Article ID Journal Published Year Pages File Type
6872840 Future Generation Computer Systems 2018 9 Pages PDF
Abstract
Nasopharyngeal carcinoma (NPC) is a serious disease with diverse prognoses and the diffusive development of the tumors further complicates the diagnosis. However, in most cases, surgery is performed by resecting the tumor that decides the life expectancy of a patient. Certainly, the graphical portrayal is a fundamental factor to distinguish and examine an NPC tumor; and, the exact nasopharyngeal carcinoma perception remains an important errand. It is crucial to improve the extent of resection for the irregular tissues while sparing the normal ones. There are several methods to envision the nasopharyngeal carcinoma, but the main problem with these strategies is the inability to imagine the border points of the nasopharyngeal tumor accurately in detail. In addition, the inability to separate the normal tissues from the undesirable ones prompts the assessment and calculation of a wrong tumor measure. NPC diagnosis is a difficult and challenging process owing to the possible shapes and regions of tumors and intensity of the images. The pathological identification of the nasopharyngeal carcinoma and comparing typical and anomalous tissues require a set of scientific strategies for the extraction of features. The aim of this paper was to outline and assess a novel method using machine learning approaches based on genetic algorithm for NPC feature selection and artificial neural networks for an automated NPC detection of the NPC tissues from endoscopic images. The proposed approach was validated by comparing the number of NPC identified through this technique against the manual checking by the ENT specialists. The classifier lists a high precision of 96.22%, the sensitivity of 95.35%, and specificity of 94.55%. Additionally, the feature chosen process makes the Artificial Neural Networks classifier straightforward and more efficient.
Related Topics
Physical Sciences and Engineering Computer Science Computational Theory and Mathematics
Authors
, , , , , ,