ANFIS IN THE CHARACTERIZATION OF FIBROSIS AND CARCINOMA USING LUNG CT IMAGES
Journal Title: Indian Journal of Computer Science and Engineering - Year 2013, Vol 4, Issue 4
Abstract
The diagnosis of tuberculosis and lung cancer is difficult, as symptoms of both diseases are similar. Due to high TB prevalence and radiological similarities, a large number of lung cancer patients initially get wrongly treated for tuberculosis based on radiological picture alone. However, treating TB leads to inflammatory fibrosis in some of the patients. In all these cases, the diagnosis is confirmed only with a biopsy which is an invasive technique that is usually performed via Bronchoscopy or CT – guided biopsy. There comes the need of an efficient Computer Aided Diagnosis(CAD) of the fibrosis and adenocarcinoma diseases. The increased chance of characterizing tissues with the help of CAD and the achievable workload reduction for the radiologist demand the usage of these systems in CT screenings as well as daily hospital practice. Generally, the CAD is designed based on the Region of Interest(ROI) given by the radiologist which makes the system semi-automatic. Our work presents a fully automated method of characterization of carcinoma from other lung abnormalities namely fibrosis and suspicious of tuberculosis. A comparison study is also done by evaluating the performance of Adaptive Neuro-Fuzzy Inference System(ANFIS) as a Classifier with three set of features. These feature set include entropy and parameters extracted by Gray Level Co-Occurrence Matrix(GLCM) and Gray Level Run Length Matrix(GLRLM).
Authors and Affiliations
D. Lakshmi , Roy Santhosham , H. Ranganathan
Keywords
Related Articles
- EP ID EP141238
- DOI -
- Views 106
- Downloads 0
Refined Anchor Free Localisation for Wireless Sensor Monitoring in Wireless Sensor Networks
Localisation is required for many ad-hoc sensor network applications. In this paper we look at the limitations of the existing localisation technique, Anchor Free Localisation (AFL) with regards to coping with non-unifor...
PERFORMANCE ANALYSIS OF ENERGY EFFICIENT CLUSTERING SCHEMES FOR WSN
Clustering enables energy constrained wireless sensor networks to consume less battery power for routing the data packets. In order to achieve the key goal of prolonging the lifetime of sensor nodes besides avoiding unde...
Predictive congestion control mechanism for MANET
In adhoc networks connection failure between source and destination often occurs, due to mobility of nodes. After every failure the connection between source and destination gets disconnected.The problem is while sending...
A literature study on clustering the uncertainty data
Clustering is one of the important topics in data mining. The purpose of clustering is to group the similar data items. Clustering the uncertainty data is not an easy task but an essential task in data mining. Uncertain...
Moving Object Tracking Techniques: A Critical Review
Moving Object Tracking is one of the challenging problems in the field of computer vision, surveillance, traffic monitoring, video compression etc. The goal of object tracking is to locate a moving object in consecutive...