A multi-view CNN model to predict resolving of new lung nodules on follow-up low-dose chest CT.
Authors
Affiliations (7)
Affiliations (7)
- Department of Radiology, University of Groningen, University Medical Center of Groningen, Groningen, The Netherlands. [email protected].
- Data Science in Health (DASH), University of Groningen, University Medical Center of Groningen, Groningen, The Netherlands. [email protected].
- Department of Radiology, University of Groningen, University Medical Center of Groningen, Groningen, The Netherlands.
- Data Science in Health (DASH), University of Groningen, University Medical Center of Groningen, Groningen, The Netherlands.
- Department of Neurology, University of Groningen, University Medical Center of Groningen, Groningen, The Netherlands.
- Data Science in Health (DASH), University of Groningen, University Medical Center of Groningen, Groningen, The Netherlands. [email protected].
- Department of Radiation Oncology, University of Groningen, University Medical Center of Groningen, Groningen, The Netherlands. [email protected].
Abstract
New, intermediate-sized nodules in lung cancer screening undergo follow-up CT, but some of these will resolve. We evaluated the performance of a multi-view convolutional neural network (CNN) in distinguishing resolving and non-resolving new, intermediate-sized lung nodules. This retrospective study utilized data on 344 intermediate-sized nodules (50-500 mm<sup>3</sup>) in 250 participants from the NELSON (Dutch-Belgian Randomized Lung Cancer Screening) trial. We implemented four-fold cross-validation for model training and testing. A multi-view CNN model was developed by combining three two-dimensional (2D) CNN models and one three-dimensional (3D) CNN model. We used 2D, 2.5D, and 3D models for comparison. The models' performance was evaluated using sensitivity, specificity, and area under the ROC curve (AUC). Specificity, indicating what percentage of non-resolving nodules requiring follow-up can be correctly predicted, was maximized. Among all nodules, 18.3% (63) were resolving. The multi-view CNN model achieved an AUC of 0.81, with a mean sensitivity of 0.63 (SD, 0.15) and a mean specificity of 0.93 (SD, 0.02). The model significantly improved performance compared to 2D, 2.5D, or 3D models (p < 0.05). Under the premise of specificity greater than 90% (meaning < 10% of non-resolving nodules are incorrectly identified as resolving), follow-up CT in 14% of individuals could be prevented. The multi-view CNN model achieved high specificity in discriminating new intermediate nodules that would need follow-up CT by identifying non-resolving nodules. After further validation and optimization, this model may assist with decision-making when new intermediate nodules are found in lung cancer screening. The multi-view CNN-based model has the potential to reduce unnecessary follow-up scans when new nodules are detected, aiding radiologists in making earlier, more informed decisions. Predicting the resolution of new intermediate lung nodules in lung cancer screening CT is a challenge. Our multi-view CNN model showed an AUC of 0.81, a specificity of 0.93, and a sensitivity of 0.63 at the nodule level. The multi-view model demonstrated a significant improvement in AUC compared to the three 2D models, one 2.5D model, and one 3D model.