To Get any Project for CSE, IT ECE, EEE Contact Me @ 09666155510, 09849539085 or mail us - ieeefinalsemprojects@gmail.com-Visit Our Website: www.finalyearprojects.org
IEEE 2014 MATLAB IMAGE PROCESSING PROJECTS Lung nodule classification with multi level patch based context analysis
1. GLOBALSOFT TECHNOLOGIES
IEEE PROJECTS & SOFTWARE DEVELOPMENTS
IEEE FINAL YEAR PROJECTS|IEEE ENGINEERING PROJECTS|IEEE STUDENTS PROJECTS|IEEE
BULK PROJECTS|BE/BTECH/ME/MTECH/MS/MCA PROJECTS|CSE/IT/ECE/EEE PROJECTS
CELL: +91 98495 39085, +91 99662 35788, +91 98495 57908, +91 97014 40401
Visit: www.finalyearprojects.org Mail to:ieeefinalsemprojects@gmail.com
Lung Nodule Classification with Multi-Level
Patch-based Context Analysis
Abstract—In this paper, we propose a novel classification
2. Abstract
In this paper, we propose a novel classification method for the four types of lung nodules, i.e.,
well-circumscribed, vascularized, juxta-pleural and pleural-tail, in low dose computed
tomography (LDCT) scans. The proposed method is based on contextual analysis by combining
the lung nodule and surrounding anatomical structures, and has three main stages: an adaptive
patch-based division is used to construct concentric multi-level partition; then, a new feature set
is designed to incorporate intensity, texture and gradient information for image patch feature
description and then a contextual latent semantic analysis-based classifier is designed to calculate
the probabilistic estimations for the relevant images. Our proposed method was evaluated on a
publicly available dataset and clearly demonstrated promising classification performance.
3. Existing Method
Among various gradient-based methods, HOG is being widely used and can also improve
performance considerably when coupled with LBP. However, unlike SIFT and MR8+LBP
descriptors, the raw HOG descriptor cannot handle rotation-invariant problems. Therefore, we
designed a multi-orientation HOG descriptor inspired by our previous work to provide further an
advanced gradient description in addition to that from SIFT. The designed descriptor is adaptive
to the locations of patches relative to the centroid of the nodule, rather than having the same
initial orientation for all patches.
4. Proposed Method
During the experiments, the selected training images were also included in the testing stage for
the proposed method as well as all control methods. In this way, the global dictionary for
contextual analysis classification could be obtained through the whole dataset, and more images
were incorporated for testing.
Merits
Complexity is high.
Demerits
Complexity is low.
5. Results
The distributions of classification rates given parameter on the training and testing
datasets.