基于MRI影像组学的BI-RADS 3-5类乳腺病变三分类

医生根据磁共振影像征象对患者的乳腺病变程度进行BI-RADS分类评估时存在一定的主观性,且 BI-RADS 3-5类病变的良恶性存在交叉,在临床诊断时极易发生因诊断类别较高而造成不必要的有创治疗．针对这些问题,本文应用影像组学技术对乳腺的T₁加权（T1W）和动态对比增强（DCE）磁共振图像进行特征提取和融合,采用最小绝对收缩和选择算子（LASSO）算法筛选出各特征集的最优特征集,并分别使用支持向量机（SVM）、随机森林（RF）、K最近邻（KNN）及逻辑回归（LR）算法进行BI-RADS 3-5类乳腺病变三分类,并且在此基础上实现乳腺良恶性分类．结果显示基于特征融合的四个影像组学模型对乳腺病变BI-RADS 3-5类的分类准确率分别为81.25%、87.50%、78.38%、81.25%;对乳腺病变良恶性鉴别的准确率分别为90.91%、93.55%、92.73%、94.55%. 这表明MRI影像组学结合机器学习的算法对乳腺病变BI-RADS分类效果及良恶性鉴别效果均较好,且特征融合可进一步提高分类预测的准确率．     

基于多模态数据特征融合的舰船识别算法研究

在复杂海域场景下如何综合利用舰船监测的多模态数据进行高效特征提取和特征融合，以此来综合提升舰船识别精度仍存在巨大挑战。针对海域环境中舰船单一数据源识别准确率问题，提出一种有效的多模态数据特征提取和特征融合的舰船识别算法，然后基于深度残差网络模型进行特征融合以提升舰船识别准确率。通过实验结果对比，相比于其他算法基于多模态数据的舰船识别算法平均准确率提升约18%，有效地提升了舰船识别准确率，对相关船舶领域的研发工作具有借鉴意义。     

基于红外和可见光图像逐级自适应融合的场景深度估计

从图像中恢复场景的深度是计算机视觉领域中的一个关键问题。考虑到单一类型图像在深度估计中受场景不同光照的限制,提出了基于红外和可见光图像逐级自适应融合的场景深度估计方法（PF-CNN）。该方法包括双流滤波器部分耦合网络、自适应多模态特征融合网络以及自适应逐级特征融合网络。在双流卷积中红外和可见光图像的滤波器部分耦合使两者特征得到增强;自适应多模态特征融合网络学习红外和可见光图像的残差特征并将两者自适应加权融合,充分利用两者的互补信息;逐级特征融合网络学习多层融合特征的结合,充分利用不同卷积层的不同特征。实验结果表明:PF-CNN在测试集上获得了较好的效果,将阈值指标提高了5%,明显优于其他方法。     

基于多尺度特征与通道特征融合的脑肿瘤良恶性分类模型

针对脑肿瘤良恶性分类过程复杂、分类准确率不高等问题,提出了一种基于多尺度特征与通道特征融合的分类模型。该模型以ResNeXt网络为主干网络,首先,将基于空洞卷积的多尺度特征提取模块代替第一层卷积层,利用膨胀率获取不同感受野的图像信息,将全局特征与局部显著特征相结合;其次,添加通道注意力机制模块,融合特征通道信息,提高对肿瘤区域的关注度,降低对冗余信息的关注度;最后,采用学习率的线性衰减策略、图像的标签平滑策略以及基于医学图像的迁移学习策略的组合优化提高模型的学习能力和泛化能力。在BraTS2017和BraTS2019数据集中进行实验,准确率分别达到98.11%和98.72%。与经典模型和其他先进方法相比,该分类模型能够有效地减少分类过程的复杂度,提高脑肿瘤良恶性分类的准确率。     

基于异构光子神经网络的多模态特征融合

当前光子神经网络的研究主要集中在单一模态网络的性能提升上,而缺少对多模态信息处理的研究。与单一模态网络相比,多模态学习可以利用不同模态信息之间的互补性,因此,多模态学习可以使得模型学习到的表示更加完备。本文提出了将光子神经网络和多模态融合技术相结合的方法。首先,利用光子卷积神经网络和光子人工神经网络相结合构建异构光子神经网络,并通过异构光子神经网络处理多模态数据。其次,在融合阶段通过引入注意力机制提升融合效果,最终提高任务分类的准确率。在多模态手写数字数据集分类任务上,使用拼接方法融合的异构光子神经网络的分类准确率为95.75%;引入注意力机制融合的异构光子神经网络的分类准确率为98.31%,并且优于当前众多先进单一模态的光子神经网络。结果显示：与电子异构神经网络相比,该模型训练速度提升了1.7倍。与单一模态的光子神经网络模型相比,异构光子神经网络可以使得模型学习到的表示更加完备,从而有效地提高多模态手写数字数据集分类的准确率。     

