Analysis Of Classification Methods For Diagnosis Of Pulmonary Nodules In CT Images

Baboo, Capt. Dr. S.Santhosh; Iyyapparaj, E.

doi:10.9790/0661-1903011825

Cited by 1 publication

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The contextual clustering is an algorithm uses an overlapping window of 5x5 pixels for the segmented image.The Threshold value for the segmented image is T=140 and control parameter β ranges from 0 to 1 [1,2].All the steps of contextual clustering algorithm is adopted to segment the lung region from CT lung image . In images, Region growing is a method used in the identification of connected regions of interest that makes use of the threshold values with respect to a discrete connectivity.…”

Section: Contextual Clustering With Region Growingmentioning

confidence: 99%

“…For setting the threshold value in segmenting the region of interest that are present in the CT lung image, the combination of region growing and clustering is used. The implementation of region growing based contextual clustering is done as follows [ The contextual value Vcc is calculated as below [1] (1) Input lung image was taken from the LIDC-Lung image database consortium which is further processed for the segmentation. In the contextual clustering splitting of the entire image is done as 5x5 windows on the basis of the region-based growing method which is an iterative method.…”

Section: Contextual Clustering With Region Growingmentioning

confidence: 99%

See 1 more Smart Citation

Fast and Adaptive Detection of Pulmonary Nodules in Thoracic CT Images Using a Contextual Clustering Based Region Growing

Bhakkiyalakshmi¹,

Ponnammal²,

M³

et al. 2018

IJET

View full text Add to dashboard Cite

For segmenting the Region of interest and for analyzing each area separately to locate whether pathologies present in it or not, we use segmentation process as the first step to diagnose lung image using ComputerAided Diagnosis. In this paper, ROI is segmented by using supervised Contextual Clustering in addition to the Region growing algorithm. Accurate segmentation of the lungs from the chest volume is obtained from the Contextual clustering which is better than all other thresholding approaches that are simple. Initial Nodule Candidates can be detected and segmented effectively by contextual clustering which is considered to be the most effective approach when compared to the remaining approaches present.We combine rule-based filtering and a feature based support vector machine using which we can reduce the False-positives (FP) ,custom CNN, Alex net, neuro-fuzzy classifier.

show abstract

Section: Contextual Clustering With Region Growingmentioning

confidence: 99%

Section: Contextual Clustering With Region Growingmentioning

confidence: 99%