Nodular-Deep: Classification of Pulmonary Nodules using Deep Neural Network

Pulmonary nodules represent higher malignancy rate and an accurate detection is very crucial when clinically diagnosis by radiologists from high-resolution computed tomography (HRCT) images. At an early stage, if lung cancer is not diagnosis then it leads toward death. In the past studies, it noticed that many computer-aided diagnostic (CADe) system for classification of lung nodules are developed but tested on the limited dataset and focused on domain expert knowledge. Therefore, those CADx systems were not suitable for large-scale environments. To address these issues, an efficient and effective CADe system is developed to classify the pulmonary lung nodules into benign and malignant classes. In this paper, a new CADe system is implemented through the integration of variants of advanced deep learning algorithms known as Nodular-Deep. Convolutional neural network (CNN) and recurrent neural network (RNN) algorithms are combined with softmax linear classifier without using hand-crafted features and any pre- or post-processing steps. The Nodular-Deep system is tested on the 1200 scans obtained from LIDC-IDRI database covers a set of 2600 pulmonary nodules. This dataset contains an equal number of benign (non-cancerous) and malignant (cancerous) nodules. The performance of nodular-deep system is evaluated through 10-fold cross validation test through the statistical metrics such as sensitivity (SE), Specificity (SP) and area under the receiver operating curve (AUC). On this 2600 pulmonary nodules, the Nodular-Deep system is achieved on average result such as 94% of SE, 96% of SP and 0.95 of AUC. This obtained results demonstrate that this nodular-Deep system outperforms compared to manual segmentation by a radiologist.

[1]  Wen-Huang Cheng,et al.  Computer-aided classification of lung nodules on computed tomography images via deep learning technique , 2015, OncoTargets and therapy.

[2]  Dennis Wollersheim,et al.  Pulmonary nodule classification with deep residual networks , 2017, International Journal of Computer Assisted Radiology and Surgery.

[3]  Yann LeCun,et al.  Computing the stereo matching cost with a convolutional neural network , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Aydin Akan,et al.  Classification of Pulmonary Nodules by Using Hybrid Features , 2013, Comput. Math. Methods Medicine.

[5]  N. Pavlidis,et al.  Lung cancer during pregnancy: A narrative review , 2015, Journal of advanced research.

[6]  Phil Blunsom,et al.  A Convolutional Neural Network for Modelling Sentences , 2014, ACL.

[7]  Bram van Ginneken,et al.  Automatic detection of subsolid pulmonary nodules in thoracic computed tomography images , 2014, Medical Image Anal..

[8]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[9]  Niranjan Khandelwal,et al.  A Combination of Shape and Texture Features for Classification of Pulmonary Nodules in Lung CT Images , 2016, Journal of Digital Imaging.

[10]  Wei Shen,et al.  Multi-scale Convolutional Neural Networks for Lung Nodule Classification , 2015, IPMI.

[11]  Wenqing Sun,et al.  Computer aided lung cancer diagnosis with deep learning algorithms , 2016, SPIE Medical Imaging.

[12]  Heng Huang,et al.  Lung Nodule Classification With Multilevel Patch-Based Context Analysis , 2014, IEEE Transactions on Biomedical Engineering.

[13]  D. Shen,et al.  Computer-Aided Diagnosis with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans , 2016, Scientific Reports.

[14]  Bram van Ginneken,et al.  Bag-of-Frequencies: A Descriptor of Pulmonary Nodules in Computed Tomography Images , 2015, IEEE Transactions on Medical Imaging.

[15]  Wei Li,et al.  Pulmonary Nodule Classification with Deep Convolutional Neural Networks on Computed Tomography Images , 2016, Comput. Math. Methods Medicine.

[16]  Satish Babu,et al.  Role of Computer Aided Diagnosis (CAD) in the detection of pulmonary nodules on 64 row multi detector computed tomography , 2016, Lung India : official organ of Indian Chest Society.

[17]  Wojciech Zaremba,et al.  Recurrent Neural Network Regularization , 2014, ArXiv.

[18]  Qaisar Abbas,et al.  Segmentation of differential structures on computed tomography images for diagnosis lung-related diseases , 2017, Biomed. Signal Process. Control..

[19]  Guixia Kang,et al.  Multiview convolutional neural networks for lung nodule classification , 2017, Int. J. Imaging Syst. Technol..

[20]  Bram van Ginneken,et al.  Pulmonary Nodule Detection in CT Images: False Positive Reduction Using Multi-View Convolutional Networks , 2016, IEEE Transactions on Medical Imaging.

[21]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.