南昌大学学报(理科版)
南昌大學學報(理科版)
남창대학학보(이과판)
JOURNAL OF NANCHANG UNIVERSITY(NATURAL SCIENCE)
2014年
1期
31-35
,共5页
聚类%相似度函数%半监督学习%图像分割
聚類%相似度函數%半鑑督學習%圖像分割
취류%상사도함수%반감독학습%도상분할
Clustering%Similarity function%Semi-supervised learning%Image segmentation
医学图像分割是计算机视觉和图像处理领域近年来研究的热点问题之一。一种基于 k-means 聚类和半监督学习的医学图像分割新算法被提出。在 k-means 聚类模型中,相似度函数是关系到聚类效果好坏的关键因素。所使用的相似度函数通过基于 side-information 的半监督学习方法来确定;确定后的相似度函数又被运用回 k-means 聚类模型中来实现对医学图像的分割。为了检验该算法效果,脑部肿瘤患者的磁共振图像被运用在实验中。分析结果表明:该算法在本文所采用的实例中能获得优于传统算法的分割效果。
醫學圖像分割是計算機視覺和圖像處理領域近年來研究的熱點問題之一。一種基于 k-means 聚類和半鑑督學習的醫學圖像分割新算法被提齣。在 k-means 聚類模型中,相似度函數是關繫到聚類效果好壞的關鍵因素。所使用的相似度函數通過基于 side-information 的半鑑督學習方法來確定;確定後的相似度函數又被運用迴 k-means 聚類模型中來實現對醫學圖像的分割。為瞭檢驗該算法效果,腦部腫瘤患者的磁共振圖像被運用在實驗中。分析結果錶明:該算法在本文所採用的實例中能穫得優于傳統算法的分割效果。
의학도상분할시계산궤시각화도상처리영역근년래연구적열점문제지일。일충기우 k-means 취류화반감독학습적의학도상분할신산법피제출。재 k-means 취류모형중,상사도함수시관계도취류효과호배적관건인소。소사용적상사도함수통과기우 side-information 적반감독학습방법래학정;학정후적상사도함수우피운용회 k-means 취류모형중래실현대의학도상적분할。위료검험해산법효과,뇌부종류환자적자공진도상피운용재실험중。분석결과표명:해산법재본문소채용적실례중능획득우우전통산법적분할효과。
Medical Image Segmentation is one of the most popular applications in contemporary computer vi-sion and image processing fields.A novel algorithm based on k-means clustering and semi-supervised learn-ing was presented in this study.The similarity function is one of the most important factors in clustering algorithms.It was determined via a semi-supervised learning process based on side-information in k-means method in our study.The learned similarity function was thereafter incorporated in the clustering model to differentiate tumor pixels from non-tumor pixels.In order to evaluate the presented algorithm,experiments incorporating MRI from patients with brain tumor were conducted as well.The superiority of the intro-duced algorithm over several existing ones was demonstrated therein.