3. 3
OBJECTIVE
To detect the size and location of brain tumors and
edemas from the Magnetic Resonance Images.
4. 4
INTRODUCTION
Brain tumor is an abnormal mass of tissue in which
cells grow and multiply uncontrollably seemingly
unchecked by the mechanisms that control normal
cells.
This change detection process uses a novel score
function based on Bhattacharya coefficient computed
with gray level intensity histograms.
The score function admits a very fast search to
locate the bounding box.
5. 5
METHODOLOGY
MRI IMAGE AS INPUT
HPF&MEDIAN FILTERS
SEGMENTATION OF IMAGE
MORPHOLOGICAL
OPERATION
TUMOR REGION DETECTED
ALGORITHM:
6. 6
D
Locating a Bounding Box:
1.Axis of symmetry on an axial MR slice is found which divides
brain in two halves left (I) and right (R).
2. One half serves as test Image and the other half supplies as the
reference image.
Image I Reference Image R
7. 7
3. Novel score function is used which identify the region of
change with two searches – one along the vertical direction and
other along the horizontal direction.
4. Novel score function uses Bhattacharya coefficient to
detects a rectangle D which represents the region of interest
between images I and R
8. 8
RESULTS
This method has been tested on 12 brain MRI images.
MRI image is taken as input image.
15. EDEMA REGION
• Size of the edema region in pixels displayed
in command window
15
16. 16
ADVANTAGES
1. Uses region-based left-right symmetry, rather than point-wise
symmetry
2. Uses single MR image
3. No training data required
4. No image registration needed
17. 17
CONCLUSION
•The current method uses a computer aided system for brain MR
image segmentation for detection of tumour location using
bounding box symmetry.
•The resulting method is very fast, robust and reliable for indexing
tumour or edema images for both archival and retrieval purposes
and it can use as a vehicle for further clinical investigations.
18. 18
FUTURE SCOPE
•In future, this technique can be developed to classify the
tumours based on feature extraction.
•This technique can be applied for ovarian, breast, lung, skin
tumours.
•Instead of rectangular boxes, can work with general boundaries:
level set based framework.