MRI Based Acoustic Neuroma Image Segmentation System
碩士 === 國立中興大學 === 資訊管理學系所 === 99 === This research proposes a MRI based acoustic neuroma image segmentation system. Acoustic neuroma, also known as vestibular schwannoma, is one kind of intracranial tumor. Most commonly, acoustic neuroma arises in a wedge shaped area bounded by the petrous bone, the...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2011
|
Online Access: | http://ndltd.ncl.edu.tw/handle/82435459192491022005 |
id |
ndltd-TW-099NCHU5396012 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-099NCHU53960122017-10-29T04:34:12Z http://ndltd.ncl.edu.tw/handle/82435459192491022005 MRI Based Acoustic Neuroma Image Segmentation System 以MRI為基礎之聽神經瘤切割系統 Mei-Lin Lin 林玫霖 碩士 國立中興大學 資訊管理學系所 99 This research proposes a MRI based acoustic neuroma image segmentation system. Acoustic neuroma, also known as vestibular schwannoma, is one kind of intracranial tumor. Most commonly, acoustic neuroma arises in a wedge shaped area bounded by the petrous bone, the pons and the cerebellum. Acoustic neuroma results from abnormal hyperplasia of Schwann cells of the inferior vestibular nerve. Generally, acoustic neuroma is often a benign tumor; however, it still has potential probability to become a malignant tumor that usually grows faster and tends to spread to other organs which may seriously harm human bodies or even cause death. Acoustic neuroma MR images which are scanned by the doctor are used in this research to detect the location of tumors. The involvement of the user is needed in this research. A seed point is assigned by the user, and edge based segmentation methods such as gradient calculation, edge enhancement, and noise reduction are used to illustrate edge of the acoustic neuroma in MRI. Besides, a region growing method is used to get the intensity feature of the acoustic neuroma. The combination of edge based segmentation methods and the region growing method provides a good result in acoustic neuroma segmentation. The goal of this research is to solve great amount of waste in medical resource and time consuming in traditional acoustic neuroma detection. ACM and LSM are used to investigate the performance of the proposed method. In order to quantitate segmentation results, four commonly used segmentation error measures (ME, RAE, MHD, and RDE) are used in this research. The results show that the proposed method is better than other two methods with regards to segmentation accuracy. 蔡孟勳 2011 學位論文 ; thesis 61 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中興大學 === 資訊管理學系所 === 99 === This research proposes a MRI based acoustic neuroma image segmentation system. Acoustic neuroma, also known as vestibular schwannoma, is one kind of intracranial tumor. Most commonly, acoustic neuroma arises in a wedge shaped area bounded by the petrous bone, the pons and the cerebellum. Acoustic neuroma results from abnormal hyperplasia of Schwann cells of the inferior vestibular nerve. Generally, acoustic neuroma is often a benign tumor; however, it still has potential probability to become a malignant tumor that usually grows faster and tends to spread to other organs which may seriously harm human bodies or even cause death. Acoustic neuroma MR images which are scanned by the doctor are used in this research to detect the location of tumors. The involvement of the user is needed in this research. A seed point is assigned by the user, and edge based segmentation methods such as gradient calculation, edge enhancement, and noise reduction are used to illustrate edge of the acoustic neuroma in MRI. Besides, a region growing method is used to get the intensity feature of the acoustic neuroma. The combination of edge based segmentation methods and the region growing method provides a good result in acoustic neuroma segmentation. The goal of this research is to solve great amount of waste in medical resource and time consuming in traditional acoustic neuroma detection. ACM and LSM are used to investigate the performance of the proposed method. In order to quantitate segmentation results, four commonly used segmentation error measures (ME, RAE, MHD, and RDE) are used in this research. The results show that the proposed method is better than other two methods with regards to segmentation accuracy.
|
author2 |
蔡孟勳 |
author_facet |
蔡孟勳 Mei-Lin Lin 林玫霖 |
author |
Mei-Lin Lin 林玫霖 |
spellingShingle |
Mei-Lin Lin 林玫霖 MRI Based Acoustic Neuroma Image Segmentation System |
author_sort |
Mei-Lin Lin |
title |
MRI Based Acoustic Neuroma Image Segmentation System |
title_short |
MRI Based Acoustic Neuroma Image Segmentation System |
title_full |
MRI Based Acoustic Neuroma Image Segmentation System |
title_fullStr |
MRI Based Acoustic Neuroma Image Segmentation System |
title_full_unstemmed |
MRI Based Acoustic Neuroma Image Segmentation System |
title_sort |
mri based acoustic neuroma image segmentation system |
publishDate |
2011 |
url |
http://ndltd.ncl.edu.tw/handle/82435459192491022005 |
work_keys_str_mv |
AT meilinlin mribasedacousticneuromaimagesegmentationsystem AT línméilín mribasedacousticneuromaimagesegmentationsystem AT meilinlin yǐmriwèijīchǔzhītīngshénjīngliúqiègēxìtǒng AT línméilín yǐmriwèijīchǔzhītīngshénjīngliúqiègēxìtǒng |
_version_ |
1718557155453304832 |