本文選題：結(jié)節(jié)　切入點(diǎn)：TI-RADS　出處：《西南交通大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

【摘要】：在醫(yī)學(xué)領(lǐng)域中,結(jié)節(jié)是指未經(jīng)診斷不確定良惡性的腫塊,甲狀腺結(jié)節(jié)包含良性結(jié)節(jié)和惡性結(jié)節(jié)。其中甲狀腺癌就是惡性結(jié)節(jié),良性結(jié)節(jié)多是炎癥性結(jié)節(jié)或者囊腫。由于甲狀腺結(jié)節(jié)無明顯的病癥表現(xiàn),因此病癥極易被人忽視。目前,甲狀腺疾病的常用診斷方法是超聲檢測(cè),但是人工進(jìn)行超聲診斷仍然存在一些主觀缺陷。隨著醫(yī)學(xué)影像設(shè)備的廣泛應(yīng)用和數(shù)字圖像處理技術(shù)的飛速發(fā)展,利用圖像處理進(jìn)行計(jì)算機(jī)輔助診斷的研究越來越多。計(jì)算機(jī)輔助診斷的主要目的是通過計(jì)算機(jī)的識(shí)別處理把超聲圖像準(zhǔn)確地分類,為醫(yī)生和病人提供可參考的診斷結(jié)果。本文主要研究的是基于TI-RADS表的甲狀腺結(jié)節(jié)超聲圖像的特征提取和可視化。目的是研究TI-RADS等級(jí)不同的甲狀腺結(jié)節(jié)超聲圖像,把結(jié)節(jié)的分級(jí)結(jié)果和不同等級(jí)特征的差異利用圖像表現(xiàn)出來。主要研究?jī)?nèi)容包括三部分:甲狀腺結(jié)節(jié)超聲圖像的預(yù)處理,甲狀腺結(jié)節(jié)超聲圖像的特征提取以及甲狀腺結(jié)節(jié)超聲圖像的可視化設(shè)計(jì)。超聲圖像預(yù)處理包含圖像去噪和圖像分割。針對(duì)甲狀腺圖像中的斑點(diǎn)噪聲,應(yīng)用了基于邊緣增強(qiáng)的各向異性擴(kuò)散模型(EEAD),在保留超聲圖像質(zhì)量的情況下去除了超聲圖像中的斑點(diǎn)噪聲。針對(duì)超聲圖像的結(jié)節(jié)分割,提出了基于邊緣梯度算子和形狀約束的圖割算法(Graph Cut),主要通過最小化能量函數(shù)得到結(jié)節(jié)區(qū)域。分割算法優(yōu)化了超聲圖像分割結(jié)果形狀不準(zhǔn)確以及邊緣毛躁的現(xiàn)象。甲狀腺結(jié)節(jié)的特征提取提出了基于TI-RADS表的超聲圖像特征量化方法。把結(jié)節(jié)的特征分成形態(tài)、邊界、回聲、縱橫比和鈣化5類。通過形態(tài)學(xué)特征提取、灰度特征提取等多種方法,獲得5類共計(jì)34個(gè)數(shù)據(jù)特征,并用相關(guān)性、T檢驗(yàn)和聚類等方法對(duì)特征數(shù)據(jù)進(jìn)行了效果驗(yàn)證。在可視化研究階段,主要工作包括聚類分析和可視化設(shè)計(jì)。聚類算法根據(jù)特征的樣本規(guī)律將其劃分成不同等級(jí),數(shù)據(jù)可視化把分級(jí)結(jié)果利用可視化布局展示。實(shí)驗(yàn)中針對(duì)單一類別的特征聚類和多類特征聚類分別應(yīng)用了基于遺傳學(xué)的蟻群算法聚類(GACO)和多視圖加權(quán)聚類(TW-Kmeans)�？梢暬瘜�(shí)驗(yàn)針對(duì)不同的數(shù)據(jù)結(jié)構(gòu)設(shè)計(jì)可視化布局,實(shí)現(xiàn)針對(duì)基本信息的可視化和結(jié)節(jié)特征的可視化設(shè)計(jì)。應(yīng)用圓形分區(qū)圖和矩形樹狀圖表示基本信息之間的關(guān)系。應(yīng)用雷達(dá)圖、平行坐標(biāo)圖和星形散點(diǎn)圖表現(xiàn)結(jié)節(jié)的分級(jí)結(jié)果和不同級(jí)別的特征差異。
[Abstract]:In the field of medicine, nodule is an undiagnosed benign and malignant mass. Thyroid nodule contains benign and malignant nodule. Thyroid carcinoma is a malignant nodule. Benign nodules are mostly inflammatory nodules or cysts. Because thyroid nodule has no obvious symptom, it is easy to be ignored. At present, ultrasound is commonly used to diagnose thyroid diseases. However, there are still some subjective defects in artificial ultrasound diagnosis. With the wide application of medical imaging equipment and the rapid development of digital image processing technology, The main purpose of computer-aided diagnosis is to classify ultrasonic images accurately by computer recognition. This paper mainly studies the feature extraction and visualization of thyroid nodules based on TI-RADS table. The purpose of this paper is to study the ultrasound images of thyroid nodules with different TI-RADS grades. The difference between the classification results of the nodules and the characteristics of different grades is represented by the image. The main contents of the study include three parts: the preprocessing of the ultrasonic images of the thyroid nodules, The feature extraction of thyroid nodule ultrasound image and the visualization design of thyroid nodule ultrasonic image. Ultrasonic image preprocessing includes image denoising and image segmentation. An anisotropic diffusion model based on edge enhancement was applied to remove speckle noise in ultrasonic images without preserving the quality of ultrasound images. A graph cutting algorithm based on edge gradient operator and shape constraint is proposed, which is mainly used to minimize the energy function to obtain the nodule region. The segmentation algorithm optimizes the phenomena of inaccurate shape and hairy edge of ultrasonic image segmentation results. Feature extraction of thyroid nodule A method of ultrasonic image feature quantization based on TI-RADS table is proposed. The feature of thyroid nodule is divided into shape. The boundary, echo, aspect ratio and calcification are classified into five categories. By means of morphological feature extraction and gray feature extraction, a total of 34 data features of 5 categories are obtained. In the visualization research stage, the main work includes clustering analysis and visual design. The clustering algorithm divides the feature data into different grades according to the law of the samples. Data visualization shows the hierarchical results by visual layout. In the experiment, the genetic ant colony algorithm (ACO) and the multi-view weighted clustering (TW-Kmeansan) are applied to single class and multi-class feature clustering, respectively. Design visual layout for different data structures, The basic information is visualized and the nodule feature is visualized. The relationship between the basic information is expressed by using the circular partition map and the rectangular tree chart, and the radar image is used to show the relationship between the basic information and the basic information. Parallel coordinate map and star scatter plot show nodule classification results and characteristics of different grades.
【學(xué)位授予單位】：西南交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R581;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 吳向陽;張利軍;陳萬烤;計(jì)忠平;俞俊;;使用過濾與放大技術(shù)的微博數(shù)據(jù)監(jiān)控分析系統(tǒng)[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2016年11期

