctly predicted T1-T2/[all T1-T2]), as commonly defined in deep learning models, were used to evaluate CNN performance. The area under the curve (AUC) was calculated for the final model. Results. The algorithm, composed of two networks (a “feature extractor” and a “classifier”), developed and tested achieved an accuracy, recall, specificity, and AUC of 87%, 69%, 69%, and 0.83; 86%, 77%, 70%, and 0.73; and 90%, 47%, 67%, and 0.68 in the training, validation, and test sets, respectively. Conclusion. We obtained proof of concept that CNNs can be used as a tool to assist in the staging of patients affected by lung cancer.Keywords
Funding Information
- Sanofi (IG-2016-18585)
- Associazione Italiana per la Ricerca sul Cancro (IG-2016-18585)
This publication has 14 references indexed in Scilit:
- Ability of FDG PET and CT radiomics features to differentiate between primary and metastatic lung lesionsEuropean Journal of Nuclear Medicine and Molecular Imaging, 2018
- A deep 3D residualCNNfor false‐positive reduction in pulmonary nodule detectionMedical Physics, 2018
- Deep Learning: A Primer for RadiologistsRadioGraphics, 2017
- Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentationMedical Image Analysis, 2017
- Multilevel Contextual 3-D CNNs for False Positive Reduction in Pulmonary Nodule DetectionIEEE Transactions on Biomedical Engineering, 2016
- Efficacy of lymph node dissection during robotic-assisted lobectomy for non-small cell lung cancer: retrospective review of 159 consecutive casesJournal of Thoracic Disease, 2016
- Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional NetworksIEEE Transactions on Medical Imaging, 2016
- Imaging of lung cancer: Implications on staging and managementIndian Journal of Radiology and Imaging, 2015
- Pathological response after neoadjuvant chemotherapy in resectable non-small-cell lung cancers: proposal for the use of major pathological response as a surrogate endpointThe Lancet Oncology, 2014
- Diagnostic value of fluorine 18 fluorodeoxyglucose positron emission tomography/computed tomography for the detection of metastases in non–small‐cell lung cancer patientsInternational Journal of Cancer, 2012