A bilinear convolutional neural network for lung nodules classification on CT images
- PDF / 1,124,683 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 96 Downloads / 206 Views
ORIGINAL ARTICLE
A bilinear convolutional neural network for lung nodules classification on CT images Rekka Mastouri1
· Nawres Khlifa1 · Henda Neji2,3 · Saoussen Hantous-Zannad2,3
Received: 12 June 2020 / Accepted: 21 October 2020 © CARS 2020
Abstract Purpose Lung cancer is the most frequent cancer worldwide and is the leading cause of cancer-related deaths. Its early detection and treatment at the stage of a lung nodule improve the prognosis. In this study was proposed a new classification approach named bilinear convolutional neural network (BCNN) for the classification of lung nodules on CT images. Methods Convolutional neural network (CNN) is considered as the leading model in deep learning and is highly recommended for the design of computer-aided diagnosis systems thanks to its promising results on medical image analysis. The proposed BCNN scheme consists of two-stream CNNs (VGG16 and VGG19) as feature extractors followed by a support vector machine (SVM) classifier for false positive reduction. Series of experiments are performed by introducing the bilinear vector features extracted from three BCNN combinations into various types of SVMs that we adopted instead of the original softmax to determine the most suitable classifier for our study. Results The method performance was evaluated on 3186 images from the public LUNA16 database. We found that the BCNN [VGG16, VGG19] combination with and without SVM surpassed the [VGG16]2 and [VGG19]2 architectures, achieved an accuracy rate of 91.99% against 91.84% and 90.58%, respectively, and an area under the curve (AUC) rate of 95.9% against 94.8% and 94%, respectively. Conclusion The proposed method improved the outcomes of conventional CNN-based architectures and showed promising and satisfying results, compared to other works, with an affordable complexity. We believe that the proposed BCNN can be used as an assessment tool for radiologists to make a precise analysis of lung nodules and an early diagnosis of lung cancers. Keywords Bilinear CNN · SVM · Lung nodules · Classification
Introduction Lung cancer is the first cause of cancer-related death worldwide. The mortality rate of lung cancer surpasses that of prostate, colon and breast cancers. The American Cancer Society estimates that lung cancer is expected to cause 135,720 deaths in 2020, accounting for about 25% of all cancer deaths [1, 2]. Early screening and localization of lung
B
Rekka Mastouri [email protected]
1
Higher Institute of Medical Technologies of Tunis, Research Laboratory of Biophysics and Medical Technologies, University of Tunis el Manar, 1006 Tunis, Tunisia
2
Faculty of Medicine of Tunis, University of Tunis el Manar, 1007 Tunis, Tunisia
3
Medical Imaging Department, Abderrahmen Mami Hospital, 2035 Ariana, Tunisia
cancer in situ at its nodular stage are very important and beneficial to improve the patient’s treatment effect. In fact, early diagnosis of lung cancer increases the five-year survival rate from 18.6 to 56% [2, 3]. Thanks to its high spatial resolution, compute
Data Loading...
