基于支持向量机多模态超声模型诊断肾疾病

目的 比较基于支持向量机（SVM）和传统Logistic回归法基于常规超声、彩色多普勒超声和弹性成像参数构建的多模态超声模型诊断肾脏疾病的效能。方法 收集94例肾脏疾病患者（肾病组）及无肾脏疾病的对照组患者109名，分别进行常规超声、彩色超声和剪切波弹性检查。采用Logistic回归法和SVM构建模型。利用随机数字法将全部201例患者按照3：1分为2组，以其中153例为训练样本，进行单因素变量判断和建立SVM模型；以50例为验证样本，评价SVM模型的预测效果。结果 Logistic回归方程纳入左肾皮质弹性硬度和右肾宽度。Logistic回归模型预测肾脏疾病的准确率为83.74%，SVM模型为85.10%（χ²=0.21，P=0.65）。结论 多模态超声对于肾脏疾病具有较高诊断效能；SVM和Logistic模型的诊断效能相似。     

经直肠多模态超声联合应用在前列腺癌诊断中的临床价值

目的探讨多模态超声联合应用在前列腺癌（PCa）诊断中的临床价值。 方法选取2017年7月至2018年12月在温州医科大学附属第一医院就诊的临床疑似前列腺癌的患者202例,所有患者均行实验室检查及经直肠多模态超声检查,根据手术病理结果分为前列腺癌组和非前列腺癌组,应用Logistic回归单因素及多因素分析分别建立多模态超声诊断前列腺癌的模型及多模态超声联合实验室检查和临床资料诊断前列腺癌的模型,应用受试者工作特征曲线（ROC）曲线下面积比较新建两个模型、实验室检查、临床资料对前列腺癌的诊断效能。 结果单因素Logistic回归分析结果显示二维超声、彩色多普勒、弹性成像、造影剂到达时间、峰值强度、强度差以及单位时间增强强度诊断前列腺癌,差异均有统计学意义（χ²=5.89、13.81、44.15,Z=1.55、2.16、2.81、2.43,P均<0.05）,多因素Logistic回归分析结果显示：弹性成像和强度差是诊断前列腺癌的独立预测因子,建立模型多模态超声（MUS）评分。联合MUS评分、实验室检查和临床资料,进行单因素及多因素Logistic回归分析,结果显示,MUS评分、前列腺特异抗原密度（PSAD）和年龄是诊断前列腺癌的独立预测因子,建立模型MPA（MUS-PSAD-AGE）评分。MPA评分诊断PCa的ROC曲线下面积0.906,敏感度78.50%,特异度91.49%,阳性预测值91.30%,阴性预测值78.90%,MUS评分诊断PCa的ROC曲线下面积0.773,敏感度53.27%,特异度92.55%,阳性预测值89.10%,阴性预测值63.50%,PSAD诊断PCa的ROC曲线下面积0.847,敏感度76.64%,特异度89.36%,阳性预测值89.10%,阴性预测值77.10%,年龄诊断PCa的ROC曲线下面积0.675,敏感度77.57%,特异度48.94%,阳性预测值63.40%,阴性预测值65.70%。MPA评分对前列腺癌的诊断效能最高,且与MUS评分、PSAD及年龄比较,差异均有统计学意义（Z=8.48,t=-4.45,P均<0.05）。 结论多模态超声联合PSAD及年龄诊断前列腺癌具有较高的临床应用价值。     

颈部淋巴结核多模态超声表现的相关性研究

目的总结颈部淋巴结核多模态超声特征,探讨多模态超声对颈部淋巴结核的诊断价值。方法选取我院就诊的颈部淋巴结肿大患者105例,根据病理结果分为结核组70例和非结核组35例,比较两组多模态超声表现,应用Logistic多元回归分析淋巴结核的相关因素。结果结核组中37例(52.9%)淋巴结边界清晰,53例(75.7%)淋巴门结构消失,54例(77.1%)应变式弹性成像评分2分,42例(60.0%)弹性应变率比值2,56例(80.0%)超声造影发现液化坏死,均高于非结核组,差异均有统计学意义(均P0.05)。Logistic回归分析显示,超声造影发现液化坏死、淋巴结边界清晰及应变式弹性成像评分2分是淋巴结核的独立影响因素。结论多模态超声检查有助于颈部淋巴结核的准确诊断;液化坏死、淋巴结边界清晰及应变式弹性成像评分2分与颈淋巴结核相关。     

