發(fā)布時間：2018-01-20 04:08

  本文關鍵詞： 磨玻璃密度結節(jié) 神經網(wǎng)絡 多層感知器　出處：《臨床放射學雜志》2017年08期 　論文類型：期刊論文

【摘要】：目的利用神經網(wǎng)絡分析法構建肺磨玻璃密度結節(jié)(GGN)侵襲性的CT預測模型,探討其預測的準確性。方法回顧性分析203例經手術病理證實為肺腺癌的肺GGN的CT影像特征。采集患者基本信息,統(tǒng)計肺結節(jié)密度(純磨玻璃結節(jié)或混合磨玻璃結節(jié))、是否含有內核、大小、實性成分比例;采用評分法對空泡征、胸膜牽拉征、血管集束征三個影像特征進行量化評分,利用單因素方差分析各CT特征在不同病理分組間的差異,利用神經網(wǎng)絡法將病例隨機分為培訓組(103例)和檢驗組(100例),建立各CT特征與GGN病理之間的預測模型。結果203例肺GGN中AAH 20例,AIS 26例,MIA 74例,I-ADC 83例。四組病理類型間的結節(jié)性質、直徑、實性成分比例以及三個影像特征通過單因素方差分析均存在顯著性差異(P0.05)�；诖藬�(shù)據(jù)而使用神經網(wǎng)絡的"多層感知器"(MLP)建立預測模型。培訓組總體預測準確率為80.6%(AAH 92.9%,AIS 38.5%,MIA 91.2%,I-ADC81.0%)檢驗組預測總體準確率為72.0%(AAH 50.0%,AIS 46.2%,MIA 72.5%,I-ADC 82.9%),各自變量在模型中的重要性WTMW/WTLW(0.270,100%),影像特征評分(0.263,97.6%),WTMW(0.099,36.7%),WTLW(0.097,36.0%),胸膜牽拉征(0.085,31.5%),血管集束征(0.084,31.0%),空泡征(0.051,18.8%),內核(0.027,9.9%),結節(jié)密度(0.025,9.4%)。結論基于神經網(wǎng)絡建立的GGN侵襲性CT預測模型可用于GGN病理侵襲性評估。
[Abstract]:Objective to establish a CT model for predicting the invasion of GGNN by neural network analysis. Methods the CT features of 203 cases of lung adenocarcinoma proved by operation and pathology were analyzed retrospectively. The basic information of the patients was collected. The density of pulmonary nodules (pure glassy nodules or mixed glassy nodules) was calculated to determine whether they contained the kernel, size, and proportion of solid components. Three imaging features, vacuole sign, pleural traction sign and vascular cluster sign, were scored quantitatively by scoring method. The differences of CT features among different pathological groups were analyzed by univariate variance analysis. The patients were randomly divided into training group (n = 103) and test group (n = 100). Results among the 203 cases of pulmonary GGN, 20 cases had AAH and 26 cases had GGN. 83 cases of I-ADC. The nodules and diameters between the four pathological types. There were significant differences in the proportion of real components and the three image features by single factor ANOVA (P0.05). Based on this data, a multilayer perceptron based on neural network (MLP) was used. The prediction model was established. The overall prediction accuracy of the training group was 80.6% and AAH 92.9%. The overall accuracy of prediction in the AIS 38.5 and MIA91.2 (I-ADC81.0) test group was 72.0 and AIS 46.2%. MIA 72.5 and I-ADC 82.9, the importance of their variables in the model WTM / WTL WN 0.270 / 100, image feature score of 0.263. 97.6% WTMW0.099 / 36.7T / WTLWN 0.0979 / 36.00, and 0.085 / 31.5 for pleural traction). The vascular cluster sign was 0.084% 31.0%, the vacuole sign was 0.051% and 18.8%, the nucleus was 0.027% 9. 9%, and the nodular density was 0. 025%. Conclusion the predictive model of GGN invasive CT based on neural network can be used to evaluate the pathological invasiveness of GGN.
【作者單位】： 天津市天津醫(yī)科大學腫瘤醫(yī)院放射科;
【基金】：天津醫(yī)科大學腫瘤醫(yī)院科研項目(編號:Y1602-1)
【分類號】：R730.44;R734.2
【正文快照】： 近年來,隨著低劑量多層螺旋CT(low dose CT,電壓120 k V,自適應管電流,層厚1.25 mm,螺距LDCT)在早期肺癌篩查中的廣泛應用,越來越多的0.984∶1,旋轉時間0.6 s,視野(FOV)400 mm,重組肺磨玻璃密度結節(jié)(ground glass nodules,GGN)被早層厚1.25 mm,噪聲指數(shù)N=14,自適應統(tǒng)計迭代重

【相似文獻】

相關會議論文 前1條

1 韓敏;席劍輝;王立久;王金城;;用神經網(wǎng)絡分析建筑材料成分的構成[A];第二十屆中國控制會議論文集（下）[C];2001年

相關碩士學位論文 前1條

1 馬鵬飛;幾個不同類型的Hopfield神經網(wǎng)絡分析[D];東北林業(yè)大學;2010年

，

本文編號：1446784