Journal
NEUROCOMPUTING
Volume 453, Issue -, Pages 299-311Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2020.06.144
Keywords
Lung Cancer; Nodule Detection; CT Scan Images; Convolutional Neural Networks; Recurrent Neural Networks; Long Short Term Memory
Categories
Funding
- Higher Education Commission (HEC) [2(1064)]
Ask authors/readers for more resources
This study investigates the use of computer aided diagnosis systems based on deep learning methods for automatic detection and classification of lung cancer. The proposed Multi-view Convolutional Recurrent Neural Network (MV-CRecNet) model utilizes multiple views to better differentiate lung cancer nodules, outperforming other models in experimental evaluations.
Screening via low-dose Computer Tomography (CT) has been shown to reduce lung cancer mortality rates by at least 20%. However, the assessment of large numbers of CT scans by radiologists is cost intensive, and potentially produces varying and inconsistent results for differing radiologists (and also for temporally-separated assessments by the same radiologist). To overcome these challenges, computer aided diagnosis systems based on deep learning methods have proved effective in automatic detection and classification of lung cancer. Latterly, interest has focused on the full utilization of the 3D information in CT scans using 3D-CNNs and related approaches. However, such approaches do not intrinsically correlate size and shape information between slices. In this work, an innovative approach Multi-view Convolutional Recurrent Neural Network (MV-CRecNet) is proposed that exploits shape, size and cross-slice variations while learning to identify lung cancer nodules from CT scans. The multiple-views that are passed to the model ensure better generalization and the learning of robust features. We evaluate the proposed MV-CRecNet model on the reference Lung Image Database Consortium and Image Database Resource Initiative and Early Lung Cancer Action Program datasets; six evaluation metrics are applied to eleven comparison models for testing. Results demonstrate that proposed methodology outperforms all of the models against all of the evaluation metrics. (c) 2021 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available