ReviLung Abnormal Tissue Extraction from CAT Image Using HBBAS Methodew

Lung Abnormal Tissue
Extraction from CAT Image
Using HBBAS Method
Presented by,
K.VIJILA RANI
4/13/2017Footer Text 1

 To extract the lung lesion from computed
tomography image.
OBJECTIVE

 Image processing :
- digital form
- growing research area
- integrated with the medical and biotechnology
field.
 Medical Imaging:
- visual representation of the interior of a body.
 Lung Cancer:
- dangerous disease for which still proper
treatment is not available.
- tumor grows larger than 2mm
- spreads to other parts of the body
INTRODUCTION

 Types of lung cancer:
- small cell lung cancer
- non small cell lung cancer
 Causes of lung cancer:
- cigarette smoking
- radon gas
 Lung lesion:
-abnormal tissue
Cont.…

 X-Rays
 Magnetic Resonance Imaging
 Computed Tomography
Medical Imaging Technologies

 HBBA Segmentation Approach
4/13/2017Footer Text
6
BLOCK DIAGRAM
Input
image
2D2D lung
parenchyma
segmentation
Preprocessing
Improved
toboggan
searching
Histogram
binning based
automatic
segmentation
3D lung lesion
segmentation
Lesion
contour
extraction
Lung lesion
refining
Output
segmented
image

 INPUT: Gradient Image OUTPUT : Label Image
Improved toboggan algorithm
Step 1. Calculate the gradient image.
Step 2. Scan the four neighborhoods (or eight) of each pixel
in the gradient image. As one slice is enough for the selection of the
lesion seed point.
Step 3. Mark the pixels slide to the local minimum by the same label with
the “minimum” pixel.
u
Step 4. The process is repeated until all pixels in the image are
segmented.

 Histogram-based approaches can also be quickly adapted
to occur over multiple frames, while maintaining their
single pass efficiency.
 The same approach that is taken with one frame can be
applied to multiple, and after the results are merged.
 Histogram bins means range interval of image pixel.
HISTOGRAM BINNING BASED
SEGMENTATION

 seed region growing method. This method takes a set
of seeds as input along with the image. The seeds
mark each of the objects to be segmented.
 The regions are iteratively grown by comparison of all
unallocated neighboring pixels to the regions.
 This process continues until all pixels are assigned to a
region.
3D LUNG LESION SEGMENTATION

RRRESULT

INPUT IMAGE

2D LUNG PARENCHYMA
SEGMENTATION

PREPROCESSING

TOBOGGAN SEARCH

HISTOGRAM BINNING BASED
AUTOMATIC SEGMENTATION

SEGMENTATION SINGLE SLICE
IMAGE

3D LUNG LESION SEGMENTATION

LUNG LESIONS INCLUDING SOLID
NODULES

LESION REGION OF THE CAVITY
TUMOR

Performance analysis for histogram binning vs TBGA
Segmentation

 Area of the lung lesion region estimated
 Euclidean distance between center slice and
adjacent slice is calculated.
 Less time consumption(Execution time single
lesion segmentation = 0.018688s).
Advantages

 In conclusion, the novel HBBAS can achieve
robust, efficient and accurate lung lesion
segmentation in CT images automatically.
 The new approach does not require any
training dataset.
 Unsupervised method
CONCLUSION

 [1] Jungian Song “Lung Lesion Extraction Using a Toboggan Based Growing Automatic Segmentation Approach,” IEEE
Trans Med Imaging, vol. 35, No 1,Jan. 2016.
 [2] D. M. Campos, A. Simões, I. Ramos, and A. Campilho, “Feature-Based Supervised Lung Nodule Segmentation,” no. Ci,
pp. 23–26, 2014.
 [3]A. Mansoor, U. Bagci, Z. Xu, B. Foster, K. N. Olivier, and J. M. Elinoff et al., “A generic approach to pathological lung
segmentation,” IEEE Trans Med Imaging, vol. 33, pp. 2293–2310, Dec. 2014.
 [4] B. Lassen, E. M. Van Rikxoort, M. Schmidt, S. Kerkstra, B. Van Ginneken,and J. M. Kuhnigk, “Automatic segmentation
of the pulmonary lobes from chest CT scans based on Fissures, Vessels, Bronchi,” IEEE Trans. Med. Imaging, vol. 32, no. 2,
pp. 210–222, 2013
 [5] A. a Farag, H. E. A. El Munim, J. H. Graham, and A. a Farag, “A novel approach for lung nodules segmentation in chest
CT using level sets.,” IEEE Trans. Image Process., vol. 22, no. 12, pp. 5202–5213, 2013.
 [6] S. Sun, Y. Guo, Y. Guan, and H. Ren, “Juxta-Vascular Nodule Segmentation Based on the Flowing Entropy and
Geodesic Distance Feature,” Scientia Sinica(Informationis), vol. 61, pp. 1136–1146, 2013.
 [7] Y. C. Lin, Y. P. Tsai, Y. P. Hung, and Z. C. Shih, “Comparison between immersion-based and toboggan-based
watershed image segmentation,” IEEE Trans. Image Process., vol. 15, no. 3, pp. 632–640, 2012.
 [8] M. Tan, R. Deklerck, B. Jansen, M. Bister, and J. Cornelis, “A novel computer-aided lung nodule detection system for
CT images,” Med. Phys., vol. 38, no. 10, p. 5630, 2011.
 [9] C. Li, R. Huang, Z. Ding, J. C. Gatenby, D. N. Metaxas, and J. C. Gore, “A level set method for image segmentation in
the presence of intensity inhomogeneities with application to MRI,” IEEE Trans. Image Process., vol. 20, no. 7, pp. 2007–
2016, 2011.
 [10] D. S. Paik, C. F. Beaulieu, G. D. Rubin, B. Acar, R. B. Jeffrey, J. Yee, J. Dey, and S. Napel, “Surface normal overlap: A
computer-aided detection algorithm with application to colonic polyps and lung nodules in helical CT,” IEEE Trans. Med.
Imaging, vol. 23, no. 6, pp. 661–675,2004.
References

Thank you

ReviLung Abnormal Tissue Extraction from CAT Image Using HBBAS Methodew

More Related Content

Similar to ReviLung Abnormal Tissue Extraction from CAT Image Using HBBAS Methodew (20)

Recently uploaded (20)

ReviLung Abnormal Tissue Extraction from CAT Image Using HBBAS Methodew