基于深度可分离卷积的轻量化残差网络高光谱影像分类

针对传统深度残差网络在对高光谱图像进行特征提取和分类过程中因参数量大导致的训练时间长的问题,提出一种基于深度可分离卷积的轻量化残差网络模型（DSC-Res14）。该模型首先基于一层三维卷积层对经主成分分析方法降维后的高光谱影像进行光谱特征和空间特征初提取;其次,引入3个不同尺度的三维深度可分离卷积残差层对影像的深层语义特征进行提取,减少了网络训练参数量,增强了网络对高维、多尺度空间特征信息的表达能力。经在公开的Indian Pines和Pavia University标准数据集上进行实验验证,结果表明：所提模型在两个数据集上的分类精度分别为99.46%和99.65%;对比同类模型,所提模型在保证较高分类精度的同时,参数量和计算量小,训练时间短,并具有良好的鲁棒性。     

水下目标多模态深度学习分类识别研究

水下目标的分类识别对于水声探测具有重要意义。提出一种水下目标多模态深度学习分类识别方法。针对水声信号的一维时域模态和二维频域模态特征建立一种多模态特征融合的深度学习结构,结合长短时记忆网络和卷积神经网络的优点,对一维时域信号和二维频谱信号分别进行并行处理,对输出进行典型相关分析,形成特征融合表示,并利用相邻帧的相关性进行参数优化。利用实测水声信号对算法进行了验证。结果表明：提出的算法对于水下目标识别的精度有显著的提高。     

融合全局和局部深度特征的高分辨率遥感影像场景分类方法

提出了一种融合全局和局部深度特征(GLDFB)的视觉词袋模型。通过视觉词袋模型将深度卷积神经网络提取的多个层次的高层特征进行重组编码并融合,利用支持向量机对融合特征进行分类。充分利用包含场景局部细节信息的卷积层特征和包含场景全局信息的全连接层特征,完成对遥感影像场景的高效表达。通过对两个不同规模的遥感图像场景数据集的实验研究表明,相比现有方法,所提方法在高层特征表达能力和分类精度方面具有显著优势。     

多模态图像引导手术导航进展

手术导航综合运用器官分割建模与手术规划、位姿标定与跟踪定位、多模态图像配准与融合显示等技术，使医生精确定位病灶与手术工具的位置，透过组织表面对内部组织进行观测，可大幅提升手术的安全性，缩短手术时间并提高手术效率。常规手术通常使用超声、内窥镜或X光等单模态影像进行手术过程引导，信息单一且均为二维影像，空间立体信息缺失，手术过程严重依赖医生经验；而多模态图像引导的手术导航技术通过融合多模态图像的优势，在三维空间提供病灶的结构或功能信息，大幅提升医生对血管、神经以及重要组织结构的空间辨识力。由此，本文针对多模态图像分割建模、手术方案决策、手术空间位姿标定与跟踪、多模态图像配准、图像融合与显示等多模态图像引导手术导航的关键技术进行总结和分析，提出其进一步发展面临的挑战并展望其未来发展趋势。多模态图像引导手术导航技术已成为神经外科、颅颌面、骨科、经皮穿刺、血管介入等临床科室精准治疗的新兴手段，具有重要的应用前景。     

射线技术在医学领域的应用

正照片说明:图1用于肿瘤放射治疗的医用加速器关键部件-加速管图2用于人体全身扫描用PET样机图3用于乳腺癌早期微小病灶筛查和良恶性诊断的国内首台技术领先的乳腺专用分子影像诊断系统图4可同时进行正电子、单光子成像的双核素多功能乳腺成像系统图5面向小型活体动物,尤其是昆虫、鱼类以及小鼠、大鼠等啮齿动物的全身或局部结构高信噪比三维能谱成     

Computerized breast lesions detection using kinetic and morphologic analysis for dynamic contrast-enhanced MRI

To facilitate rapid and accurate assessment, this study proposed a novel fully automatic method to detect and identify focal tumor breast lesions using both kinetic and morphologic features from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). After motion registration of all phases of the DCE-MRI study, three automatically generated lines were used to segment the whole breast region of each slice. The kinetic features extracted from the pixel-based time-signal intensity curve (TIC) by a two-stage detection algorithm was first used, and then three-dimensional (3-D) morphologic characteristics of the detected regions were applied to differentiate between tumor and non-tumor regions. In this study, 95 biopsy-confirmed lesions (28 benign and 67 malignant lesions) in 54 women were used to evaluate the detection efficacy of the proposed system. The detection performance was analyzed using the free-response operating characteristics (FROC) curve and detection rate. The proposed computer-aided detection (CADe) system had a detection rate of 92.63% (88/95) of all tumor lesions, with 6.15 false positives per case. Based on the results, kinetic features extracted by TIC can be used to detect tumor lesions and 3-D morphology can effectively reduce the false positives.     

Computer-aided diagnosis of breast DCE-MRI using pharmacokinetic model and 3-D morphology analysis

Three-dimensional (3-D) dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) consists of a large number of images in different enhancement phases which are used to identify and characterize breast lesions. The purpose of this study was to develop a computer-assisted algorithm for tumor segmentation and characterization using both kinetic information and morphological features of 3-D breast DCE-MRI. An integrated color map created by intersecting kinetic and area under the curve (AUC) color maps was used to detect potential breast lesions, followed by the application of a region growing algorithm to segment the tumor. Modified fuzzy c-means clustering was used to identify the most representative kinetic curve of the whole segmented tumor, which was then characterized by using conventional curve analysis or pharmacokinetic model. The 3-D morphological features including shape features (compactness, margin, and ellipsoid fitting) and texture features (based on the grey level co-occurrence matrix) of the segmented tumor were obtained to characterize the lesion. One hundred and thirty-two biopsy-proven lesions (63 benign and 69 malignant) were used to evaluate the performance of the proposed computer-aided system for breast MRI. Five combined features including rate constant (k_ep), volume of plasma (v_p), energy (G₁), entropy (G₂), and compactness (C₁), had the best performance with an accuracy of 91.67% (121/132), sensitivity of 91.30% (63/69), specificity of 92.06% (58/63), and A_z value of 0.9427. Combining the kinetic and morphological features of 3-D breast MRI is a potentially useful and robust algorithm when attempting to differentiate benign and malignant lesions.     

Diagnosis of suspicious breast lesions using an empirical mathematical model for dynamic contrast-enhanced MRI

The purpose of this study was to test whether an empirical mathematical model (EMM) of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) can distinguish between benign and malignant breast lesions. A modified clinical protocol was used to improve the sampling of contrast medium uptake and washout. T(1)-weighted DCE magnetic resonance images were acquired at 1.5 T for 22 patients before and after injection of Gd-DTPA. Contrast medium concentration as a function of time was calculated over a small region of interest containing the most rapidly enhancing pixels. Then the curves were fitted with the EMM, which accurately described contrast agent uptake and washout. Results demonstrate that benign lesions had uptake (P<2.0 x 10(-5)) and washout (P<.01) rates of contrast agent significantly slower than those of malignant lesions. In addition, secondary diagnostic parameters, such as time to peak of enhancement, enhancement slope at the peak and curvature at the peak of enhancement, were derived mathematically from the EMM and expressed in terms of primary parameters. These diagnostic parameters also effectively differentiated benign from malignant lesions (P<.03). Conventional analysis of contrast medium dynamics, using a subjective classification of contrast medium kinetics in lesions as "washout," "plateau" or "persistent" (sensitivity=83%, specificity=50% and diagnostic accuracy=72%), was less effective than the EMM (sensitivity=100%, specificity=83% and diagnostic accuracy=94%) for the separation of benign and malignant lesions. In summary, the present research suggests that the EMM is a promising alternative method for evaluating DCE-MRI data with improved diagnostic accuracy.     

Feature fusion of palmprint and face via tensor analysis and curvelet transform

In order to improve the recognition accuracy of the unimodal biometric system and to address the problem of the small samples recognition, a multimodal biometric recognition approach based on feature fusion level and curve tensor is proposed in this paper. The curve tensor approach is an extension of the tensor analysis method based on curvelet coefficients space. We use two kinds of biometrics: palmprint recognition and face recognition. All image features are extracted by using the curve tensor algorithm and then the normalized features are combined at the feature fusion level by using several fusion strategies. The k-nearest neighbour (KNN) classifier is used to determine the final biometric classification. The experimental results demonstrate that the proposed approach outperforms the unimodal solution and the proposed nearly Gaussian fusion (NGF) strategy has a better performance than other fusion rules.     

Intravoxel incoherent motion diffusion-weighted imaging as an adjunct to dynamic contrast-enhanced MRI to improve accuracy of the differential diagnosis of benign and malignant breast lesions

PurposeTo investigate the value of use of intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) as an adjunct to dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to distinguish benign from malignant breast lesions.Materials and methodsRetrospective analysis of data pertaining to 117 patients with breast lesions who underwent DCE-MRI and IVIM-DWI examination with 3.0 T MRI was conducted. A total of 128 lesions were pathologically confirmed (47 benign and 81 malignant). Between-group differences in DCE-MRI parameters (Morphology, enhancement pattern, maximum slope of increase (MSI) and time–signal curve (TIC) type) and IVIM-DWI parameters (f value, D value and D* value) were assessed. Multivariate logistic regression was performed to identify variables that distinguished benign from malignant breast lesions. The diagnostic performance of DCE-MRI and DCE-MRI plus IVIM-DWI, to distinguish benign from malignant breast lesions, was evaluated using pathology results as the gold standard.ResultsLesion morphology, MSI, and TIC type (P < 0.05), but not the enhancement pattern (P > 0.05), were significantly different between the benign and malignant groups. The f (8.53 ± 2.14) and D* (7.64 ± 2.07) values in the malignant group were significantly higher than those in the benign group (7.68 ± 1.97 and 6.83 ± 2.13, respectively), while the D value (0.99 ± 0.22) was significantly lower than that (1.34 ± 0.17) in the benign group (P < 0.05 for all). On logistic regression analysis, the sensitivity, specificity and accuracy of DCE-MRI were 90.1%, 70.2% and 82.8% respectively; the corresponding figures for the combination of IVIM-DWI and DCE-MRI were 88.8%, 85.1%, and 87.5%respectively.ConclusionIVIM-DWI method as an adjunct to DCE-MRI can improve the specificity and accuracy in differential diagnosis of benign and malignant lesions of breast.     

Deep learning based classification of focal liver lesions with contrast-enhanced ultrasound

Classification of liver masses is important to early diagnosis of patients. In this paper, a diagnostic system of liver disease classification based on contrast enhanced ultrasound (CEUS) imaging is proposed. In the proposed system, the dynamic CEUS videos of hepatic perfusion are firstly retrieved. Secondly, time intensity curves (TICs) are extracted from the dynamic CEUS videos using sparse non-negative matrix factorizations. Finally, deep learning is employed to classify benign and malignant focal liver lesions based on these TICs. Quantitative comparisons demonstrate that the proposed method outperforms the compared classification methods in accuracy, sensitivity and specificity.     

基于I-BGLAM纹理和光谱融合的高光谱显微成像木材树种分类

为了提高木材树种分类的正确率,提出了一种基于I-BGLAM纹理特征和光谱特征融合的高光谱图像的木材树种分类方法。实验数据是利用SOC710VP高光谱成像仪获取的可见光/近红外（372.53~1 038.57 nm）范围内的高光谱图像。首先,利用基于OIF的特征波段选择方法降低高光谱图像的维数,选择出含有信息量大的波段。其次,对选择出的波段图像使用NSCT及NSCT逆变换得到融合图像,对得到的融合图像使用I-BGLAM提取其纹理特征。与此同时,对高光谱图像的全波段求取平均光谱并进行S-G（Savitzky-Golay）平滑得到光谱特征。最后,将得到的纹理特征和光谱特征融合后送进极限学习机（ELM）中进行分类。此外,还和基于灰度共生矩阵（GLCM）的木材识别的传统方法以及近几年木材树种识别领域内被提出的主流方法进行了比较。该研究主要创新点有两个：一是将强纹理提取器I-BGLAM用于高光谱图像中提取其纹理特征;二是提出一种新的特征融合的模型用于高光谱图像的分类。针对8个树种的实验结果表明,单独使用I-BGLAM提取的纹理特征来进行分类的正确率最高可到达88.54%,而使用GLCM提取纹理特征的传统方法正确率最高只有76.04%,该结果可以得出本文使用I-BGLAM在纹理特征提取方面要优于GLCM,这为后面建立的融合模型打下很好的基础,单独使用平均光谱特征来分类的正确率最高可以达到92.71%,使用所提出的特征融合方法所得到的分类正确率最高可达到100%,这说明使用所提出的融合模型来分类要比以前单独使用某一种特征的分类模型要好。此外,使用所提出的方法得到的分类正确率要高于本领域内其他两种主流的识别方法。因此,所提出的基于I-BGLAM纹理特征和光谱特征融合的方法能够提高木材树种分类的正确率,该方法在木材树种分类方面有着一定的利用价值。     

