This paper addresses the challenge of accurately segmenting COVID-19 lung infections in CT images, crucial for disease diagnosis and treatment. It proposes an improved seUNet-Attention model, enhancing the efficiency and accuracy of segmentation. The model, equipped with an attention mechanism, excels in identifying lung infection features, especially in low-contrast images. Experiments on public datasets show the model's superiority over existing methods, with improved detail preservation and edge segmentation of lesion areas. This advancement significantly supports clinical decision-making in diagnosing and treating COVID-19 lung infections.

The effect of a partial time delay on the response to external weak input signals in a bistable oscillator with anormal diffusive coupling was studied. Periodic resonance or anti-resonance in the signal response with time delay was observed, and the resonance period equals the period of the external input signal. Specifically, for the negative mean-field density parameter, the signal response can be improved through time delay, which is a resonance phenomenon. Conversely, for the positive mean-field density parameter, no such enhancement effect was observed, suggesting the presence of an anti-resonance phenomenon. As the probability of a partial time delay increases, the width of the time delay of the optimal signal response becomes narrower. When the probability of a partial time delay is large enough, the response of the system is optimal only when the time delay closely approximates integer or half-integer multiples of the external signal period. These numerical findings provide a new approach for weak signal detection that could be applied to the extraction of weak feature information within relevant fields.

Lots of studies have been carried out on characteristic of epileptic Electroencephalograph (EEG). However, traditional EEG characteristic research methods lack exploration of spatial information. To study the characteristics of epileptic EEG signals from the perspective of the whole brain?this paper proposed combination methods of multi-channel characteristics from time-frequency and spatial domains. This paper was from two aspects: Firstly, signals were converted into 2D Hilbert Spectrum (HS) images which reflected the time-frequency characteristics by Hilbert-Huang Transform (HHT). These images were identified by Convolutional Neural Network (CNN) model whose sensitivity was 99.8%, accuracy was 98.7%, specificity was 97.4%, F1-score was 98.7%, and AUC-ROC was 99.9%. Secondly, the multi-channel signals were converted into brain networks which reflected the spatial characteristics by Symbolic Transfer Entropy (STE) among different channels EEG. And the results show that there are different network properties between ictal and interictal phase and the signals during the ictal enter the synchronization state more quickly, which was verified by Kuramoto model. To summarize, our results show that there was different characteristics among channels for the ictal and interictal phase, which can provide effective physical non-invasive indicators for the identification and prediction of epileptic seizures.

Scalp EEG is often used to diagnose epileptic brain diseases in clinic, but its characteristics of high noise, strong interference, nonlinearity and non-stationary will affect clinical diagnosis and scientific research. In order to better solve this problem, the existing MNELAB software and empirical model decomposition（EMD） are used to process electroencephalogram（EEG） in epilepsy in this paper. Through comparative experiments, it is found that the artifact and noise removal methods based on MNELAB and EMD have achieved good results, but the program written by EMD algorithm can carry out multi-channel and mass signal processing. This method is superior to the existing software in autonomy and transparency. Good artifact and noise removal methods can provide important means and premise for scientific research on clinical diagnosis and EEG.

The automatic segmentation method of MRI brain tumors uses computer technology to segment and label tumor areas and normal tissues, which plays an important role in assisting doctors in the clinical diagnosis and treatment of brain tumors. This paper proposed a multiresolution fusion MRI brain tumor segmentation algorithm based on improved inception U-Net named MRF-IUNet (multiresolution fusion inception U-Net). By replacing the original convolution modules in U-Net with the inception modules, the width and depth of the network are increased. The inception module connects convolution kernels of different sizes in parallel to obtain receptive fields of different sizes, which can extract features of different scales. In order to reduce the loss of detailed information during the downsampling process, atrous convolutions are introduced in the inception module to expand the receptive field. The multiresolution feature fusion modules are connected between the encoder and decoder of the proposed network to fuse the semantic features learned by the deeper layers and the spatial detail features learned by the early layers, which improves the recognition and segmentation of local detail features by the network and effectively improves the segmentation accuracy. The experimental results on the BraTS (the Multimodal Brain Tumor Segmentation Challenge) dataset show that the Dice similarity coefficient (DSC) obtained by the method in this paper is 0.94 for the enhanced tumor area, 0.83 for the whole tumor area, and 0.93 for the tumor core area. The segmentation accuracy has been improved.

糖尿病性视网膜病变是一种难以诊断、高风险的致盲性疾病.针对人工对图像特征提取困难、分类准确性差、耗费时间长的问题,采用卷积神经网络构建糖尿病性视网膜病变自动分类器具有重要的临床价值.方法:本文针对已收集好的彩色眼底图像,通过对图像的清洗、扩增、归一化构建糖尿病性视网膜病变数据集.利用VGG16与FCN的优点将其结合,将全连接层改造为卷积层,构建新的糖尿病性视网膜病分类模型.将ImageNet充分训练好的VGG16网络模型参数作为本文模型初始化参数,送入已改造的神经网络模型提取特征,最后输出分类结果.结果:实验结果表明,本文提出的深度学习分类方法的准确率与损失值均优于传统同类别的卷积神经网络分类算法,对临床诊断参考有重要的意义.结论:本文利用的方法对解决数据分布不均衡和过拟合的问题有一定的促进作用,具有较好的鲁棒性.

