北京生物醫(yī)學(xué)工程

CT圖像肺結(jié)節(jié)自動(dòng)檢測(cè)

Automated Detection of Lung Nodules Based on CT Images

作者：李慶玲劉杰

單位：北京交通大學(xué)（北京100044）

關(guān)鍵詞：肺結(jié)節(jié)；肺實(shí)質(zhì)分割；肺結(jié)節(jié)檢測(cè)；分類(lèi)

分類(lèi)號(hào)：

出版年·卷·期（頁(yè)碼）：2010·29·6（599-602）

摘要：

肺癌是對(duì)人類(lèi)生命健康危害最大的惡性腫瘤之一。計(jì)算機(jī)輔助診斷系統(tǒng)對(duì)肺部CT圖像進(jìn)行自動(dòng)分析后，可提示醫(yī)生可疑肺結(jié)節(jié)，從而克服醫(yī)生在診斷中的一些主觀(guān)因素，為此本文提出了一種基于胸部CT圖像的可疑肺結(jié)節(jié)自動(dòng)檢測(cè)算法。首先，根據(jù)胸部組織的特殊結(jié)構(gòu)，利用一種新的分割算法提取出肺實(shí)質(zhì)部分；在此基礎(chǔ)上提取出灰度與結(jié)節(jié)相近的感興趣區(qū)域，包括結(jié)節(jié)、肺血管、支氣管；然后，以已標(biāo)記的結(jié)節(jié)數(shù)據(jù)作為樣本集，計(jì)算結(jié)節(jié)的面積、灰度均值、灰度方差、圓形度、形狀矩、體積、球形度等特征值，利用最近鄰法建立分類(lèi)器判別函數(shù)；最后，計(jì)算測(cè)試集感興趣區(qū)域的上述特征，對(duì)其進(jìn)行判別、分類(lèi)，并標(biāo)記出結(jié)節(jié)。試驗(yàn)結(jié)果表明，該算法綜合考慮了肺結(jié)節(jié)特征,具有較高的準(zhǔn)確度。

Lung cancer is one of the most malignant tumour in human life. The computer aided diagnosis system can automatically analyze the lung image and prompt lung nodule to doctors, thereby overcoming some subjective factors from doctors in diagnosis. This paper presents an automatic detection method for lung nodules based on chest CT images. First, according to the special chest structure, a new segmentation algorithm was proposed to extract the lung parenchyma. The regions of interest (ROI) where gray was likely as nodule, such as nodules, pulmonary vessels, airways, were extracted. Second, taking marked nodules as sample set, the area, average gray, variance, shape matrix, volume, spherical degree were set as discriminating features, the discrimination of classifier was devised based on the nearest neighbor algorithm. Last, such features of ROI in testing set were calculated and classified. Experimental result showed that the algorithm considered the characters of lung nodule generally and achieve high accuracy.

參考文獻(xiàn)：

［1］Sluimer I,Schilham A, Mathias P,et al.Computer analysis of computed tomography scans of the lung［J］.A Survey, IEEE Transactions on Medical Imaging,2006，25（4）：385-405.
［2］Al-Kadi OS, Watson D. Texture analysis of aggressive and nonaggressive lung tumor CE CT images［J］. IEEE Transactions on Biomedical Engineering,2008,55(7):1822-1830.
［3］Yim Yeny,Hong Helen.Correction of segmented lung boundary for inclusion of pleural nodules and pulmonary vessels in chest CT images［J］.Computers in Biology and Medicine,2007，38：845-857.
［4］Dehmeshki J,Ye XJ,Lin XY,et al.Automated detection of lung nodules in CT images using shape-based genetic algorithm［J］.Computerized Medical Imaging and Graphics ,2007,31:408-417.
［5］Mastumoto S,Kundel HL,Gee JC,Gefter WB,et al.Pulmonary nodule detection in CT images with quantized convergence index fiter［J］.Medical Image analysis,2006, 10:343-352.
［6］Retico A,Delogu P,Fantacci ME,et al.Lung nodule detection in low-dose and thin-slice computed tomography［J］.Computers in Biology and Medicine,2008,38:525-534.
［7］Brown Matthew.Computer-aided diagnosis in thoracic CT［R］.Department of Radiology David Geffen School of Medicine at UCLA.
［8］Schilham Arnold MR. A computer-aided diagnosis system for detection of lung nodules in chest radiographs with an evaluation on a public database［J］. Medical Image Analysis,2006,10:247–258.
［9］Osman Onur,Ozekes Serhat,Ucan ON.Lung nodule diagnosis using 3D template matching［J］.Computers in Biology and Medicine ,2007,37:1167-1172.
［10］薛以鋒，鮑旭東，馬漢林，等.基于CT圖像的肺結(jié)節(jié)計(jì)算機(jī)輔助診斷系統(tǒng)［J］.中國(guó)醫(yī)學(xué)物理學(xué)雜志，2006,23(2):1075-1079.
［11］陳卉，徐巖，馬斌榮.針對(duì)肺結(jié)節(jié)檢測(cè)的肺實(shí)質(zhì)CT圖像分割［J］.中國(guó)醫(yī)學(xué)物理學(xué)雜志，2008,25(6):883-886.

［12］郭圣文，陳堅(jiān)，曾慶思.胸部CT中肺實(shí)質(zhì)的自動(dòng)分割與計(jì)算機(jī)輔助診斷［J］.華南理工大學(xué)學(xué)報(bào)：自然科學(xué)版，2008，36（1）：679-682.
［13］高園園，呂慶文，郭宏，等.一種新的肺結(jié)節(jié)檢測(cè)算法［J］.計(jì)算機(jī)工程與應(yīng)用，2007,26(43):198-199.
［14］吳龍海，周荷琴，李傳富.基于高分辨率CT圖像的肺結(jié)節(jié)檢測(cè)［J］.中國(guó)醫(yī)療器械雜志，2008,32(3):175-178.
［15］王德杭，汪家旺，于立燕，等.肺結(jié)節(jié)檢測(cè)算法研究［J］.上海生物醫(yī)學(xué)雜志，2005,26（1）:3-7.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請(qǐng)登錄！點(diǎn)此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频