乳腺实性肿块超声诊断的Logistic回归分析

目的 应用二分类Logistic回归模型分析乳腺肿块良恶性的超声鉴别诊断.方法 选择经手术病理证实的151个乳腺病灶的二维灰阶超声、二维彩色多普勒超声、三维灰阶超声、三维彩色多普勒超声、超声弹性成像的各诊断指标进行多因素回归分析,建立Logistic模型.用ROC曲线法评价Logistic模型的预报能力.结果 经前进法逐步回归的多变量二分类Logistic回归分析,筛选引入方程的超声检查指标包括:弹性成像评分、形态、内部回声、阻力指数、后方回声和汇聚征.Logistic模型的预报正确率为97.35%,ROC曲线下面积为0.996.结论 二分类Logistic回归多元分析模型能很好地描述和分析良恶性乳腺肿块的超声鉴别诊断的过程,并能筛选出有意义的鉴别诊断指标.     

常规超声及UE诊断甲状腺单发结节良恶性的Logistic回归分析

目的：利用二元Logistic回归分析，评价常规超声、弹性成像在诊断甲状腺单发结节良恶性的价值。方法：对169例甲状腺单发结节进行常规超声和UE检查图像分析，以病理结果为“金标准”， 筛选甲状腺癌的具有统计学意义的特征指标，建立回归模型。结果：经过Logistic回归分析筛选出5个具有统计学意义的特征变量：年龄、形态、微钙化、血管走行、弹性评分，Logistic模型以预测概率P=0.5作为阈值，准确率达90.3%，ROL曲线下面积为0.908。结论：常规超声联合UE在甲状腺单发结节良恶性的诊断中具有一定的临床应用价值。     

应用二分类Logistic回归模型评价超声弹性成像在甲状腺微小结节鉴别诊断中的价值

目的 运用Logistic回归筛选能够鉴别甲状腺微小结节良恶性的超声声像图特征,建立以声像图特征为自变量的二分类Logistic回归模型,评价常规超声及超声弹性成像在甲状腺微小结节良恶性鉴别诊断中的价值.方法 对140例患者共166枚甲状腺微小结节(最大径≤10 mm)的二维、彩色多普勒及超声弹性成像检查图片进行回顾性分析,以病理结果为金标准,建立回归模型.比较进入方程中的变量的优势比(OR),评价各变量尤其是弹性成像的鉴别诊断效能.结果 经过Logistic逐步回归分析,共筛选出4个具有统计学意义的特征变量,包括:边界、钙化、结节内部成分及弹性评分.其中弹性评分的OR值高于其他自变量.结论 二分类Logistic回归模型筛选出对甲状腺微小结节病理性质有鉴别诊断意义的特征变量,超声弹性成像较其他超声特征更有优势.联合应用超声弹性成像及二维声像图特征对于甲状腺微小结节的确诊具有重要临床意义.     

原发性睾丸淋巴瘤多模态超声特征的初步研究

目的 研究分析原发性睾丸淋巴瘤的多模态超声声像图特征。方法 回顾性分析20例经病理证实的原发性睾丸淋巴瘤患者的声像图资料，包括灰阶超声、彩色多普勒超声、超声造影和弹性成像。结果 20例原发性睾丸淋巴瘤，其中19例为弥漫性大B细胞淋巴瘤，1例为成熟T细胞淋巴瘤。灰阶超声显示8例患者为弥漫型，表现为睾丸明显肿大伴回声弥漫性减低；12例患者为结节型，表现为睾丸实质内单个或多发低回声结节。彩色多普勒超声显示弥漫型和结节型病灶内均可见丰富的血流信号，为Ⅲ级血流。3例患者超声造影检查发现睾丸病灶平均灌注时间为5.7 s,睾丸病灶灌注强度高于正常睾丸实质。1例弥漫型患者行剪切波弹性成像，病变侧睾丸弹性值为17 kPa,而对侧正常睾丸弹性值为3.4 kPa。结论 原发性睾丸淋巴瘤的超声声像图具有一定的特征，充分应用多模态超声成像有助于原发性睾丸淋巴瘤的准确诊断。     