In the field of ophthalmology, retinal diseases are often accompanied by complications, and effective segmentation of retinal blood vessels is an important condition for judging retinal diseases. Therefore, this paper proposes a segmentation model for retinal blood vessel segmentation. Generative adversarial networks (GANs) have been used for image semantic segmentation and show good performance. So, this paper proposes an improved GAN. Based on R2U-Net, the generator adds an attention mechanism, channel and spatial attention, which can reduce the loss of information and extract more effective features. We use dense connection modules in the discriminator. The dense connection module has the characteristics of alleviating gradient disappearance and realizing feature reuse. After a certain amount of iterative training, the generated prediction map and label map can be distinguished. Based on the loss function in the traditional GAN, we introduce the mean squared error. By using this loss, we ensure that the synthetic images contain more realistic blood vessel structures. The values of area under the curve (AUC) in the retinal blood vessel pixel segmentation of the three public data sets DRIVE, CHASE-DB1 and STARE of the proposed method are 0.9869, 0.9894 and 0.9885, respectively. The indicators of this experiment have improved compared to previous methods.

在计算机辅助眼底图像视网膜血管分割中,基于匹配滤波算法的应用非常广泛.而传统匹配滤波器算法存在分割细小血管效果较差、噪声多以及视盘干扰等问题.本文提出一种相似度滤波算法的眼底图像视网膜血管分割方法.首先用多层阈值和水平集算法提取视盘干扰区域,利用高斯模糊去除视盘干扰区域.然后采用相似度滤波运算对去除视盘干扰的彩色眼底图像进行处理.最后,将余弦相似度图进行二值化后与余弦相似度加强图进行区域连通性判断,实现眼底图像视网膜血管分割.结果 表明,该算法能较好地分割细小血管以及去除视盘干扰,能更为准确地提取眼底图像视网膜血管.

This study develops an accurate method based on the generative adversarial network (GAN) that targets the issue of the current discontinuity of micro vessel segmentation in the retinal segmentation images. The processing of images has become increasingly efficient since the advent of deep learning method. We have proposed an improved GAN combined with SE-ResNet and dilated inception block for the segmenting retinal vessels (SAD-GAN). The GAN model has been improved with respect to the following points. (1) In the generator, the original convolution block is replaced with SE-ResNet module. Furthermore, SE-Net can extract the global channel information, while concomitantly strengthening and weakening the key features and invalid features, respectively. The residual structure can alleviate the issue of gradient disappearance. (2) The inception block and dilated convolution are introduced into the discriminator, which enhance the transmission of features and expand the acceptance domain for improved extraction of the deep network features. (3) We have included the attention mechanism in the discriminator for combining the local features with the corresponding global dependencies, and for highlighting the interdependent channel mapping. SAD-GAN performs satisfactorily on public retina datasets. On DRIVE dataset, ROC_AUC and PR_AUC reach 0.9813 and 0.8928, respectively. On CHASE_DB1 dataset, ROC_AUC and PR_AUC reach 0.9839 and 0.9002, respectively. Experimental results demonstrate that the generative adversarial model, combined with deep convolutional neural network, enhances the segmentation accuracy of the retinal vessels far above that of certain state-of-the-art methods.

Automatic and accurate segmentation of brain tumors plays an important role in the diagnosis and treatment of brain tumors. In order to improve the accuracy of brain tumor segmentation, an improved multimodal MRI brain tumor segmentation algorithm based on U-net is proposed in this paper. In the original U-net, the contracting path uses the pooling layer to reduce the resolution of the feature image and increase the receptive field. In the expanding path, the up sampling is used to restore the size of the feature image. In this process, some details of the image will be lost, leading to low segmentation accuracy. This paper proposes an improved convolutional neural network named AIU-net (Atrous-Inception U-net). In the encoder of U-net, A-inception (Atrous-inception) module is introduced to replace the original convolution block. The A-inception module is an inception structure with atrous convolution, which increases the depth and width of the network and can expand the receptive field without adding additional parameters. In order to capture the multiscale features, the atrous spatial pyramid pooling module (ASPP) is introduced. The experimental results on the BraTS (the multimodal brain tumor segmentation challenge) dataset show that the dice score obtained by this method is 0.93 for the enhancing tumor region, 0.86 for the whole tumor region, and 0.92 for the tumor core region, and the segmentation accuracy is improved.

