基于神经网络分析法的肺磨玻璃密度结节侵袭性CT分析预测模型研究

被引：6

作者：

崔效楠

赵颖如

李绪斌

叶兆祥

机构：

[1] 天津市天津医科大学肿瘤医院放射科

来源：

临床放射学杂志 | 2017年 / 36卷 / 08期

关键词：

磨玻璃密度结节; 神经网络; 多层感知器;

D O I：

10.13437/j.cnki.jcr.2017.08.012

中图分类号：

R730.44 [放射线、同位素诊断]; R734.2 [肺肿瘤];

学科分类号：

100117 [系统生物医学]; 100234 [放射肿瘤学];

摘要：

目的利用神经网络分析法构建肺磨玻璃密度结节(GGN)侵袭性的CT预测模型,探讨其预测的准确性。方法回顾性分析203例经手术病理证实为肺腺癌的肺GGN的CT影像特征。采集患者基本信息,统计肺结节密度(纯磨玻璃结节或混合磨玻璃结节)、是否含有内核、大小、实性成分比例;采用评分法对空泡征、胸膜牵拉征、血管集束征三个影像特征进行量化评分,利用单因素方差分析各CT特征在不同病理分组间的差异,利用神经网络法将病例随机分为培训组(103例)和检验组(100例),建立各CT特征与GGN病理之间的预测模型。结果203例肺GGN中AAH 20例,AIS 26例,MIA 74例,I-ADC 83例。四组病理类型间的结节性质、直径、实性成分比例以及三个影像特征通过单因素方差分析均存在显著性差异(P<0.05)。基于此数据而使用神经网络的"多层感知器"(MLP)建立预测模型。培训组总体预测准确率为80.6%(AAH 92.9%,AIS 38.5%,MIA 91.2%,I-ADC81.0%)检验组预测总体准确率为72.0%(AAH 50.0%,AIS 46.2%,MIA 72.5%,I-ADC 82.9%),各自变量在模型中的重要性WTMW/WTLW(0.270,100%),影像特征评分(0.263,97.6%),WTMW(0.099,36.7%),WTLW(0.097,36.0%),胸膜牵拉征(0.085,31.5%),血管集束征(0.084,31.0%),空泡征(0.051,18.8%),内核(0.027,9.9%),结节密度(0.025,9.4%)。结论基于神经网络建立的GGN侵袭性CT预测模型可用于GGN病理侵袭性评估。

引用

页码：1101 / 1105

页数：5

共 14 条

[1]

Radiographically determined noninvasive adenocarcinoma of the lung: Survival outcomes of Japan Clinical Oncology Group 0201 [J].

Asamura, Hisao ;

Hishida, Tomoyuki ;

Suzuki, Kenji ;

Koike, Teruaki ;

Nakamura, Kenichi ;

Kusumoto, Masahiko ;

Nagai, Kanji ;

Tada, Hirohito ;

Mitsudomi, Tetsuya ;

Tsuboi, Masahiro ;

Shibata, Taro ;

Fukuda, Haruhiko .

JOURNAL OF THORACIC AND CARDIOVASCULAR SURGERY, 2013, 146 (01) :24-30

[2]

Artificial neural networks – A method for prediction of survival following liver resection for colorectal cancer metastases.[J].L. Spelt;J. Nilsson;R. Andersson;B. Andersson.European Journal of Surgical Oncology.2013, 6

[3]

Artificial Neural Network Model for Predicting 5-Year Mortality After Surgery for Hepatocellular Carcinoma: A Nationwide Study [J].

Shi, Hon-Yi ;

Lee, King-Teh ;

Wang, Jhi-Joung ;

Sun, Ding-Ping ;

Lee, Hao-Hsien ;

Chiu, Chong-Chi .

JOURNAL OF GASTROINTESTINAL SURGERY, 2012, 16 (11) :2126-2131

[4]

An optimal tumor marker group-coupled artificial neural network for diagnosis of lung cancer [J].

Wu, Yongjun ;

Wu, Yiming ;

Wang, Jing ;

Yan, Zhen ;

Qu, Lingbo ;

Xiang, Bingren ;

Zhang, Yiguo .

EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (09) :11329-11334

[5]

A Prospective Radiological Study of Thin-Section Computed Tomography to Predict Pathological Noninvasiveness in Peripheral Clinical IA Lung Cancer (Japan Clinical Oncology Group 0201) [J].

Suzuki, Kenji ;

Koike, Teruaki ;

Asakawa, Takashi ;

Kusumoto, Masahiko ;

Asamura, Hisao ;

Nagai, Kanji ;

Tada, Hirohito ;

Mitsudomi, Tetsuya ;

Tsuboi, Masahiro ;

Shibata, Taro ;

Fukuda, Haruhiko ;

Kato, Harubumi .

JOURNAL OF THORACIC ONCOLOGY, 2011, 6 (04) :751-756

[6]

Sublobar Resection for Early-Stage Lung Cancer [J].

Schuchert, Matthew J. ;

Abbas, Ghulam ;

Pennathur, Arjun ;

Nason, Katie S. ;

Wilson, David O. ;

Luketich, James D. ;

Landreneau, Rodney J. .

SEMINARS IN THORACIC AND CARDIOVASCULAR SURGERY, 2010, 22 (01) :22-31

[7]

Invasive Size is an Independent Predictor of Survival in Pulmonary Adenocarcinoma [J].

Borezuk, Alain C. ;

Qian, Fang ;

Kazeros, Angeliki ;

Eleazar, Jennifer ;

Assaad, Adel ;

Sonett, Joshua R. ;

Ginsburg, Mark ;

Gorenstein, Lyall ;

Powell, Charles A. .

AMERICAN JOURNAL OF SURGICAL PATHOLOGY, 2009, 33 (03) :462-469

[8]

Pulmonary segmentectomy by thoracotomy or thoracoscopy: Reduced hospital length of stay with a minimally-invasive approach [J].

Atkins, B. Zane ;

Harpole, David H., Jr. ;

Mangum, Jennifer H. ;

Toloza, Eric M. ;

D'Amico, Thomas A. ;

Burfeind, William R., Jr. .

ANNALS OF THORACIC SURGERY, 2007, 84 (04) :1107-1113

[9]

Radical sublobar resection for small-sized non–small cell lung cancer: A multicenter study.[J].Morihito Okada;Teruaki Koike;Masahiko Higashiyama;Yasushi Yamato;Ken Kodama;Noriaki Tsubota.The Journal of Thoracic and Cardiovascular Surgery.2006, 4

[10]

Outcomes of Sublobar Resection Versus Lobectomy for Stage I Non–Small Cell Lung Cancer: A 13-Year Analysis.[J].Amgad El-Sherif;William E. Gooding;Ricardo Santos;Brian Pettiford;Peter F. Ferson;Hiran C. Fernando;Susan J. Urda;James D. Luketich;Rodney J. Landreneau.The Annals of Thoracic Surgery.2006, 2

← 1 2 →