Texture Based Segmentation of Breast Tumors in Ultrasound Images
碩士 === 元智大學 === 資訊管理學系 === 97 === In this study, we propose an automatic texture based segmentation method for breast tumors in ultrasound images. Image processing techniques are used to segment the contour of breast tumors to assist doctors for further differential diagnosis. The correlation coeffi...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2009
|
Online Access: | http://ndltd.ncl.edu.tw/handle/82421045063308231500 |
id |
ndltd-TW-097YZU05396062 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-097YZU053960622016-05-04T04:17:09Z http://ndltd.ncl.edu.tw/handle/82421045063308231500 Texture Based Segmentation of Breast Tumors in Ultrasound Images 以紋理特徵為基礎之自動化超音波乳房腫瘤影像切割之研究 Tzung-Shin Liu 呂宗鑫 碩士 元智大學 資訊管理學系 97 In this study, we propose an automatic texture based segmentation method for breast tumors in ultrasound images. Image processing techniques are used to segment the contour of breast tumors to assist doctors for further differential diagnosis. The correlation coefficients were selected as the main texture feature to represent the characteristics breast tumor. The modified colony algorithm with optimum searching stratagem was then used to find the relationship among pixels. The inverse mapping and region classification were used to classify the position of pixels. Finally, the morphologic operations are used to modify the contour of the tumor. Experimental results show that the overall accepted rate is up to 94 % both on benign and malignant tumors of the ultrasound images. The proposed method can achieve the purpose of enhancing the accuracy of automatic segmentation effectively to assist further diagnosis. Wen-Jia Kuo 郭文嘉 2009 學位論文 ; thesis 61 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 元智大學 === 資訊管理學系 === 97 === In this study, we propose an automatic texture based segmentation method for breast tumors in ultrasound images. Image processing techniques are used to segment the contour of breast tumors to assist doctors for further differential diagnosis. The correlation coefficients were selected as the main texture feature to represent the characteristics breast tumor. The modified colony algorithm with optimum searching stratagem was then used to find the relationship among pixels. The inverse mapping and region classification were used to classify the position of pixels. Finally, the morphologic operations are used to modify the contour of the tumor. Experimental results show that the overall accepted rate is up to 94 % both on benign and malignant tumors of the ultrasound images. The proposed method can achieve the purpose of enhancing the accuracy of automatic segmentation effectively to assist further diagnosis.
|
author2 |
Wen-Jia Kuo |
author_facet |
Wen-Jia Kuo Tzung-Shin Liu 呂宗鑫 |
author |
Tzung-Shin Liu 呂宗鑫 |
spellingShingle |
Tzung-Shin Liu 呂宗鑫 Texture Based Segmentation of Breast Tumors in Ultrasound Images |
author_sort |
Tzung-Shin Liu |
title |
Texture Based Segmentation of Breast Tumors in Ultrasound Images |
title_short |
Texture Based Segmentation of Breast Tumors in Ultrasound Images |
title_full |
Texture Based Segmentation of Breast Tumors in Ultrasound Images |
title_fullStr |
Texture Based Segmentation of Breast Tumors in Ultrasound Images |
title_full_unstemmed |
Texture Based Segmentation of Breast Tumors in Ultrasound Images |
title_sort |
texture based segmentation of breast tumors in ultrasound images |
publishDate |
2009 |
url |
http://ndltd.ncl.edu.tw/handle/82421045063308231500 |
work_keys_str_mv |
AT tzungshinliu texturebasedsegmentationofbreasttumorsinultrasoundimages AT lǚzōngxīn texturebasedsegmentationofbreasttumorsinultrasoundimages AT tzungshinliu yǐwénlǐtèzhēngwèijīchǔzhīzìdònghuàchāoyīnbōrǔfángzhǒngliúyǐngxiàngqiègēzhīyánjiū AT lǚzōngxīn yǐwénlǐtèzhēngwèijīchǔzhīzìdònghuàchāoyīnbōrǔfángzhǒngliúyǐngxiàngqiègēzhīyánjiū |
_version_ |
1718256572628467712 |