计算机辅助多模态融合超声诊断乳腺良恶性肿瘤

目的 观察利用深度学习（DL）融合常规超声和超声弹性成像诊断乳腺良、恶性肿瘤的效能。方法 利用DL卷积神经网络（CNN）提取乳腺肿瘤超声灰阶与超声弹性特征,并进行多模态融合,评价融合弹性图像或弹性比值等不同信息方式对乳腺良、恶性肿瘤的诊断效能;绘制受试者工作特征（ROC）曲线,计算曲线下面积（AUC）,评估多模态融合模型的诊断效能。结果 多模态融合模型鉴别乳腺良、恶性肿物的效能优于单模态常规超声或弹性模型,其中融合灰阶与弹性图像模型鉴别诊断效能优于融合灰阶与弹性比值模型,分类准确率达93.51%,敏感度为94.88%,特异度为92.25%,AUC达0.975。结论 计算机辅助多模态融合有助于提高超声对乳腺良、恶性肿瘤的诊断效能。     

颈淋巴结核多模态超声表现及病理基础相关性研究

目的 探讨颈部淋巴结核多模态超声特征与病理基础相关性,分析多模态超声对颈部淋巴结核的诊断价值。方法 选取自2017年1月至2019年3月于我院就诊的颈部淋巴结肿大患者105例为研究对象,均行多模态超声检查以及病理检查。根据病理结果分为结核组和非结核组,比较两组多模态超声表现,应用Logistic多元回归分析淋巴结核的相关因素。结果 结核组中37例(52.86%)淋巴结边界清晰,53例(75.71%)淋巴门结构消失,54例(77.14%)弹性成像评分<2分,42例(60.00%)弹性应变率比值<2,56例(80.00%)超声造影发现液化坏死,均高于非结核组,差异均具有统计学意义(P<0.05)。Logistic多元回归分析显示,超声造影发现液化坏死、淋巴结边界清晰以及弹性成像评分<2分是淋巴结核的独立相关因素。结论 超声造影显示液化坏死、淋巴结边界清晰以及弹性成像评分<2分与颈部淋巴结核相关,综合上述多模态超声表现有助于颈部淋巴结核的诊断。     

Logistic回归模型评价声触诊组织成像和定量技术在甲状腺结节鉴别诊断中的价值

目的建立以甲状腺结节超声诊断特征为变量的回归模型,评价甲状腺影像报告和数据系统(TI-RADS)中的5项超声特征及声触诊组织成像和定量技术(VTIQ)反映的结节硬度在甲状腺结节良恶性鉴别诊断中的价值。方法对95例甲状腺结节患者的120个结节行常规超声及VTIQ检查,以病理诊断为金标准建立Logistic回归模型。评价Logistic回归模型的预报能力,计算各变量的似然比,评价弹性与常规超声各项超声特征在甲状腺结节良恶性鉴别诊断中的价值,然后将原分类系统中预测能力最差的一项由弹性特征替代,绘制ROC曲线,比较校正前后ROC曲线下面积。结果运用Logistic回归分析,筛选出对良恶性鉴别诊断中有统计学意义的甲状腺结节超声特征,包括微钙化、边缘不清及结节质地硬。Logistic回归模型对甲状腺结节良恶性预报的准确率为80.83%(97/120),敏感度为75.93%(41/54),特异度为84.85%(56/66)。弹性替代实质结节重新评估甲状腺结节分类的ROC曲线下面积分别为0.700和0.797,P0.05。结论VTIQ反映的弹性特征较常规超声中的实质结节特征更有助于甲状腺结节良恶性的鉴别诊断。     

