Volume 22, Issue 2, April 2016, Pages 431–438
Resmi R. Nair1, B. Thamilvalluvan2, M. Anto Bennet3, P. Lavanya4, S. Ragavi5, and S. Arun Kumar6
1 Assistant Professor, Department of Electronics and Communication Engineering, VELTECH, Chennai-600062, India
2 Assistant Professor, (Electronics and Communication Engineering) Veltech, Chennai-600062, India
3 Professor, Department of Electronics and Communication Engineering, VELTECH, Chennai-600062, India
4 UG Student, Department of Electronics and Communication Engineering, VELTECH, Chennai-600062, India
5 UG Student, Department of Electronics and Communication Engineering, VELTECH, Chennai-600062, India
6 UG Student, Department of Electronics and Communication Engineering, VELTECH, Chennai-600062, India
Original language: English
Copyright © 2016 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Computer-aided detection (CADe) of pulmonary nodules is critical to assist radiologist in early detection of lung cancer from computed tomography (CT) scans. So in proposed system we use CADe system based on hierarchical vector quantization (VQ) scheme. On comparing with commonly-used simple thresholding approach, the high-level VQ yields accurate segmentation of lungs from chest volume and in identifying initial nodule candidates (INCs) within lungs, low-level VQ proves to be effective for INC detection and segmentation, as well as computationally efficient compared to existing approaches. This proposed system also reduces false positive detection. False positive reduction is conducted via the rule based filtering operation in combination with feature-based support vector machine classifier. This proposed system shows out performance and demonstrate its potential for early detection of pulmonary nodules via CT imaging.
Author Keywords: CADe system, INC detection, INC segmentation, Computed tomography scans, Initial nodule candidates, Juxtapleural nodule annotation, Thoracic CT images.
Resmi R. Nair1, B. Thamilvalluvan2, M. Anto Bennet3, P. Lavanya4, S. Ragavi5, and S. Arun Kumar6
1 Assistant Professor, Department of Electronics and Communication Engineering, VELTECH, Chennai-600062, India
2 Assistant Professor, (Electronics and Communication Engineering) Veltech, Chennai-600062, India
3 Professor, Department of Electronics and Communication Engineering, VELTECH, Chennai-600062, India
4 UG Student, Department of Electronics and Communication Engineering, VELTECH, Chennai-600062, India
5 UG Student, Department of Electronics and Communication Engineering, VELTECH, Chennai-600062, India
6 UG Student, Department of Electronics and Communication Engineering, VELTECH, Chennai-600062, India
Original language: English
Copyright © 2016 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Abstract
Computer-aided detection (CADe) of pulmonary nodules is critical to assist radiologist in early detection of lung cancer from computed tomography (CT) scans. So in proposed system we use CADe system based on hierarchical vector quantization (VQ) scheme. On comparing with commonly-used simple thresholding approach, the high-level VQ yields accurate segmentation of lungs from chest volume and in identifying initial nodule candidates (INCs) within lungs, low-level VQ proves to be effective for INC detection and segmentation, as well as computationally efficient compared to existing approaches. This proposed system also reduces false positive detection. False positive reduction is conducted via the rule based filtering operation in combination with feature-based support vector machine classifier. This proposed system shows out performance and demonstrate its potential for early detection of pulmonary nodules via CT imaging.
Author Keywords: CADe system, INC detection, INC segmentation, Computed tomography scans, Initial nodule candidates, Juxtapleural nodule annotation, Thoracic CT images.
How to Cite this Article
Resmi R. Nair, B. Thamilvalluvan, M. Anto Bennet, P. Lavanya, S. Ragavi, and S. Arun Kumar, “Early Detection of Pulmonary Nodules Using Hierarchical Vector Quantization Scheme,” International Journal of Innovation and Scientific Research, vol. 22, no. 2, pp. 431–438, April 2016.
