本文選題：胰腺細(xì)胞 + 細(xì)胞抹片顯微圖像分割�。� 參考：《生物醫(yī)學(xué)工程學(xué)雜志》2017年04期

【摘要】：胰腺癌的診斷非常重要,而細(xì)胞抹片顯微圖像的病理分析是其診斷的主要手段。圖像的準(zhǔn)確自動(dòng)分割和分類是病理分析的重要環(huán)節(jié),因此本文提出了一種新的胰腺細(xì)胞抹片顯微圖像自動(dòng)分割與分類算法。在分割方面,首先采用多特征Mean-shift聚類算法(MFMS)定位細(xì)胞核區(qū)域;接著采用彈性數(shù)學(xué)形態(tài)學(xué)結(jié)合角點(diǎn)檢測(cè)的去粘連模型(CSM)對(duì)粘連重疊細(xì)胞核進(jìn)行去粘連處理,實(shí)現(xiàn)了分割的準(zhǔn)確性和魯棒性。在分類方面,首先針對(duì)分割的細(xì)胞核提取了4個(gè)形狀特征和138個(gè)不同顏色空間的紋理特征;然后結(jié)合支持向量機(jī)(SVM)和鏈?zhǔn)竭z傳算法(CAGA)實(shí)現(xiàn)封裝式特征選擇;最后將優(yōu)選特征送入SVM進(jìn)行分類,完成了胰腺細(xì)胞抹片顯微圖像的分類識(shí)別。本文采用了15幅圖像一共461個(gè)細(xì)胞核進(jìn)行測(cè)試。實(shí)驗(yàn)結(jié)果顯示,本文算法可以實(shí)現(xiàn)不同類型的胰腺細(xì)胞抹片顯微圖像的自動(dòng)分割與準(zhǔn)確分類。就分割來(lái)說(shuō),本文算法可獲得較高的正確率(93.46%±7.24%);就正常和癌變細(xì)胞的分類來(lái)說(shuō),本文算法可獲得較高的分類正確率(96.55%±0.99%)、靈敏度(96.10%±3.08%)和特異度(96.80%±1.48%)。
[Abstract]:The diagnosis of pancreatic cancer is very important, and the pathological analysis of cell smear microscopic image is the main means of diagnosis. Accurate automatic segmentation and classification of images is an important part of pathological analysis. Therefore, a new automatic segmentation and classification algorithm for pancreatic cell smear microimages is proposed in this paper. In the aspect of segmentation, firstly, multi-feature Mean-shift clustering algorithm was used to locate the nuclear region, and then the adhesion removal model was used to deal with the superimposed nuclei by elastic mathematical morphology combined with corner detection. The accuracy and robustness of segmentation are realized. In classification, four shape features and 138 texture features in different color spaces are extracted from the segmented nuclei, and then the encapsulated feature selection is realized by combining support vector machine (SVM) and chain genetic algorithm (CAGA). Finally, the optimal selection features were sent into SVM for classification, and the classification and recognition of pancreatic cell smear microimages were completed. A total of 461 nuclei were tested in 15 images. The experimental results show that the proposed algorithm can realize automatic segmentation and accurate classification of different types of pancreatic cell smear microimages. As far as segmentation is concerned, the proposed algorithm can obtain a higher accuracy rate of 93.46% 鹵7.24% and a higher accuracy rate of 96.55% 鹵0.99% and a sensitivity of 96.10% 鹵3.08% and a specificity of 96.80% 鹵1.48% for the classification of normal and cancerous cells.
【作者單位】： 重慶大學(xué)通信工程學(xué)院;第三軍醫(yī)大學(xué)生物醫(yī)學(xué)工程學(xué)院;
【分類號(hào)】：R735.9;TP391.41

【相似文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 王迎迎;乳腺癌病理切片顯微圖像分割及系統(tǒng)實(shí)現(xiàn)[D];西北大學(xué);2013年

，

本文編號(hào)：1901079