A wavelet frames + K-means based automatic method for lung area segmentation in multiple slices of CT scan

Imran Fareed Nizami; Saad Ul Hasan; Ibrahim Tariq Javed

doi:10.1109/INMIC.2014.7097345

A wavelet frames + K-means based automatic method for lung area segmentation in multiple slices of CT scan

Imran Fareed Nizami, Saad Ul Hasan, Ibrahim Tariq Javed

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

7 Citations (Scopus)

Abstract

Computer assisted detection of lung nodules offers a more accurate method of nodule detection which leads to reliable diagnosis of lung cancer. Lung segmentation is a first step in the process of automatic detection of nodules. In this paper, we propose a wavelet packet frames based approach for effective lung segmentation. The proposed algorithm selects the optimal wavelet representation that is a collection of wavelet packet frames. The frames are subsequently used for clustering of coefficients using k-means clustering, which leads to the segmented lung region. The algorithm is tested on the one publicly available dataset containing 350 images and CT scan dataset of 5 local patients containing a total of 71 images. Accurate segmentation of lung is acquired with average difference in pixels from the ground truth being as low as 1.34±0.451. Furthermore, the proposed technique is fully automated and is capable of segmenting lung in multiple slices with no manual intervention or change in parameters.

Original language	English
Title of host publication	17th IEEE INMIC 2014, IEEE International Multi Topic Conference
Subtitle of host publication	Collaborative and Sustainable Development of Technologies - Proceedings
Editors	Haroon Rasheed, Farah Lakhani, Mukesh Kumar Maheshwari
Place of Publication	New Jersey, USA
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	245-248
Number of pages	4
ISBN (Electronic)	9781479957552
ISBN (Print)	9781479957545
DOIs	https://doi.org/10.1109/INMIC.2014.7097345
Publication status	Published - 28 Apr 2015
Externally published	Yes
Event	17th IEEE International Multi Topic Conference, IEEE INMIC 2014 - Karachi, Pakistan Duration: 8 Dec 2014 → 10 Dec 2014

Other

Other	17th IEEE International Multi Topic Conference, IEEE INMIC 2014
Country/Territory	Pakistan
City	Karachi
Period	8/12/14 → 10/12/14

Access to Document

10.1109/INMIC.2014.7097345

Cite this

Nizami, I. F., Ul Hasan, S., & Javed, I. T. (2015). A wavelet frames + K-means based automatic method for lung area segmentation in multiple slices of CT scan. In H. Rasheed, F. Lakhani, & M. K. Maheshwari (Eds.), 17th IEEE INMIC 2014, IEEE International Multi Topic Conference: Collaborative and Sustainable Development of Technologies - Proceedings (pp. 245-248). [7097345] Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/INMIC.2014.7097345

Nizami, Imran Fareed ; Ul Hasan, Saad ; Javed, Ibrahim Tariq. / A wavelet frames + K-means based automatic method for lung area segmentation in multiple slices of CT scan. 17th IEEE INMIC 2014, IEEE International Multi Topic Conference: Collaborative and Sustainable Development of Technologies - Proceedings. editor / Haroon Rasheed ; Farah Lakhani ; Mukesh Kumar Maheshwari. New Jersey, USA : Institute of Electrical and Electronics Engineers (IEEE), 2015. pp. 245-248

@inproceedings{4ff6969acfd4428aa8cd5270f8b825f5,

title = "A wavelet frames + K-means based automatic method for lung area segmentation in multiple slices of CT scan",

abstract = "Computer assisted detection of lung nodules offers a more accurate method of nodule detection which leads to reliable diagnosis of lung cancer. Lung segmentation is a first step in the process of automatic detection of nodules. In this paper, we propose a wavelet packet frames based approach for effective lung segmentation. The proposed algorithm selects the optimal wavelet representation that is a collection of wavelet packet frames. The frames are subsequently used for clustering of coefficients using k-means clustering, which leads to the segmented lung region. The algorithm is tested on the one publicly available dataset containing 350 images and CT scan dataset of 5 local patients containing a total of 71 images. Accurate segmentation of lung is acquired with average difference in pixels from the ground truth being as low as 1.34±0.451. Furthermore, the proposed technique is fully automated and is capable of segmenting lung in multiple slices with no manual intervention or change in parameters.",

author = "Nizami, {Imran Fareed} and {Ul Hasan}, Saad and Javed, {Ibrahim Tariq}",

year = "2015",

month = apr,

day = "28",

doi = "10.1109/INMIC.2014.7097345",

language = "English",

isbn = "9781479957545",

pages = "245--248",

editor = "Haroon Rasheed and Farah Lakhani and Maheshwari, {Mukesh Kumar}",

booktitle = "17th IEEE INMIC 2014, IEEE International Multi Topic Conference",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "17th IEEE International Multi Topic Conference, IEEE INMIC 2014 ; Conference date: 08-12-2014 Through 10-12-2014",

