Next Article in Journal
The Expansion of Cholangioscopy: Established and Investigational Uses of SpyGlass in Biliary and Pancreatic Disorders
Previous Article in Journal
Analysis of Let-7 Family miRNA in Plasma as Potential Predictive Biomarkers of Diagnosis for Papillary Thyroid Cancer
Open AccessArticle

A Two-Stage Framework for Automated Malignant Pulmonary Nodule Detection in CT Scans

by Shimaa EL-Bana 1, Ahmad Al-Kabbany 2,3,4,*,† and Maha Sharkas 3,†
1
Alexandria Higher Institute of Engineering and Technology, Alexandria 21311, Egypt
2
Intelligent Systems Lab, Arab Academy for Science, Technology, and Maritime Transport, Alexandria 21937, Egypt
3
Department of Electronics and Communications Engineering, Arab Academy for Science, Technology, and Maritime Transport, Alexandria 21937, Egypt
4
Department of Research and Development, VRapeutic, Cairo 11728, Egypt
*
Author to whom correspondence should be addressed.
Current address: Department of Electronics and Communications Engineering, Arab Academy for Science, Technology, and Maritime Transport, Alexandria 21937, Egypt.
Diagnostics 2020, 10(3), 131; https://doi.org/10.3390/diagnostics10030131
Received: 7 January 2020 / Revised: 13 February 2020 / Accepted: 18 February 2020 / Published: 28 February 2020
(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)
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. View Full-Text
Keywords: CAD system; lung cancer; pulmonary nodules; DeepLab-V3; CNN; transfer learning; tensorflow CAD system; lung cancer; pulmonary nodules; DeepLab-V3; CNN; transfer learning; tensorflow
Show Figures

Figure 1

MDPI and ACS Style

EL-Bana, S.; Al-Kabbany, A.; Sharkas, M. A Two-Stage Framework for Automated Malignant Pulmonary Nodule Detection in CT Scans. Diagnostics 2020, 10, 131.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop