Phase Recognition of Lung Cancer via Steerable Riesz Wavelets with Rf Algorithm
S. N. V. Nishanth1, S. Suryadev2, Ch. Charan Teja Reddy3, S. Kalaivani4
1NS. N. V. Nishanth , School of Electronics Engineering, Vellore institute of technology, Vellore, India.
2S.Suryadev, School of Electronics Engineering, Vellore institute of technology, Vellore, India.
3Ch.Charan Teja Reddy, School of Electronics Engineering, Vellore institute of technology, Vellore, India.
4S.Kalaivani*, School of Electronics Engineering, Vellore institute of technology, Vellore, India.
Manuscript received on May 16, 2020. | Revised Manuscript received on May 19, 2020. | Manuscript published on June 10, 2020. | PP: 491-496 | Volume-9 Issue-8, June 2020. | Retrieval Number: H6520069820/2020©BEIESP | DOI: 10.35940/ijitee.H6520.069820
Open Access | Ethics and Policies | Cite | Mendeley
© 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: Lung cancer is one of the diseases which has a high mortality. If the condition is detected earlier, then it is easier to reduce the mortality rate. This lung cancer has caused more deaths in the world than any other cancer. The main objective is to predict lung cancer using a machine learning algorithm. Several computer-aided systems have been designed to reduce the mortality rate due to lung cancer. Machine learning is a promising tool to predict lung cancer in its early phase or stage, where the features of images are trained using a classification model. Generally, machine learning is used to have a good prediction, but in some models, due to lack of efficient feature extraction value, the training has not been done more effectively; hence the predictions are poor. In order to overcome this limitation, the proposed covariant texture model utilizing the steerable Riesz wavelets feature extraction technique to increase the effectiveness of training via the Random Forest algorithm. In this proposed model, the RF algorithm is employed to predict whether the nodule in the image is benign or malignant ii) to find the level of severity (1 to 5), if it is a malignant nodule. Our experiment result can be used as a tool to support the diagnosis and to analyze at an earlier stage of cancer to cure it.
Keywords: Benign nodule, Malignant Nodule, Random Forest, Random Walker, Steerable Riesz wavelets.
Scope of the Article: Analysis of Algorithms and Computational Complexity