Artificial intelligence and radiomics enhance the positive predictive value of digital chest tomosynthesis for lung cancer detection within SOS clinical trial
- 1 July 2020
- journal article
- research article
- Published by Springer Science and Business Media LLC in European Radiology
- Vol. 30 (7), 4134-4140
- https://doi.org/10.1007/s00330-020-06783-z
Abstract
Objective To enhance the positive predictive value (PPV) of chest digital tomosynthesis (DTS) in the lung cancer detection with the analysis of radiomics features. Method The investigation was carried out within the SOS clinical trial (NCT03645018) for lung cancer screening with DTS. Lung nodules were identified by visual analysis and then classified using the diameter and the radiological aspect of the nodule following lung-RADS. Haralick texture features were extracted from the segmented nodules. Both semantic variables and radiomics features were used to build a predictive model using logistic regression on a subset of variables selected with backward feature selection and using two machine learning: a Random Forest and a neural network with the whole subset of variables. The methods were applied to a train set and validated on a test set where diagnostic accuracy metrics were calculated. Results Binary visual analysis had a good sensitivity (0.95) but a low PPV (0.14). Lung-RADS classification increased the PPV (0.19) but with an unacceptable low sensitivity (0.65). Logistic regression showed a mildly increased PPV (0.29) but a lower sensitivity (0.20). Random Forest demonstrated a moderate PPV (0.40) but with a low sensitivity (0.30). Neural network demonstrated to be the best predictor with a high PPV (0.95) and a high sensitivity (0.90). Conclusions The neural network demonstrated the best PPV. The use of visual analysis along with neural network could help radiologists to reduce the number of false positive in DTS.Funding Information
- Fondazione Cassa di Risparmio di Cuneo
This publication has 22 references indexed in Scilit:
- Performance of Lung-RADS in the National Lung Screening TrialAnnals of Internal Medicine, 2015
- Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD): Explanation and ElaborationAnnals of Internal Medicine, 2015
- Lung Cancer Detection with Digital Chest Tomosynthesis: Baseline Results from the Observational Study SOSJournal of Thoracic Oncology, 2013
- Results of Initial Low-Dose Computed Tomographic Screening for Lung CancerThe New England Journal of Medicine, 2013
- Training and assessing classification rules with imbalanced dataData Mining and Knowledge Discovery, 2012
- Benefits and Harms of CT Screening for Lung CancerJAMA, 2012
- Automated lung segmentation in digital chest tomosynthesisMedical Physics, 2012
- Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic ScreeningThe New England Journal of Medicine, 2011
- Guidelines for Management of Small Pulmonary Nodules Detected on CT Scans: A Statement from the Fleischner SocietyRadiology, 2005
- THE TREATMENT OF TIES IN RANKING PROBLEMSBiometrika, 1945