Extreme Learning Machine for Thyroid Nodule Classification with Graph Cluster Ant Colony Optimization Based Feature Selection
Sayyad Rasheeduddin1, Kurra Rajasekhar Rao2
1Sayyad Rasheed Uddin, Research Scholar, Department of Computer-Science-Engineering, Nagarjuna University, Guntur, AP.
2Dr.Kurra Raja Rajasekhar Rao, Prof. Department of Computer-Science-Engineering, Usha Rama College of Engg and Technology, Vijayawada.
Manuscript received on 03 March 2019 | Revised Manuscript received on 08 March 2019 | Manuscript published on 30 July 2019 | PP: 1478-1488 | Volume-8 Issue-2, July 2019 | Retrieval Number: B2115078219/19©BEIESP | DOI: 10.35940/ijrte.B2115.078219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Thyroid nodule is defined as an endocrine malignancy that occurs in humans due to abnormal growth of cells. Recently, an increasing level of thyroid incidence has been identified worldwide. Thus, it is necessary to detect the nodules at an early stage. Ultrasonography is an important tool that is utilized for the detection as well as differentiation of malignant thyroid nodules from benign nodules. The nodules in ultrasound appear in different heterogenic forms, which are difficult to differentiate by the physicians. Further, large number of features available in US characteristics increases the computation time as well as complexity of classification. In this paper, Graph-Clustering Ant Colony Optimization based Extreme Learning Machine approach is proposed to achieve efficient diagnosis of thyroid nodules. It will enhance thyroid nodule classification by selecting only the optimal features and further using it for improving the function of classifier. The main goal of this technique is to differentiate the malignant nodules from the benign nodules. The performance of both feature selection and classification are evaluated through parameters such as accuracy, AUC, sensitivity and specificity. From the experimental results, it is revealed that the proposed method is significantly better than the existing methods. Thus, it is considered to be an effective tool for diagnosing the thyroid nodules with less complexity and reduced computation time.
Keywords: Thyroid Nodule, Ultrasound Image, Diagnosis, Feature Extraction, Nodules Classification.
Scope of the Article: Classification