2 雷一鳴;趙希梅;于可歆;王國(guó)棟;郭衛(wèi)東;;魯棒的超聲圖像肝硬化識(shí)別方法[J];電子測(cè)量與儀器學(xué)報(bào);2016年10期

3 何曉琳;錢慶;張澤;;腫瘤流行病學(xué)數(shù)據(jù)可視化分析[J];中華醫(yī)學(xué)圖書情報(bào)雜志;2016年01期

4 李濤;李怡勇;米永巍;丁明躍;張冀;;甲狀腺結(jié)節(jié)鈣化特征的自動(dòng)提取方法研究[J];醫(yī)療衛(wèi)生裝備;2015年12期

5 方政;胡曉輝;陳永;;基于多方向中值濾波的各向異性擴(kuò)散濾波算法[J];計(jì)算機(jī)工程與應(yīng)用;2017年04期

6 李旺英;柳黔忠;張華珍;李麗珍;張健;;高頻超聲和CT診斷甲狀腺乳頭狀癌合并鈣化的臨床價(jià)值[J];醫(yī)學(xué)影像學(xué)雜志;2015年07期

7 陳力;紀(jì)祥虎;伍岳慶;;基于各向異性改進(jìn)的水平集超聲圖像去噪算法[J];計(jì)算機(jī)應(yīng)用;2015年S1期

8 張鋒軍;;大數(shù)據(jù)技術(shù)研究綜述[J];通信技術(shù);2014年11期

9 吳俊;汪源源;陳悅;余錦華;龐蕓;;基于同質(zhì)區(qū)域自動(dòng)選取的各向異性擴(kuò)散超聲圖像去噪[J];光學(xué)精密工程;2014年05期

10 翟東海;魚江;段維夏;肖杰;李帆;;米字型各向異性擴(kuò)散模型的圖像去噪算法[J];計(jì)算機(jī)應(yīng)用;2014年05期

，

本文編號(hào)：1611597