2002
DOI: 10.1118/1.1515762
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: We are developing a computer-aided diagnosis (CAD) system for lung nodule detection on thoracic helical computed tomography (CT) images. In the first stage of this CAD system, lung regions are identified by a k-means clustering technique. Each lung slice is classified as belonging to the upper, middle, or the lower part of the lung volume. Within each lung region, structures are segmented again using weighted k-means clustering. These structures may include true lung nodules and normal structures consisting ma… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
158
0
4

Year Published

2005
2005
2019
2019

Publication Types

Select...
5
2
1

Relationship

1
7

Authors

Journals

citations
Cited by 276 publications
(162 citation statements)
references
References 25 publications
0
158
0
4
Order By: Relevance
“…Soltaninejad, Keshani and Tajeripour [28] K-Nearest Neighbors (k-NN) Suiyuan and Junfeng [29] Invariant moments Namin et al [32] Fuzzy k-NN classifier Matsumoto et al [35] and Gurcan et al [97] Rule based Ozekes and Osman [37] and Camarlinghi et al [98] Feed forward neural networks (FFNN) Ozekes and Osman [37] Naive Bayesian (NB) and Logistic regression (LR) Ge et al [45], Armato III et al [91] and Gurcan et al [97] Linear discriminant analysis (LDA)…”
Section: Authorsmentioning
confidence: 99%
“…Soltaninejad, Keshani and Tajeripour [28] K-Nearest Neighbors (k-NN) Suiyuan and Junfeng [29] Invariant moments Namin et al [32] Fuzzy k-NN classifier Matsumoto et al [35] and Gurcan et al [97] Rule based Ozekes and Osman [37] and Camarlinghi et al [98] Feed forward neural networks (FFNN) Ozekes and Osman [37] Naive Bayesian (NB) and Logistic regression (LR) Ge et al [45], Armato III et al [91] and Gurcan et al [97] Linear discriminant analysis (LDA)…”
Section: Authorsmentioning
confidence: 99%
“…CAD schemes for lung nodule detection were developed first for chest radiographs [6] and then for thick-section CT images [7][8][9][10][11][12][13]. The typical performance of current CAD schemes in thick-section CT is an 80-90% sensitivity with 1-2 false positives per section, which translates into tens of false positives per CT scan.…”
Section: Introductionmentioning
confidence: 99%
“…The typical performance of current CAD schemes in thick-section CT is an 80-90% sensitivity with 1-2 false positives per section, which translates into tens of false positives per CT scan. The majority of false positives are caused by blood vessels and other normal anatomic structures [10,12]. Because of the relatively large section thickness (5-10 mm), CAD schemes for nodule detection in thick-section CT generally detect nodules on a section-by-section basis.…”
Section: Introductionmentioning
confidence: 99%
“…The drawbacks to these approaches are the difficulties in detecting lung wall nodules. Also, there are other pattern recognition techniques used in detection of lung nodules such as clustering [100][101][102][103], linear discriminate functions [104], rule-based classification [105], Hough transform [106], connected component analysis of thresholded CT slices [107,108], gray level distance transform [102], and patient-specific a priori model [109]. The FPNs are excluded at the second stage by nodule classification [82,83,106,[110][111][112].…”
Section: Detection Of Lung Nodulesmentioning
confidence: 99%
“…The task of the classifier is to determine "optimal" boundaries for separating classes (i.e., nodules or non-nodules) in the multi-dimensional feature space which is formed by the input features [113]. Featurebased classifiers include linear discriminant analysis (LDA) [114], rule-based or linear clas-sifier [38,85,86,88,90,100,103,115]; template matching [109]; nearest cluster [97,99];…”
Section: Detection Of Lung Nodulesmentioning
confidence: 99%