PATCHMATCH BASED TREE-SEED FUZZY CLUSTERING FOR ISCHEMIC STROKE LESION SEGMENTATION IN BRAIN MR IMAGES

Mr. Tushar R. Sangole; Dr. Amit K. Gaikwad; Dr. Vinod  M. Vaze

doi:10.17605/OSF.IO/BVGW3

Authors

Mr. Tushar R. Sangole Research Scholar
Dr. Amit K. Gaikwad Associate Professor, SIT Kolhapur
Dr. Vinod M. Vaze Department of Computer Science JJTU, Rajasthan, India

DOI:

https://doi.org/10.17605/OSF.IO/BVGW3

Keywords:

Patch match, Tree seed, Ischemic Stroke lesion, lesion segmentation

Abstract

Ischemic Stroke Lesion (ISL) arises when the artery of the brain gets blocked. The blood provisions nutrients and oxygen to the brain and take out carbon dioxide and other waste cells. In case an artery gets congested, the brain cells will not be able to function and will ultimately stop functioning (Khoshnam SE et al 2017). Nerve symptoms and symptoms of IS usually occur abruptly but can also be sometimes progressive in nature. Signs and symptoms vary based on the position of the occlusion and the flow (Sommer CJ 2017). Atherosclerotic stroke is generally found in elders, and arises without symptoms in 80% of the cases. IS can be initiated by a variety of ailments, like contraction of the arteries head or neck region (Jiang X et al 2018).This is usually produced by atherosclerosis, deposition of cholesterol, or generation blood clots which arise as a consequence of rapid heartbeat, heart attack, damages in heart valve, or some other underlying origins, including drug overdose, severe blood vessel injury in the neck, or abnormal blood flow (Renna R et al 2014). MRI is extensively utilized to identify cerebral ischemia.

Medical imaging procedures are used to obtain images of various regions of the human body for analyzing the condition and for further treatment. MRI is a scheme for getting comprehensive images of the interior organs, as well as the muscles of the brain &spinal cord. It is first utilized to picture body image and bodily functions (Liu J et al 2014).

Since the brain manages whole functions of the human body, the brain is considered to be one of the significant organs of the body. Several illnesses like infections, tumors, and strokes affect the brain. In addition, tumor brain may be a noncancerous or cancerous group or abnormal cell growth in the brain. Methods like MRI can be employed for detecting brain tumors. Lately, MRI scans have gained attention due to the requirement for a better evaluation of huge amounts of information (El-Dahshan et al 2014). Obtaining brain samples and automated classification of brain cells from MRI scans is important both in medicine and in experimental studies of common and diseased brain tumors. The most significant step in the fabrication of medical imaging is segmentation, which separates the matters in the image for processing.

Downloads

Download data is not yet available.

References

Abulnaga SM, Rubin J. Ischemic stroke lesion segmentation in CT perfusion scans using pyramid pooling and focal loss. InInternational MICCAI Brainlesion Workshop 2018 Sep 16 (pp. 352-363). Springer, Cham.

Acharya UR, Meiburger KM, Faust O, Koh JE, Oh SL, Ciaccio EJ, Subudhi A, Jahmunah V, Sabut S. Automatic detection of ischemic stroke using higher order spectra features in brain MRI images. Cognitive systems research. 2019 Dec 1;58:134-42.

Babu MS, Vijayalakshmi V. A review on acute/sub-acute ischemic stroke lesion segmentation and registration challenges. Multimedia Tools and Applications. 2019 Jan 1;78(2):2481-506.

Babu MS, Vijayalakshmi V. An Effective Approach for Sub-acute Ischemic Stroke Lesion Segmentation by Adopting Meta-Heuristics Feature Selection Technique Along with Hybrid Naive Bayes and Sample-Weighted Random Forest Classification. Sensing and Imaging. 2019 Dec 1;20(1):7.

Bertels J, Robben D, Vandermeulen D, Suetens P. Contra-lateral information CNN for core lesion segmentation based on native CTP in acute stroke. InInternational MICCAI Brainlesion Workshop 2018 Sep 16 (pp. 263-270). Springer, Cham.