乳腺良恶性病变鉴别的MRI影像组学预测模型构建:基于随机森林、支持向量机、逻辑回归分类器

  目的  构建基于随机森林、支持向量机和逻辑回归分类器的MRI影像组学预测模型,对乳腺良恶性病变进行鉴别,并评估上述模型的诊断价值。  方法  回顾性分析在南方科技大学盐田医院进行MRI影像检查并获得手术病理的34例乳腺病变患者的动态增强MRI图像。按0.8∶0.2的比例将病例分为训练集（n=27）和测试集（n=7）。采用3D Slicer软件勾画乳腺病灶靶区并生成3D感兴趣体积,对每个感兴趣体积提取1037个影像组学特征,使用LASSO进行影像组学特征降维,然后在训练集中采用随机森林、支持向量机和逻辑回归等3种分类器分别构建乳腺良恶性病变的预测模型,并在测试集中进行评估。  结果  经LASSO降维后共选出6个影像组学特征标签进行建模,3种模型在训练集中的分类效果均非常好（曲线下面积>0.90）,其中稳定性最高的是基于逻辑回归分类器建立的乳腺良恶性病变影像组学预测模型。  结论  基于随机森林、支持向量机和逻辑回归的MRI影像组学预测模型在诊断乳腺良恶性病变方面都具有较好的诊断效能,其中逻辑回归模型更为稳定。影像组学方法可为乳腺良恶性病变的预测提供新的手段。      

Ultrasound Image–Based Deep Features and Radiomics for the Discrimination of Small Fat-Poor Angiomyolipoma and Small Renal Cell Carcinoma

We evaluated the performance of ultrasound image–based deep features and radiomics for differentiating small fat-poor angiomyolipoma (sfp-AML) from small renal cell carcinoma (SRCC). This retrospective study included 194 patients with pathologically proven small renal masses (diameter ≤4 cm; 67 in the sfp-AML group and 127 in the SRCC group). We obtained 206 and 364 images from the sfp-AML and SRCC groups with experienced radiologist identification, respectively. We extracted 4024 deep features from the autoencoder neural network and 1497 radiomics features from the Pyradiomics toolbox; the latter included first-order, shape, high-order, Laplacian of Gaussian and Wavelet features. All subjects were allocated to the training and testing sets with a ratio of 3:1 using stratified sampling. The least absolute shrinkage and selection operator (LASSO) regression model was applied to select the most diagnostic features. Support vector machine (SVM) was adopted as the discriminative classifier. An optimal feature subset including 45 deep and 7 radiomics features was screened by the LASSO model. The SVM classifier achieved good performance in discriminating between sfp-AMLs and SRCCs, with areas under the curve (AUCs) of 0.96 and 0.85 in the training and testing sets, respectively. The classifier built using deep and radiomics features can accurately differentiate sfp-AMLs from SRCCs on ultrasound imaging.     

基于CT影像组学结合机器学习模型预测食管胃结合部腺癌人表皮生长因子受体2状态

目的 评估基于C T影像组学结合机器学习模型术前预测食管胃交界处腺癌(A EG)人表皮生长因子受体2(HER2)状态的价值.方法 回顾性分析101例经术后病理证实的AEG患者,按7:3比例将其分为训练集(n=70)和验证集(n=31).基于门静脉期增强CT提取AEG影像组学特征,以最小绝对值选择与收缩算子回归模型针对训...     

基于剪切波弹性成像和卷积神经网络建立深度学习模型预测肾脏病变

目的 基于剪切波弹性成像（SWE）量化参数和卷积神经网络建立深度学习（DL）模型预测肾脏病变。方法 采集94例肾脏病变患者（病例组）和109名健康人（对照组）的肾脏超声SWE量化参数。利用卷积神经网络建立DL模型,比较DL模型和支持向量机、随机森林模型预测肾脏病变的敏感度、特异度、准确率和曲线下面积（AUC）。结果 DL模型对预测肾脏病变的敏感度为90.48%,特异度为100%,准确率为95.12%,AUC为0.93;支持向量机模型的敏感度、特异度、准确率和AUC分别为80.74%、80.71%、80.98%、0.90,随机森林模型分别为82.22%、77.87%、80.33%和0.88。DL模型预测敏感度、特异度、准确率和AUC均高于支持向量机和随机森林模型,与支持向量机模型和随机森林模型预测肾脏病变差异均有统计学意义（P均<0.05）。结论 基于SWE量化参数和卷积神经网络的DL模型预测肾脏疾病性能良好,具有一定临床价值。     

Point Shear Wave Elastography Using Machine Learning to Differentiate Renal Cell Carcinoma and Angiomyolipoma

