Performance Evaluation of a Deep Learning System for Differential Diagnosis of Lung Cancer With Conventional CT and FDG PET/CT Using Transfer Learning and Metadata
Authors:
- 21 April 2021
- journal article
- research article
- Published by Wolters Kluwer Health in Clinical Nuclear Medicine
- Vol. 46 (8) , 635-640
Abstract
Purpose: We aimed to evaluate the performance of a deep learning system for differential diagnosis of lung cancer with conventional CT and FDG PET/CT using transfer learning (TL) and metadata. Methods: A total of 359 patients with a lung mass or nodule who underwent noncontrast chest CT and FDG PET/CT prior to treatment were enrolled retrospectively. All pulmonary lesions were classified by pathology (257 malignant, 102 benign). Deep learning classification models based on ResNet-18 were developed using the pretrained weights obtained from ImageNet data set. We propose a deep TL model for differential diagnosis of lung cancer using CT imaging data and metadata with SUVmax and lesion size derived from PET/CT. The area under the receiver operating characteristic curve (AUC) of the deep learning model was measured as a performance metric and verified by 5-fold cross-validation. Results: The performance metrics of the conventional CT model were generally better than those of the CT of PET/CT model. Introducing metadata with SUVmax and lesion size derived from PET/CT into baseline CT models improved the diagnostic performance of the CT of PET/CT model (AUC = 0.837 vs 0.762) and the conventional CT model (AUC = 0.877 vs 0.817). Conclusions: Deep TL models with CT imaging data provide good diagnostic performance for lung cancer, and the conventional CT model showed overall better performance than the CT of PET/CT model. Metadata information derived from PET/CT can improve the performance of deep learning systems.Keywords
This publication has 26 references indexed in Scilit:
- Diagnostic value of 18F-FDG-PET/CT for the evaluation of solitary pulmonary nodulesNuclear Medicine Communications, 2017
- Update in the Evaluation of the Solitary Pulmonary NoduleRadioGraphics, 2014
- Contourlet Textual Features: Improving the Diagnosis of Solitary Pulmonary Nodules in Two Dimensional CT ImagesPLOS ONE, 2014
- Multidetector CT of Solitary Pulmonary NodulesThoracic Surgery Clinics, 2010
- A Comparison of the Diagnostic Accuracy of18F-FDG PET and CT in the Characterization of Solitary Pulmonary NodulesJournal of Nuclear Medicine, 2008
- Accuracy of transmission CT and FDG-PET in the detection of small pulmonary nodules with integrated PET/CTEuropean Journal of Nuclear Medicine and Molecular Imaging, 2006
- FDG PET of Infection and InflammationRadioGraphics, 2005
- F-18 Fluorodeoxyglucose Chest Uptake in Lung Inflammation and InfectionClinical Nuclear Medicine, 2000
- A method of comparing the areas under receiver operating characteristic curves derived from the same cases.Radiology, 1983
- The meaning and use of the area under a receiver operating characteristic (ROC) curve.Radiology, 1982