Research on Different Classifiers for Early Detection of Lung Nodules
Madan. K1, Bhanu Anusha K2, Pavan Kalyan. P3, Neelima. N4
1Madan. K, Department of Electronics & Communication Engineering, Amrita School of Engineering, Bengaluru Amrita Vishwa Vidyapeetham (Tamil Nadu), India.
2Bhanu Anusha K, Department of Electronics & Communication Engineering, Amrita School of Engineering, Bengaluru Amrita Vishwa Vidyapeetham (Tamil Nadu), India.
3Pavan Kalyan. P, Department of Electronics & Communication Engineering, Amrita School of Engineering, Bengaluru Amrita Vishwa Vidyapeetham (Tamil Nadu), India.
4Neelima. N, Department of Electronics & Communication Engineering, Amrita School of Engineering, Bengaluru Amrita Vishwa Vidyapeetham (Tamil Nadu), India.
Manuscript received on 22 July 2019 | Revised Manuscript received on 03 August 2019 | Manuscript Published on 10 August 2019 | PP: 1037-1040 | Volume-8 Issue-2S3 July 2019 | Retrieval Number: B11940782S319/2019©BEIESP | DOI: 10.35940/ijrte.B1194.0782S319
Open Access | Editorial and Publishing 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: Lung cancer is one of the most common deadliest disease which has highest death rate as per the recent medical research. However, research indicates that early detection of lung cancer improves chances of survival. The disease is identified using nodules attached to lung walls and lung parenchyma. Nodules plays significant role in identifying cancer in lungs. The proposed approach to determine lung nodules has three stages preprocessing, feature extraction and classification. Segmentation is the preprocessing technique involves two phases namely lung parenchyma segmentation and lung nodules segmentation. Then, texture features and geometric features are extracted using feature extraction algorithms. Lastly, using classification techniques the nodules are classified as benign or malign. TCIA dataset was used for validation of the proposed approach. Form the dataset, CT images were used which have high density resolution and adequate information which helps to find every small detail easily. The proposed method helps in improving accuracy to find number of the lung nodules in lung region and also helps is differentiating benign and malign nodules using CNN architecture. Different classifiers such as SVM, MLP and CNN classifiers are used in comparison analysis. As the result, we conclude that the approach of feature extraction with CNN decreases the false positive rate significantly compared to the existing classification approaches.
Keywords: Lung Nodules, Thresholding, Morphological Operators, Segmentation, CNN Classifier.
Scope of the Article: Classification