Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/279800
Title: | Brain tumor detection and segmentation using optimized neural network and watershed algorithm |
Researcher: | Anand J Dhas |
Guide(s): | Vinsley S S |
Keywords: | Engineering and Technology,Engineering,Engineering Multidisciplinary Brain Tumor Watershed Algorithm Optimized Neural Network Neural Network |
University: | Anna University |
Completed Date: | 2018 |
Abstract: | Momentarily, identification and treatment of brain tumors is regarding radiological appearance, clinical symptoms, and frequent newlinehistopathology. Magnetic Resonance Imaging (MRI) has been a salient newlinenoninvasive tool to the anatomical assay of tumors in the brain. Anyhow, enormous diagnostic questions, like the grade and type of the tumor, are complicated for addressing utilizing MRI. In contemporary years brain tumor newlinerevelation utilizing MRI images has been a powerful clinical research field. newlineMRI is an effective tool to visualize internal structure within a body in a newlinesecured way. It contains the capacity for recording signals which can newlinedistinguish betwixt divergent soft tissues (like gray matter and also white newlinematter). A Brain tumor has been very pernicious disease that causes deaths of newlineseveral individuals. Moreover, the detection and also stratification system newlineshould be available thence it might be diagnosed at earlier stages. MRI newlinebecomes a precious tool for clinical assay in contemporary days and it directs newlineits salient role in applications of revelation of brain tumor. MRI contains the newlinebenefit which doesn t generate any tissue damage with its radiation .It newlineproffers precious information as per the tissue. Therefore, the intended work newlineemployed MRI images for sensing the brain tumor. The intended brain tumor newlinerevelation approach includes four sections, namely i) Initial pre-processing newlinesection, ii) Segmentation section, iii) Feature extraction section and iv) newlineClassification section. At the outset, the input image fetched from the MRI newlinedatabase will be employed to skull stripping to remove the unneeded region from the image. Skull stripping methodologies make the image appropriate for additional processing. After that, the skull stripped image experiences newlineapportionment through proficient watershed apportionment algorithm newline newline |
Pagination: | xx, 169p. |
URI: | http://hdl.handle.net/10603/279800 |
Appears in Departments: | Faculty of Information and Communication Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title.pdf | Attached File | 172.62 kB | Adobe PDF | View/Open |
02_certificates.pdf | 3.14 MB | Adobe PDF | View/Open | |
03_abstract.pdf | 7.62 kB | Adobe PDF | View/Open | |
04_acknowledgement.pdf | 35.56 kB | Adobe PDF | View/Open | |
05_contents.pdf | 24.99 kB | Adobe PDF | View/Open | |
06_chapter1.pdf | 528.68 kB | Adobe PDF | View/Open | |
07_chapter2.pdf | 214.71 kB | Adobe PDF | View/Open | |
08_chapter3.pdf | 315.05 kB | Adobe PDF | View/Open | |
09_chapter4.pdf | 769.41 kB | Adobe PDF | View/Open | |
10_chapter5.pdf | 703.84 kB | Adobe PDF | View/Open | |
11_conclusion.pdf | 145.84 kB | Adobe PDF | View/Open | |
12_references.pdf | 181.91 kB | Adobe PDF | View/Open | |
13_publications.pdf | 221.35 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: