本文選題：肝癌　切入點(diǎn)：AFP　出處：《大連理工大學(xué)》2016年碩士論文

【摘要】：肝細(xì)胞癌(HCC)是世界范圍內(nèi)癌癥相關(guān)死亡的第二大病因,在世界范圍內(nèi)肝癌的發(fā)病率都呈上升趨勢(shì),全球每年大約有75萬(wàn)的新發(fā)病例。在中國(guó),基于人口的研究表明,肝細(xì)胞癌的發(fā)病率和死亡率在所有的癌癥類型里均排在第二位,并且其發(fā)病率近似于死亡率,這說(shuō)明患有肝癌的大部分患者都死于肝細(xì)胞癌。在臨床上,我們通常通過(guò)檢測(cè)AFP和腹部超聲波檢測(cè)法來(lái)診斷肝癌。而這種傳統(tǒng)的診斷方法存在兩個(gè)問(wèn)題：1.當(dāng)檢測(cè)到AFP異常時(shí),患者大多數(shù)往往已經(jīng)到了肝癌晚期,這時(shí)候不管是手術(shù)還是放療或化療等,患者的治愈率都是極低的,并且花費(fèi)極高；2.AFP并不是診斷肝癌的唯一標(biāo)志物,有時(shí)這個(gè)標(biāo)志物在診斷肝癌時(shí)是無(wú)效的,因此可能導(dǎo)致誤診,延誤了患者的最佳治療期。因此本篇論文以某醫(yī)院提供的當(dāng)?shù)卦缙诟伟�、肝病患者的檢測(cè)指標(biāo)為研究對(duì)象,提取這些指標(biāo)之間的隱藏模式和關(guān)系,通過(guò)這些指標(biāo)及關(guān)系構(gòu)建診斷早期肝癌的分類器,從而達(dá)到盡早預(yù)測(cè)肝癌、提高診斷肝癌準(zhǔn)確率的目的。研究?jī)?nèi)容包括以下方面：(1)分析早期肝癌患者和肝病患者的各項(xiàng)檢測(cè)指標(biāo),并對(duì)數(shù)據(jù)進(jìn)行分析和預(yù)處理。從分析結(jié)果上看,早期肝癌患者的AFP值大多數(shù)都處于正常范圍內(nèi),與肝病患者相當(dāng)；而這兩類患者的其他檢測(cè)指標(biāo)大多數(shù)都高于正常范圍。因此兩者之間的檢測(cè)指標(biāo)存在交叉部分,單靠檢測(cè)指標(biāo)并不能將肝癌患者與肝病患者區(qū)分開(kāi)來(lái)。數(shù)據(jù)預(yù)處理方面,利用關(guān)聯(lián)算法提取特異性指標(biāo),利用特征選擇和主成分分析(PCA)對(duì)數(shù)據(jù)進(jìn)行降維處理。(2)利用SVM對(duì)肝癌患者和肝病患者進(jìn)行分類研究,建立支持向量機(jī)分類器模型。此分類器模型整合了經(jīng)過(guò)數(shù)據(jù)預(yù)處理得到的16種特異性指標(biāo),這些指標(biāo)對(duì)于肝癌的診斷具有重要意義；同時(shí)利用網(wǎng)格劃分法和粒子群優(yōu)法算法優(yōu)化SVM模型參數(shù),最終分類器模型的預(yù)測(cè)準(zhǔn)確率分別是94.186%和93.0233%。(3)針對(duì)基本粒子群算法容易陷入局部最優(yōu)的問(wèn)題,提出了自適應(yīng)變異粒子群算法,利用變異操作對(duì)粒子群算法進(jìn)行優(yōu)化,以求達(dá)到全局最優(yōu)解,提高分類器的準(zhǔn)確率,最終得到的預(yù)測(cè)準(zhǔn)確率是95.3488%。
[Abstract]:Hepatocellular carcinoma (HCC) is the second leading cause of cancer-related deaths worldwide, and the incidence of liver cancer is on the rise worldwide, with about 750000 new cases per year worldwide. In China, population-based studies show that. The morbidity and mortality of hepatocellular carcinoma are the second highest among all cancer types, and the incidence is similar to the mortality rate, which means that most patients with liver cancer die from hepatocellular carcinoma. We usually use AFP and abdominal ultrasound to diagnose liver cancer. But there are two problems with this traditional diagnostic method: 1. When we detect abnormal AFP, the majority of patients tend to have advanced liver cancer. At this time, whether it is surgery, radiotherapy or chemotherapy, the cure rate of patients is extremely low, and the cost of AFP is extremely high. 2. AFP is not the only marker for the diagnosis of liver cancer. Sometimes this marker is ineffective in the diagnosis of liver cancer, so it may lead to misdiagnosis. The best treatment period is delayed. Therefore, this paper takes the local early liver cancer and liver disease detection index provided by a hospital as the research object, and extracts the hidden pattern and relationship between these indexes. Based on these indexes and relationships, a classifier for early diagnosis of liver cancer was constructed to predict liver cancer as early as possible. The purpose of this study is to improve the accuracy of diagnosis of liver cancer. The contents of the study include the following aspects: 1) Analysis of the early stage liver cancer patients and liver disease patients, and analysis and preprocessing of the data. From the perspective of the analysis results, Most of the AFP values of patients with early liver cancer are within the normal range, which is similar to that of the patients with liver disease, and most of the other indexes of the two groups are higher than the normal range. The detection index alone can not distinguish the liver cancer patients from the liver disease patients. In the aspect of data preprocessing, the association algorithm is used to extract the specific indexes. Feature selection and principal component analysis (PCA) were used to reduce the dimension of the data. (2) SVM was used to classify the patients with liver cancer and liver disease. The support vector machine classifier model is established. The classifier model integrates 16 specific indexes obtained by data preprocessing, which are of great significance for the diagnosis of liver cancer. At the same time, the SVM model parameters are optimized by using mesh division method and particle swarm optimization algorithm. The prediction accuracy of the final classifier model is 94.186% and 93.02333%, respectively. An adaptive mutation particle swarm optimization algorithm is proposed, in order to achieve the global optimal solution and improve the accuracy of the classifier, the prediction accuracy is 95.3488%.
【學(xué)位授予單位】：大連理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP18;R735.7

