北京生物醫(yī)學(xué)工程

基于機(jī)器學(xué)習(xí)的肝癌無(wú)創(chuàng)檢測(cè)

Non-invasive detection of liver cancer based on machine learning

作者：熊征斯黃鋼郝麗俊許飛

單位：1上海理工大學(xué)醫(yī)療器械與食品學(xué)院（上海 200093）； 2 上海健康醫(yī)學(xué)院（上海 201318）； 3 上海交通大學(xué)醫(yī)學(xué)院（上海 200025）

關(guān)鍵詞：診斷；電子鼻；原發(fā)性肝癌；特征提取；機(jī)器學(xué)習(xí)

分類號(hào)：R318.04 R735.7

出版年·卷·期（頁(yè)碼）：2020·39·1（74-79）

摘要：

目的根據(jù)肝癌臨床診斷的需求，建立肝癌診斷預(yù)測(cè)模型，以達(dá)到無(wú)創(chuàng)檢測(cè)肝癌的目的。方法利用德國(guó)企業(yè)產(chǎn)ILD.3000型電子鼻設(shè)備采集正常受試者和肝癌患者的呼氣數(shù)據(jù)，對(duì)呼氣所得時(shí)間序列數(shù)據(jù)進(jìn)行特征提取，包括序列數(shù)據(jù)的最大值、最小值、均值、標(biāo)準(zhǔn)差、序列數(shù)據(jù)總和等統(tǒng)計(jì)學(xué)特征。結(jié)合特征降維算法和機(jī)器學(xué)習(xí)分類模型對(duì)呼氣特征數(shù)據(jù)進(jìn)行正常受試者和原發(fā)性肝癌患者的二分類實(shí)驗(yàn)。結(jié)果通過(guò)模型選擇和參數(shù)調(diào)整，在線性核函數(shù)支持向量機(jī)上對(duì)呼氣數(shù)據(jù)取得92.3%的最優(yōu)二分類結(jié)果。結(jié)論以正常受試者和肝癌患者的呼氣數(shù)據(jù)為樣本，利用機(jī)器學(xué)習(xí)建模的方法可以對(duì)肝癌做出診斷預(yù)測(cè)，且在此數(shù)據(jù)上，線性核函數(shù)支持向量機(jī)算法具有最好的分類效果。

Objective To establish a predictive model for diagnosis of liver cancer in order to achieve non-invasive detection of liver cancer. Methods The exhalation data of normal subjects and patients with liver cancer were collected by ILD.3000 electronic nose equipment manufactured by German enterprises. The features of exhalation time series data were extracted, including maximum, minimum, mean, standard deviation and sum of sequence data. Combining feature dimension reduction algorithm and machine learning classification model, a binary classification experiment was carried out for normal subjects and patients with primary liver cancer using expiratory feature data. Results Through model selection and parameter adjustment, 92.3% of the optimal binary classification results were obtained for exhalation data on linear kernel function support vector machine. Conclusion Using the exhalation data of normal subjects and patients with liver cancer as samples, the diagnosis and prediction of liver cancer can be made by using machine learning modeling method. On this data, the linear kernel function support vector machine algorithm has the best classification effect.

參考文獻(xiàn)：

[1] Fu J , Wang H . Precision diagnosis and treatment of liver cancer in China[J]. Cancer Letters, 2017, 412:283.

[2] 陳意飛, 夏偉, 顧晨, 等. 肝細(xì)胞癌臨床診斷及其適配體應(yīng)用的研究現(xiàn)狀[J]. 中華診斷學(xué)電子雜志, 2019, 7(2):141-144.

Chen YF, Xia W, Gu C, et al. Research of diagnosis and application of aptamer in hepatocellular carcinoma [J]. Chinese Journal of Diagnostics(Electronic Edition), 2019, 7(2): 141-144.

[3] Amann A ,Miekisch W ,Schubert J ,et al. Analysis of exhaled breath for disease detection[J]. Annual Review of Analytical Chemistry, 2014, 7(1):455-482.

[4] Rudnicka J, Kowalkowski T, Buszewski B. Searching for selected VOCs in human breath samples as potential markers of lung cancer[J]. Lung Cancer,2019,135:123-129.

[5] Saalberg Y , Wolff M . VOC breath biomarkers in lung cancer[J]. Clinica Chimica Acta, 2016, 459:5-9.

[6] Lopez-Sanchez LM, Jurado-Gamez B, Feu-Collado N, et al. Exhaled breath condensate biomarkers for the early diagnosis of lung cancer using proteomics[J]. American Journal of Physiology - Lung Cellular and Molecular Physiology, 2017, 313(4):664-676.

[7] Oakley-Girvan I , Davis SW . Breath based volatile organic compounds in the detection of breast, lung, and colorectal cancers: a systematic review[J]. Cancer Biomarkers, 2017,21(1):1-11.

[8] Kitiyakara T , Redmond S , Unwanatham N , et al. The detection of Hepatocellular carcinoma (HCC) from patients’ breath using canine scent detection: proof of concept study[J]. Journal of Breath Research, 2017, 11(4):046002.

[9] Kazmierczak PM , Theisen D , Thierfelder KM , et al. Improved detection of hypervascular liver lesions with CAIPIRINHA–dixon–TWIST–volume-interpolated breath-hold examination[J]. Investigative Radiology, 2015, 50(3):153-160.

[10] B?rwolf R, Zirnsak M , Freesmeyer M . Detection of a liver metastasis by breath-hold FDG-PET/CT not visible on standard PET/CT[J]. Japanese Journal of Clinical Oncology, 2014, 44(8):775.

[11] Rief M , Wagner M , Franiel T , et al. Detection of focal liver lesions in unenhanced

and ferucarbotran-enhanced magnetic resonance imaging: a comparison of T2-weighted breath-hold and respiratory-triggered sequences[J]. Magnetic Resonance Imaging, 2009, 27(9):1223-1229.

[12] 張方圓, 郁蕓, 趙宇, 等. 人工神經(jīng)網(wǎng)絡(luò)在臨床醫(yī)學(xué)中的應(yīng)用[J]. 北京生物醫(yī)學(xué)工程, 2016, 35(4):318-324.

Fangyuan Z , Yun YU , Yu Z , et al. Application of artificial neural network in clinical medicine[J]. Beijing Biomedical Engineering, 2016,35(4):318-324.

[13] Madara T, Māris B, Strazda G , et al. Detection of lung cancer in exhaled breath with an electronic nose using support vector machine analysis[J]. Journal of Breath Research, 2017 ，11 (3): 036009.

[14] 拱健婷,鄒慧琴,王佳宇,等. 基于電子鼻技術(shù)的不同產(chǎn)地當(dāng)歸快速鑒別研究[J].中國(guó)醫(yī)藥導(dǎo)報(bào)，2019,16（28）:39-43.

Gong JT,Zou HQ,Wang JY,et al. Rapid identification research on Angelica sinensis from different producing areas based on electronic nose technology[J]. China Medical Herald，2019,16（28）:39-43.

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