Author : Aafreen Nawresh. A 1
Date of Publication :30th March 2018
Abstract: Image processing techniques help in clearly identifying, segmenting and bringing out the possible outcome in the field of medical diagnosis. Haemorrhage in the brain prevailing due to mental stress and trauma is the most important cause of illness and death. Identifying the injured region from the normal-unaffected part of the brain has to be done such that there are no false predictions at the time of emergency situations. Segmentation is an approach to extract the features of haemorrhage from brain MRI dataset. Image Processing techniques; initially pre-processing steps, morphological operations, and segmentation operations are being deployed to highlight the haemorrhage area. In this paper, in Pre-processing; median filter is used to preserve the edges, morphological operations such as erosion-dilation removes and adds pixels to the boundaries of objects in the image, segmentation technique like Otsu thresholding looks onto the region or area inside the segment that has to be brought out and Watershed Segmentation helps in marking foreground and background location of object in image. This concludes that segmentation of haemorrhage in the brain can be done distinctly. Accuracy rate in segmentation is compared to get the best suitable segmentation algorithm
Reference :
-
- Hu, Qingmao, et al. "Segmentation of brain from computed tomography head images." Engineering in Medicine and Biology Society, 2005. IEEE-EMBS 2005. 27th Annual International Conference of the. IEEE, 2006.
- Liao, Chun-Chih, et al. "A multiresolution binary level set method and its application to intracranial hematoma segmentation." Computerized Medical Imaging and Graphics33.6 (2009): 423-430.
- Bardera, Anton, et al. "Semi-automated method for brain hematoma and edema quantification using computed tomography." Computerized medical imaging and graphics33.4 (2009): 304-311.
- Amoda, Niket, and Ramesh K. Kulkarni. "Image segmentation and detection using watershed transform and region based image retrieval." Int. J. Emerg. Trends & Techno. Comp. Sci 2 (2013): 89-94.
- Al-Ayyoub, Mahmoud, et al. "Automatic detection and classification of brain hemorrhages." WSEAS transactions on computers 12.10 (2013): 395-405.
- Rajini, N. Hema, and R. Bhavani. "Computer aided detection of ischemic stroke using segmentation and texture features." Measurement 46.6 (2013): 1865-1874.
- Seal, Arindrajit, Arunava Das, and Prasad Sen. "Watershed: An Image Segmentation Approach." International Journal of Computer Science and Information Technologies (IJCSIT) 6 (2015): 2295- 2297.
- Vijay, Vasupradha, A. R. Kavitha, and S. Roselene Rebecca. "Automated Brain Tumor Segmentation and Detection in MRI Using Enhanced Darwinian Particle Swarm Optimization (EDPSO)." Procedia Computer Science 92 (2016): 475-480.