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 Kerstin Schütte;Christian Schulz;Alexander Link;Peter Malfertheiner;;Current biomarkers for hepatocellular carcinoma: Surveillance, diagnosis and prediction of prognosis[J];World Journal of Hepatology;2015年02期

2 Jung Woo Shin;Young-Hwa Chung;;Molecular targeted therapy for hepatocellular carcinoma:Current and future[J];World Journal of Gastroenterology;2013年37期

3 顧嵐;曹陽(yáng);鮑亞星;胡曉云;耿闖;方向明;;易忽略的CT間接征象對(duì)早期肝癌的診斷價(jià)值[J];臨床放射學(xué)雜志;2013年09期

4 黃婭;張鳳美;范志娟;劉樹(shù)業(yè);;甲胎蛋白、異常凝血酶原聯(lián)合檢測(cè)在肝細(xì)胞肝癌診斷中的臨床意義[J];中國(guó)實(shí)驗(yàn)診斷學(xué);2013年05期

5 肖蕾;毛睿;楊穎;張瑞麗;忙尼沙·阿不都拉;包永星;;高爾基體糖蛋白73、α-L-巖藻糖苷酶、甲胎蛋白單項(xiàng)檢測(cè)與聯(lián)合檢測(cè)對(duì)原發(fā)性肝癌的診斷價(jià)值研究[J];中國(guó)全科醫(yī)學(xué);2013年18期

6 叢文銘;;關(guān)于建立肝膽系統(tǒng)腫瘤病理生物學(xué)診斷模式的思考[J];臨床與實(shí)驗(yàn)病理學(xué)雜志;2013年01期

，

本文編號(hào)：1666554