The question of whether ultrasound point shear wave elastography can differentiate renal cell carcinoma (RCC) from angiomyolipoma (AML) is controversial. This study prospectively enrolled 51 patients with 52 renal tumors (42 RCCs, 10 AMLs). We obtained 10 measurements of shear wave velocity (SWV) in the renal tumor, cortex and medulla. Median SWV was first used to classify RCC versus AML. Next, the prediction accuracy of 4 machine learning algorithms—logistic regression, naïve Bayes, quadratic discriminant analysis and support vector machines (SVMs)—was evaluated, using statistical inputs from the tumor, cortex and combined statistical inputs from tumor, cortex and medulla. After leave-one-out cross validation, models were evaluated using the area under the receiver operating characteristic (ROC) curve (AUC). Tumor median SWV performed poorly (AUC = 0.62; p = 0.23). Except logistic regression, all machine learning algorithms reached statistical significance using combined statistical inputs (AUC = 0.78–0.98; p < 7.1 × 10^–3). SVMs demonstrated 94% accuracy (AUC = 0.98; p = 3.13 × 10^–6) and clearly outperformed median SWV in differentiating RCC from AML (p = 2.8 × 10^–4).     

基于超声影像组学的乳腺癌预测模型的诊断性能研究

目的评估并比较基于不同机器学习算法建立的乳腺癌超声影像组学预测模型的诊断性能。 方法回顾性收集2017年1月至2019年4月就诊皖南医学院第一附属医院、有明确病理结果的乳腺肿块病例828例，以2018年8月31日为节点将其分为训练集（526例）和验证集（302例），提取肿块的超声影像组学特征并进行特征筛选，运用k最近邻（kNN）、逻辑回归（LR）、朴素贝叶斯（NB）、随机森林（RF）和支持向量机（SVM）5种机器学习算法分别建立预测模型，使用重复交叉验证方法做内部验证，计算比较各模型的敏感度、特异度、阳性预测值（PPV）和阴性预测值（NPV），并实施外部验证，绘制ROC曲线并比较ROC曲线下面积（AUC）以评价模型的鉴别诊断性能，绘制校准曲线评价模型校准度。 结果从提取的109个影像组学特征中筛选出19个特征建立了5种机器学习算法模型。在内部验证中，5种模型的敏感度、特异度、PPV、NPV比较，总体差异均有统计学意义（P均＜0.001）。LR模型的特异度、PPV、NPV中位数分别为0.769、0.816、0.778，3项指标均高于其他4种模型；敏感度中位数为0.824，高于kNN、RF和SVM模型。此外，SVM模型的特异度、PPV、NPV中位数分别为0.706、0.774、0.759，虽均低于LR模型，但均高于其他3种模型。在外部验证中，LR、SVM、RF、kNN和NB的AUC依次为0.890、0.832、0.821、0.746和0.703，其中LR与SVM的AUC差异有统计学意义（P=0.012）；此外，各模型在校准性能上表现并不一致，LR和SVM模型的校准曲线显示乳腺癌实际概率与预测概率之间的一致性较好。 结论以超声影像组学特征为基础，运用不同机器学习算法建立的乳腺癌超声预测模型，均表现出较高的诊断性能，其中LR模型表现最为突出；选择合适的机器学习算法有助于进一步提高预测模型的诊断性能，提供更加准确的量化预测结果。     

Assessment of lipid peroxidation and artificial neural network models in early Alzheimer Disease diagnosis

Objective: Lipid peroxidation constitutes a molecular mechanism involved in early Alzheimer Disease (AD) stages, and artificial neural network (ANN) analysis is a promising non-linear regression model, characterized by its high flexibility and utility in clinical diagnosis. ANN simulates neuron learning procedures and it could provide good diagnostic performances in this complex and heterogeneous disease compared with linear regression analysis. Design and Methods: In our study, a new set of lipid peroxidation compounds were determined in urine and plasma samples from patients diagnosed with early Alzheimer Disease (n = 70) and healthy controls (n = 26) by means of ultra-performance liquid chromatography coupled with tandem mass-spectrometry. Then, a model based on ANN was developed to classify groups of participants. Results: The diagnostic performances obtained using an ANN model for each biological matrix were compared with the corresponding linear regression model based on partial least squares (PLS), and with the non-linear (radial and polynomial) support vector machine (SVM) models. Better accuracy, in terms of receiver operating characteristic-area under curve (ROC-AUC), was obtained for the ANN models (ROC-AUC 0.882 in plasma and 0.839 in urine) than for PLS and SVM models. Conclusion: Lipid peroxidation and ANN constitute a useful approach to establish a reliable diagnosis when the prognosis is complex, multidimensional and non-linear.     

