2012
DOI: 10.1016/j.proeng.2012.06.357
|View full text |Cite
|
Sign up to set email alerts
|

Lung Nodule Segmentation through Unsupervised Clustering Models

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
13
0

Year Published

2016
2016
2024
2024

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 16 publications
(13 citation statements)
references
References 17 publications
0
13
0
Order By: Relevance
“…Lee et al (23) and Zheng and Lei (24) are interesting reviews of hand-designed methods for lung nodule segmentation featuring thresholding, region growing, watershed, edge detection and active contours. Other engineered approaches include clustering (25), graph-based methods (26), fractal analysis (27), convexity models (28), vector quantisation (29) and a variety of ad hoc solutions as well as combinations of the above methods (30)(31)(32)(33)(34). Deep learning approaches differ significantly from the conventional ones in that they employ pre-defined architectures [convolutional neural networks (CNN)] which contain a number of parameters the values of which need to be determined by training (35).…”
Section: Original Articlementioning
confidence: 99%
“…Lee et al (23) and Zheng and Lei (24) are interesting reviews of hand-designed methods for lung nodule segmentation featuring thresholding, region growing, watershed, edge detection and active contours. Other engineered approaches include clustering (25), graph-based methods (26), fractal analysis (27), convexity models (28), vector quantisation (29) and a variety of ad hoc solutions as well as combinations of the above methods (30)(31)(32)(33)(34). Deep learning approaches differ significantly from the conventional ones in that they employ pre-defined architectures [convolutional neural networks (CNN)] which contain a number of parameters the values of which need to be determined by training (35).…”
Section: Original Articlementioning
confidence: 99%
“…Vaidhya et al [27] presented a brain tumor segmentation method with stacked denoising autoencoder evaluated on multi-sequence MRI images. In a work by Sivakumar et al [28], the segmentation of lung nodules is performed with unsupervised clustering methods. In another study, Kumar et al [7] used features from autoencoder for lung nodule classification.…”
Section: Related Workmentioning
confidence: 99%
“…Many different works have been done and reported in literature previously to detect and classify the lung tumor from CT image using various types of algorithms [3][4][5][6][7][8][9][10][11][12][13][14]. Lung tumor is often segmented manually which is user and experience dependent, subjective, and may lead to erroneous diagnosis.…”
Section: Introductionmentioning
confidence: 99%
“…K-means clustering [11] is the simplest type of hard clustering algorithm but it is susceptible to noise and so without proper pre-processing method cannot segment the targeted regions accurately. Fuzzy c-means (FCM) [12] is better than other hard clustering algorithms because it has more ambiguity tolerance and preserves more original picture data. However, it fails to properly segment images with complicated texture and background because it only acknowledges gray level intensity but does not consider the spatial information.…”
Section: Introductionmentioning
confidence: 99%