Bharathi PG, Agrawal A, Sundaram P, Sardesai S. Combination of hand-crafted and unsupervised learned features for ischemic stroke lesion detection from Magnetic Resonance Images. Biocybernetics and Biomedical Engineering. 2019 Apr 1;39(2):410-25.

Binaghi E, Omodei M, Pedoia V, Balbi S, Lattanzi D, Monti E. Automatic Segmentation of MR Brain Tumor Images using Support Vector Machine in Combination with Graph Cut. InIJCCI (NCTA) 2014 Oct 22 (pp. 152-157).

Chen W, Liu B, Peng S, Sun J, Qiao X. S3D-UNet: separable 3D U-Net for brain tumor segmentation. InInternational MICCAI Brainlesion Workshop 2018 Sep 16 (pp. 358-368). Springer, Cham.

Chen, X., & Pan, L. (2018). A survey of graph cuts/graph search based medical image segmentation. IEEE reviews in biomedical engineering, 11, 112-124.

Chin CL, Lin BJ, Wu GR, Weng TC, Yang CS, Su RC, Pan YJ. An automated early ischemic stroke detection system using CNN deep learning algorithm. In2017 IEEE 8th International Conference on Awareness Science and Technology (iCAST) 2017 Nov 8 (pp. 368-372). IEEE.

Dong H, Yang G, Liu F, Mo Y, Guo Y. Automatic brain tumor detection and segmentation using U-Net based fully convolutional networks. Inannual conference on medical image understanding and analysis 2017 Jul 11 (pp. 506-517). Springer, Cham.

El-Dahshan ES, Mohsen HM, Revett K, Salem AB. Computer-aided diagnosis of human brain tumor through MRI: A survey and a new algorithm. Expert systems with Applications. 2014 Sep 1;41(11):5526-45.

Feng X, Ye G, Cao R, Qi P, Lu J, Chen J, Wang D. Identification of Predictors for Hemorrhagic Transformation in Patients with Acute Ischemic Stroke After Endovascular Therapy Using the Decision Tree Model. Clinical Interventions in Aging. 2020;15:1611.

Gautam, A., & Raman, B. (2019). Segmentation of ischemic stroke lesion from 3d mr images using random forest. Multimedia Tools and Applications, 78(6), 6559-6579.

Griffis, J. C., Allendorfer, J. B., & Szaflarski, J. P. (2016). Voxel-based Gaussian naïve Bayes classification of ischemic stroke lesions in individual T1-weighted MRI scans. Journal of neuroscience methods, 257, 97-108.

Gupta, A., Vupputuri, A., & Ghosh, N. (2019, July). Delineation of Ischemic Core and Penumbra Volumes from MRI using MSNet Architecture. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 6730-6733). IEEE.

Huber T, Alber G, Bette S, Boeckh-Behrens T, Gempt J, Ringel F, Alberts E, Zimmer C, Bauer JS. Reliability of semi-automated segmentations in glioblastoma. Clinical neuroradiology. 2017 Jun 1;27(2):153-61.

Jiang X, Andjelkovic AV, Zhu L, Yang T, Bennett MV, Chen J, Keep RF, Shi Y. Blood-brain barrier dysfunction and recovery after ischemic stroke. Progress in neurobiology. 2018 Apr 1;163:144-71.

Kamnitsas K, Baumgartner C, Ledig C, Newcombe V, Simpson J, Kane A, Menon D, Nori A, Criminisi A, Rueckert D, Glocker B. Unsupervised domain adaptation in brain lesion segmentation with adversarial networks. InInternational conference on information processing in medical imaging 2017 Jun 25 (pp. 597-609). Springer, Cham.

Kamnitsas K, Ferrante E, Parisot S, Ledig C, Nori AV, Criminisi A, Rueckert D, Glocker B. DeepMedic for brain tumor segmentation. InInternational workshop on Brainlesion: Glioma, multiple sclerosis, stroke and traumatic brain injuries 2016 Oct 17 (pp. 138-149). Springer, Cham.