Robustness of radiomic features of benign breast lesions and hormone receptor positive/HER2-negative cancers across DCE-MR magnet strengths

Radiomic features extracted from breast lesion images have shown potential in diagnosis and prognosis of breast cancer. As medical centers transition from 1.5 T to 3.0 T magnetic resonance (MR) imaging, it is beneficial to identify potentially robust radiomic features across field strengths because images acquired at different field strengths could be used in machine learning models. Dynamic contrast-enhanced MR images of benign breast lesions and hormone receptor positive/HER2-negative (HR+/HER2-) breast cancers were acquired retrospectively, yielding 612 unique cases: 150 and 99 benign lesions imaged at 1.5 T and 3.0 T, and 223 and 140 HR+/HER2- cancerous lesions imaged at 1.5 T and 3.0 T, respectively. In addition, an independent set of seven lesions imaged at both field strengths, three benign lesions and four HR+/HER2- cancers, was analyzed separately. Lesions were automatically segmented using a 4D fuzzy c-means method; thirty-eight radiomic features were extracted. Feature value distributions were compared by cancer status and imaging field strength using the Kolmogorov-Smirnov test. Features that did not demonstrate a statistically significant difference were considered to be potentially robust. The area under the receiver operating characteristic curve (AUC), for the task of classifying lesions as benign or HR+/HER2- cancer, was determined for each feature at each field strength. Three features were found to be both potentially robust across field strength and of high classification performance, i.e., AUCs statistically greater than 0.5 in the classification task: one shape feature (irregularity), one texture feature (sum average) and one enhancement variance kinetics features (enhancement variance increasing rate). In the demonstration set of lesions imaged at both field strengths, two of the three potentially robust features showed qualitative agreement across field strength. These findings may contribute to the development of computer-aided diagnosis models that are robust across field strength for this classification task.     

Classification of breast mass lesions using model-based analysis of the characteristic kinetic curve derived from fuzzy c-means clustering

The purpose of this study is to evaluate the diagnostic efficacy of the representative characteristic kinetic curve of dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) extracted by fuzzy c-means (FCM) clustering for the discrimination of benign and malignant breast tumors using a novel computer-aided diagnosis (CAD) system. About the research data set, DCE-MRIs of 132 solid breast masses with definite histopathologic diagnosis (63 benign and 69 malignant) were used in this study. At first, the tumor region was automatically segmented using the region growing method based on the integrated color map formed by the combination of kinetic and area under curve color map. Then, the FCM clustering was used to identify the time-signal curve with the larger initial enhancement inside the segmented region as the representative kinetic curve, and then the parameters of the Tofts pharmacokinetic model for the representative kinetic curve were compared with conventional curve analysis (maximal enhancement, time to peak, uptake rate and washout rate) for each mass. The results were analyzed with a receiver operating characteristic curve and Student's t test to evaluate the classification performance. Accuracy, sensitivity, specificity, positive predictive value and negative predictive value of the combined model-based parameters of the extracted kinetic curve from FCM clustering were 86.36% (114/132), 85.51% (59/69), 87.30% (55/63), 88.06% (59/67) and 84.62% (55/65), better than those from a conventional curve analysis. The A(Z) value was 0.9154 for Tofts model-based parametric features, better than that for conventional curve analysis (0.8673), for discriminating malignant and benign lesions. In conclusion, model-based analysis of the characteristic kinetic curve of breast mass derived from FCM clustering provides effective lesion classification. This approach has potential in the development of a CAD system for DCE breast MRI.