目的:分析智慧课堂在《数据结构与算法》教学中的应用效果.方法:选取皖南医学院同专业两个年级学生作为研究对象,分析比较智慧课堂教学和传统教学两种教学模式在《数据结构与算法》课程中的教学效果.2019级学生(n=133)采用智慧课堂教学作为研究组,2018级学生(n=135)采用传统课堂教学作为对照组,从作业成绩、实验成绩和期末考试成绩3个方面对教学效果进行客观评价.结果:研究组的作业成绩、期末考试成绩(85.40±7.66、81.80±8.64)均高于对照组(78.30±9.73、71.50±11.57),差异有统计学意义(P<0.05);而研究组实验成绩(72.60±10.81)与对照组(70.80±12.42)差异无统计学意义(P>0.05);研究组优良率(66.17％)高于对照组(29.63％),差异有统计学意义(P<0.05).结论:智慧课堂教学模式在《数据结构与算法》课程中总体教学效果优于传统教学模式.

随着大数据、人工智能等新一代信息技术与医疗健康深度融合,医疗健康行业对具有医学特色的信息化人才培养提出新的挑战.以皖南医学院信息管理与信息系统专业为例,通过培养目标和专业认可度分析专业现状,针对存在的问题,分别从学生和教师两个层面探索医学特色人才培养模式,以期切实贴合专业培养目标,为医疗卫生领域、相关企事业单位培养复合型专业人才,为医学院校非医学专业医学特色培养模式提供参考.

通过建立媒体介入的信息不对称医患纠纷博弈模型,得出媒体介入对医患纠纷博弈的影响.首先建立信息不对称医患纠纷博弈模型,研究其演化稳定策略,然后分别在网络媒体的正面引导和负面激化下建立信息不对称医患纠纷博弈模型,规定医患纠纷争夺的利益与医患发生冲突的代价的比值为医患利益冲突比,通过比较分析可得,当医患利益冲突比大于等于1时,媒体的正面引导提高了医方的收益,媒体的负面激化提高了患方的收益,降低了医方的收益;当医患利益冲突比小于1时,媒体的介入对医患群体最终混合策略的纳什均衡解没有影响,此时医患双方选择合作策略的比例取决于医患利益冲突比和医患信息不对称度,双方选择合作策略的比例都随医患利益冲突比的减小而增大,医方选择合作的比例随着医患信息不对称度的增大而增大,患方选择合作策略的比例随着医患信息不对称度的增加而减少.

医学信息专业结合信息科学和医学,以智能医疗为培养方向,形成"人工智能+医疗"复合专业培养新模式.结合"数据结构"课程和医学信息专业的特点,形成交叉学科相互融合的教学方法,实施先修课程导入、细化实验考核方式以及通过医学应用实例实施项目驱动教学,激发学生学习兴趣.教学实践表明,此方法能够充分发挥学生的学习兴趣,教学效果良好.

分析面向医学院校开设数据挖掘课程过程中存在的不足,给出数据挖掘实践教学资源库的建设原则,并根据医学院校人才培养特点、资源整合程度以及学生实践层次需求,提出"三级四层"实践教学资源库的建设框架,促进健康医疗大数据分析人才的实践创新能力培养.

癫痫是大脑神经细胞群超同步放电的一种常见慢性神经疾病,为了更好地对癫痫进行检测,提出了基于EEG的样本熵和深度神经网络(Deep Neural Network,DNN)的方法.将EEG信号用小波变换进行预处理后,以10 s为时间片求出样本熵,实验表明癫痫发作期间样本熵下降,经统计分析样本熵能够和数据集中已标注的标签基本一致,以样本熵下降处的点作为癫痫发作标签对数据集进行深度神经网络学习,能够达到99.5％的检测准确性.

脑电图(Electroencephalogram,EEG)是诊断癫痫发作的重要依据.针对人工识别癫痫脑电信号中出现的效率低易误诊等问题,依据遗传算法和支持向量机理论,提出基于遗传算法结合支持向量机分类模型(GM-SVM)的癫痫发作脑电信号识别方法.将支持向量机相关参数设计成遗传个体,将遗传算法的适应度值设置为GM-SVM的识别准确率,通过迭代寻优获得较优的识别效果.最后,该方法在伯恩大学癫痫研究中心的脑电数据上进行训练和评估,结果表明该方法可以正确识别癫痫发作脑电信号,并达到98％的精度和99％的AUC(Area Under ROC Curve,ROC曲线下的面积),相较于其他分类算法有较优的识别性能.

医学院校"大学计算机基础"课程是不可或缺的通识课,为了改进传统授课方法,利用学生碎片化学习时间,应设计一种针对医学院校移动教学App.对App进行了总体设计、数据库设计、详细功能设计以及实现等,最终把设计的App进行推广使用,能够有效地提供学生学习效率.

高倍镜下拍摄的图像视野小,不能看到完整的结构特征.为了获得全视野观看效果,文中提出基于SURF特征点提取的显微图像拼接方法.首先采用RANSAC算法剔除不匹配的特征点,然后用加权平滑的方法来消除拼接缝,并对背景亮度不均匀的问题进行处理.实验结果表明,文中方法能够精确有效地解决显微镜高倍镜下视野小,无法观察到清晰完整的组织细胞结构图像的问题.