【摘要】：隨著超聲成像和醫(yī)學(xué)診斷技術(shù)的發(fā)展，超聲已成為甲狀腺癌檢查的主要手段之一。當(dāng)前，甲狀腺癌的確定主要通過醫(yī)生對B超圖像的定性判別來完成，但由于甲狀腺癌生物學(xué)特性多變以及各大醫(yī)院診斷側(cè)重點(diǎn)的不一，使得診斷結(jié)果易受醫(yī)生的經(jīng)驗(yàn)、水平、狀態(tài)等因素的影響，診斷結(jié)果的準(zhǔn)確度很難保證。因此，需要建立一種客觀的方法，為醫(yī)師診斷甲狀腺疾病提供必要的輔助手段。 集成學(xué)習(xí)是機(jī)器學(xué)習(xí)中的一種新型技術(shù)，它是在對新的實(shí)例進(jìn)行分類的時(shí)候，把若干個(gè)體分類器集成起來，通過對多個(gè)分類器的分類結(jié)果進(jìn)行某種組合來決定最終的分類，通常情況下，集成學(xué)習(xí)能夠獲得比單個(gè)分類器更好的性能。論文將動(dòng)態(tài)集成技術(shù)引入到醫(yī)學(xué)圖像的分類問題中，研究如何利用動(dòng)態(tài)集成算法在分類上的優(yōu)勢解決甲狀腺B超圖像分類識別中識別率低的問題。 針對上述存在的問題，本文對特征提取量化、集成算法等方面進(jìn)行了深入的研究，主要獲得以下研究成果： 1.針對傳統(tǒng)集成算法無法獲得穩(wěn)定分類精度的問題，對基于聚類的動(dòng)態(tài)集成算法進(jìn)行了改進(jìn)，改進(jìn)k-means聚類算法的目標(biāo)函數(shù)和與能力區(qū)域距離計(jì)算公式，得到一種新的聚類和距離測量標(biāo)準(zhǔn)，提高了集成算法的分類準(zhǔn)確率；同時(shí)，，提出了一種選擇加權(quán)動(dòng)態(tài)集成方法，采用多個(gè)分類器進(jìn)行并聯(lián)集成，以此來增加分類模型的穩(wěn)定性；最后，通過實(shí)驗(yàn)證明了本文改進(jìn)算法的有效性。 2.通過分析甲狀腺B超圖像，研究甲狀腺良惡性結(jié)節(jié)在超聲圖像上的不同特點(diǎn)，綜合考慮臨床鑒別甲狀腺結(jié)節(jié)的各種特征，分別對其進(jìn)行量化，并提出了針對甲狀腺結(jié)節(jié)特有的微鈣化度度量方法，最終提取了最能描述結(jié)節(jié)性質(zhì)的圓形度、衰減系數(shù)、微鈣化度等9個(gè)特征參數(shù)作為甲狀腺疾病數(shù)據(jù)集，為醫(yī)生提供較為客觀的量化參數(shù)。 3.為衡量本文算法分類器的性能，將本文基于改進(jìn)動(dòng)態(tài)集成的方法與相似研究常用的線性判別、BP神經(jīng)網(wǎng)絡(luò)和SVM算法進(jìn)行了分類效果的比較，證明了本文算法的優(yōu)勢。
[Abstract]:With the development of ultrasound imaging and medical diagnosis, ultrasound has become one of the main methods of thyroid cancer examination. At present, the determination of thyroid cancer is mainly accomplished by the qualitative identification of B-ultrasound images by doctors. However, because of the changeable biological characteristics of thyroid cancer and the different diagnostic emphases in major hospitals, the diagnosis results are easily subject to the doctor's experience and level. The accuracy of diagnostic results is difficult to ensure due to the influence of state and other factors. Therefore, it is necessary to establish an objective method for physicians to diagnose thyroid diseases. Ensemble learning is a new technology in machine learning. When classifying new examples, it integrates several individual classifiers and determines the final classification by combining the classification results of multiple classifiers. In general, ensemble learning can achieve better performance than a single classifier. In this paper, the dynamic integration technique is introduced into the medical image classification problem, and how to use the dynamic integration algorithm to solve the problem of low recognition rate in the classification and recognition of thyroid B ultrasound image is studied. In view of the above problems, this paper makes a deep research on the feature extraction and quantization, integration algorithm and so on. The main research results are as follows: 1. Aiming at the problem that the traditional ensemble algorithm can not obtain the stable classification accuracy, the dynamic ensemble algorithm based on clustering is improved to improve the objective function of the k-means clustering algorithm and the calculation formula of distance between the clustering algorithm and the capability region. A new clustering and distance measurement standard is obtained, which improves the classification accuracy of the ensemble algorithm. At the same time, a selective weighted dynamic ensemble method is proposed, in which multiple classifiers are used for parallel integration to increase the stability of the classification model. Finally, the effectiveness of the improved algorithm is proved by experiments. 2. By analyzing the B-ultrasound images of thyroid gland, the different characteristics of benign and malignant thyroid nodules on ultrasound images were studied, and the clinical features of distinguishing thyroid nodules were comprehensively considered and quantified respectively. Finally, nine characteristic parameters, such as roundness, attenuation coefficient and microcalcification degree, which can best describe the nature of thyroid nodules, are extracted as data sets of thyroid diseases. To provide more objective quantitative parameters for doctors. 3. In order to evaluate the performance of the classifier in this paper, the improved dynamic ensemble method is compared with the linear discriminant, BP neural network and SVM algorithm, and the advantages of this algorithm are proved.
【學(xué)位授予單位】：河北大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：R445.1;R736.1;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李國正,楊杰,孔安生,陳念貽;基于聚類算法的選擇性神經(jīng)網(wǎng)絡(luò)集成[J];復(fù)旦學(xué)報(bào)(自然科學(xué)版);2004年05期

2 梅浩;;甲狀腺癌病理分型與手術(shù)術(shù)式相關(guān)性分析[J];當(dāng)代醫(yī)學(xué);2012年26期

3 徐亞利;陶曉峰;;甲狀腺結(jié)節(jié)的影像學(xué)診斷新進(jìn)展[J];放射學(xué)實(shí)踐;2013年04期

4 趙杰;祁永梅;;一種新的甲狀腺腫瘤超聲圖像特征提取算法[J];光電工程;2013年09期

5 張燕平;曹振田;趙姝;鄭堯軍;杜玲;竇蓉蓉;;一種新的決策樹選擇性集成學(xué)習(xí)方法[J];計(jì)算機(jī)工程與應(yīng)用;2010年17期

6 張健沛;程麗麗;楊靜;馬駿;;基于全信息相關(guān)度的動(dòng)態(tài)多分類器融合[J];計(jì)算機(jī)科學(xué);2008年03期

7 周志華,陳世福;神經(jīng)網(wǎng)絡(luò)集成[J];計(jì)算機(jī)學(xué)報(bào);2002年01期

8 征荊,丁曉青,吳佑壽;基于最小代價(jià)的多分類器動(dòng)態(tài)集成[J];計(jì)算機(jī)學(xué)報(bào);1999年02期

9 胡步發(fā);陳炳興;黃銀成;;基于表情子空間多分類器集成的非特定人人臉表情識別[J];計(jì)算機(jī)應(yīng)用;2011年03期

10 郝紅衛(wèi);王志彬;殷緒成;陳志強(qiáng);;分類器的動(dòng)態(tài)選擇與循環(huán)集成方法[J];自動(dòng)化學(xué)報(bào);2011年11期

本文編號：2322061