}

Nizami, IF, Ul Hasan, S & Javed, IT 2015, A wavelet frames + K-means based automatic method for lung area segmentation in multiple slices of CT scan. in H Rasheed, F Lakhani & MK Maheshwari (eds), 17th IEEE INMIC 2014, IEEE International Multi Topic Conference: Collaborative and Sustainable Development of Technologies - Proceedings., 7097345, Institute of Electrical and Electronics Engineers (IEEE), New Jersey, USA, pp. 245-248, 17th IEEE International Multi Topic Conference, IEEE INMIC 2014, Karachi, Pakistan, 8/12/14. https://doi.org/10.1109/INMIC.2014.7097345

A wavelet frames + K-means based automatic method for lung area segmentation in multiple slices of CT scan. / Nizami, Imran Fareed; Ul Hasan, Saad; Javed, Ibrahim Tariq.
17th IEEE INMIC 2014, IEEE International Multi Topic Conference: Collaborative and Sustainable Development of Technologies - Proceedings. ed. / Haroon Rasheed; Farah Lakhani; Mukesh Kumar Maheshwari. New Jersey, USA: Institute of Electrical and Electronics Engineers (IEEE), 2015. p. 245-248 7097345.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - A wavelet frames + K-means based automatic method for lung area segmentation in multiple slices of CT scan

AU - Nizami, Imran Fareed

AU - Ul Hasan, Saad

AU - Javed, Ibrahim Tariq

PY - 2015/4/28

Y1 - 2015/4/28

N2 - Computer assisted detection of lung nodules offers a more accurate method of nodule detection which leads to reliable diagnosis of lung cancer. Lung segmentation is a first step in the process of automatic detection of nodules. In this paper, we propose a wavelet packet frames based approach for effective lung segmentation. The proposed algorithm selects the optimal wavelet representation that is a collection of wavelet packet frames. The frames are subsequently used for clustering of coefficients using k-means clustering, which leads to the segmented lung region. The algorithm is tested on the one publicly available dataset containing 350 images and CT scan dataset of 5 local patients containing a total of 71 images. Accurate segmentation of lung is acquired with average difference in pixels from the ground truth being as low as 1.34±0.451. Furthermore, the proposed technique is fully automated and is capable of segmenting lung in multiple slices with no manual intervention or change in parameters.

AB - Computer assisted detection of lung nodules offers a more accurate method of nodule detection which leads to reliable diagnosis of lung cancer. Lung segmentation is a first step in the process of automatic detection of nodules. In this paper, we propose a wavelet packet frames based approach for effective lung segmentation. The proposed algorithm selects the optimal wavelet representation that is a collection of wavelet packet frames. The frames are subsequently used for clustering of coefficients using k-means clustering, which leads to the segmented lung region. The algorithm is tested on the one publicly available dataset containing 350 images and CT scan dataset of 5 local patients containing a total of 71 images. Accurate segmentation of lung is acquired with average difference in pixels from the ground truth being as low as 1.34±0.451. Furthermore, the proposed technique is fully automated and is capable of segmenting lung in multiple slices with no manual intervention or change in parameters.

UR - http://www.scopus.com/inward/record.url?scp=84937250217&partnerID=8YFLogxK

U2 - 10.1109/INMIC.2014.7097345

DO - 10.1109/INMIC.2014.7097345

M3 - Conference proceeding contribution

AN - SCOPUS:84937250217

SN - 9781479957545

SP - 245

EP - 248

BT - 17th IEEE INMIC 2014, IEEE International Multi Topic Conference

A2 - Rasheed, Haroon

A2 - Lakhani, Farah

A2 - Maheshwari, Mukesh Kumar

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - New Jersey, USA

T2 - 17th IEEE International Multi Topic Conference, IEEE INMIC 2014

Y2 - 8 December 2014 through 10 December 2014

ER -

Nizami IF, Ul Hasan S, Javed IT. A wavelet frames + K-means based automatic method for lung area segmentation in multiple slices of CT scan. In Rasheed H, Lakhani F, Maheshwari MK, editors, 17th IEEE INMIC 2014, IEEE International Multi Topic Conference: Collaborative and Sustainable Development of Technologies - Proceedings. New Jersey, USA: Institute of Electrical and Electronics Engineers (IEEE). 2015. p. 245-248. 7097345 doi: 10.1109/INMIC.2014.7097345

A wavelet frames + K-means based automatic method for lung area segmentation in multiple slices of CT scan

Abstract

Other

Access to Document

Other files and links

Fingerprint

Cite this