Nodular-Deep: Classifcation of Pulmonary Nodules using Deep Neural Network
Journal Title: International Journal of Medical Research & Health Sciences (IJMRHS) - Year 2017, Vol 6, Issue 8
Abstract
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 classifcation 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 effcient 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 classifer 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), Specifcity (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.
Authors and Affiliations
Qaisar Abbas| College of Computer and Information Sciences, Al-Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi Arabia Corresponding e-mail: qaisarabbasphd@gmail.com
Keywords
Related Articles
- EP ID EP12430
- DOI -
- Views 360
- Downloads 15
Effect of core stability exercise on postural stability in children with Down syndrome
Down syndrome is one of the commonest causes of developmental delay in children. Postural stability problems often exist with Down syndrome. To investigate the effect of core stability exercises on postural stability in...
150-Cavity Synchronization by Extended Loop in Neuraminidase of 2009 H1N1 Influenza Type A Virus: A Simulation Study
Neuraminidase (NA) is a novel drug target for antiviral inhibitors. In this druggable target, a cavity adjacent to the active site exists and is known as the 150-cavity. NA is divided into two groups: Group 1 and Group...
EVALUATION OF CORTICOSTEROID USE PATTERN IN STEROID RESPONSIVE DERMATOLOGICAL CONDITIONS
Background: Skin diseases account for 2% of the Out Patient Department based consultations in general practice worldwide, which includes diseases like, Dermatitis, Eczema, Acne, Urticaria, Psoriasis, skin allergy etc....
Assessment of Urinary-5-Hydroxyindolacetic Acid as A Diagnostic Parameter in Early Detection of Acute Appendicitis
Background: Acute appendicitis is the most common abdominal surgical emergency especially in children and young adults. The diagnosis of appendicitis is diffcult because half the cases are incorrectly identifed. Seroton...
Protein Tyrosine Phosphatase 1B (PTPN1) Gene polymorphism (467T>C) and Metabolic Syndrome: A Pilot Study
Background: The metabolic syndrome (Met S) is composed of heart attack predisposing factors as diabetes, abdominal obesity, high cholesterol, and high blood pressure. Protein tyrosine phosphatase 1B (PTP1B), is negative...