Abstract
This research is concerned with malignant pulmonary nodule detection (PND) in low-dose CT scans. Due to its crucial role in the early diagnosis of lung cancer, PND has considerable potential in improving the survival rate of patients. We propose a two-stage framework that exploits the ever-growing advances in deep neural network models, and that is comprised of a semantic segmentation stage followed by localization and classification. We employ the recently published DeepLab model for semantic segmentation, and we show that it significantly improves the accuracy of nodule detection compared to the classical U-Net model and its most recent variants. Using the widely adopted Lung Nodule Analysis dataset (LUNA16), we evaluate the performance of the semantic segmentation stage by adopting two network backbones, namely, MobileNet-V2 and Xception. We present the impact of various model training parameters and the computational time on the detection accuracy, featuring a 79.1% mean intersection-over-union (mIoU) and an 88.34% dice coefficient. This represents a mIoU increase of 60% and a dice coefficient increase of 30% compared to U-Net. The second stage involves feeding the output of the DeepLab-based semantic segmentation to a localization-then-classification stage. The second stage is realized using Faster RCNN and SSD, with an Inception-V2 as a backbone. On LUNA16, the two-stage framework attained a sensitivity of 96.4%, outperforming other recent models in the literature, including deep models. Finally, we show that adopting a transfer learning approach, particularly, the DeepLab model weights of the first stage of the framework, to infer binary (malignant-benign) labels on the Kaggle dataset for pulmonary nodules achieves a classification accuracy of 95.66%, which represents approximately 4% improvement over the recent literature.
Highlights
Lung cancer remains the most prevalent cancer in the world
We proposed a two-stage framework that employs deep learning frameworks for pulmonary nodule detection (PND) in CT scans, trained and tested on Lung Nodule Analysis challenge (LUNA16) and Kaggle 2017 datasets
We proposed the recently proposed DeepLab-V3 plus model for semantic segmentation, and we demonstrated that it is capable of attaining state-of-the-art Dice Coefficient and
Summary
Because early detection can reduce the mortality rate, high-risk individuals are being screened with low-dose CT scans. Predicting lung cancer from a chest scan has relied on reducing the high-dimensional CT scan to a few regions of interest. An example of these regions of interest is solitary pulmonary nodules. Diagnostics 2020, 10, 131; doi:10.3390/diagnostics10030131 www.mdpi.com/journal/diagnostics (SPN) [1], which are usually an early indication of lung cancer. Lung cancer late diagnosis rates represent 70–80% of the patients, we can increase early diagnosis by improving the quality of pulmonary nodule detection (PND), which enhances the chance of successful surgical treatment
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