Lumbar Ultrasound Image Feature Extraction and Classification with Support Vector Machine

Needle entry site localization remains a challenge for procedures that involve lumbar puncture, for example, epidural anesthesia. To solve the problem, we have developed an image classification algorithm that can automatically identify the bone/interspinous region for ultrasound images obtained from lumbar spine of pregnant patients in the transverse plane. The proposed algorithm consists of feature extraction, feature selection and machine learning procedures. A set of features, including matching values, positions and the appearance of black pixels within pre-defined windows along the midline, were extracted from the ultrasound images using template matching and midline detection methods. A support vector machine was then used to classify the bone images and interspinous images. The support vector machine model was trained with 1,040 images from 26 pregnant subjects and tested on 800 images from a separate set of 20 pregnant patients. A success rate of 95.0% on training set and 93.2% on test set was achieved with the proposed method. The trained support vector machine model was further tested on 46 off-line collected videos, and successfully identified the proper needle insertion site (interspinous region) in 45 of the cases. Therefore, the proposed method is able to process the ultrasound images of lumbar spine in an automatic manner, so as to facilitate the anesthetists' work of identifying the needle entry site.     

Establishment of a discriminant mathematical model for diagnosis of deficiency-cold syndrome using gene expression profiling

OBJECTIVE: To screen diagnostic markers of Deficiency-Cold syndrome by gene expression profile and to establish a discriminant mathematical milliliters model for the clinical diagnosis of this syndrome based on a support vector machine (SVM). METHODS: A family suffering from Deficiency-Cold syndrome is chosen for this study. This family has 5 patients with Deficiency-Cold syndrome and 10 normal members. The peripheral blood samples for these 5 patients and 5 normal members are tested by using cDNA microarray with 18,816 clones to get their differential expression genes. These genes are further explored to understand their biological functions and pathways through existing databases. A SVM model for clinical diagnosis is then developed based on these differential expression genes. RESULTS: A total of 83 differential expression genes were identified between patients and normal members, in which 21 genes were recorded in the FATIGO database and 16 genes were related to metabolism. Eight (8) pathways were sorted out in the KEGG database, and half pathways were associated with human metabolism. A discriminant mathematical model based on a support vector machine successfully predicted a normal person and a patient with heavy Deficiency-Cold syndrome based on their gene differential expression profiles. Thus, this model may classify the Deficiency-Cold syndrome. CONCLUSION: This work demonstrates that the differential expression genes can be used to identify normal persons and patients with Deficiency-Cold syndrome. Deficiency-Cold syndrome is mainly associated with the metabolism-related gene regulations. In addition, the discriminant mathematical model based on a support vector machine is applicable to the clinical diagnosis for Deficiency-Cold syndrome.     

声触诊组织定量分析在慢性肾病中应用的初步探讨

目的 初步探讨声触诊组织定量分析技术(VTQ)在慢性肾病(CKD)中的应用价值.方法 CKD组65例、对照组70例共270个肾脏行VTQ检查,测量反映组织弹性和顺应力的剪切波速度(Vs), 将结果和常规超声、血Scr/BUN、病理结果进行对照和统计学分析.结果 肾脏Vs值由高到低依次为肾皮质区>肾髓质区>肾窦区.CKD组肾皮质Vs较对照组低;常规超声图像上典型CKD表现者肾皮质区Vs减低,常规超声表现正常而血Scr/BUN异常者多数肾皮质区Vs亦减低.设定肾皮质Vs 2.9～4.1 m/s为正常范围,VTQ对肾病检出阳性率高于血Scr/BUN检查.结论 VTQ能敏感并较早发现肾病组织弹性顺应力异常,为临床提供更丰富的信息.