Accurate quantification of blood cells samples plays a critical role in clinical diagnosis. In this study, we have developed a deep learning network based on YOLOv5 that integrates attention mechanisms into the backbone network for precise detection of blood cells. Extensive experiments were conducted on BCCD dataset to evaluate the effectiveness of our approach. Our experimental results demonstrate the impact of incorporating attention mechanisms into the YOLOv5 network. Notably, our method achieved an impressive precision rate of 89.8%, surpassing the original result by 1.7 percentage points. This improvement signifies the power of attention mechanisms in enhancing the precision of blood cell detection.

文章以医学数据挖掘课程为例,从教学现状出发,分析该课程在医学本科院校中的教学现状和存在的问题,探讨了如何提升医学信息工程和信息管理与信息系统等专业本科生的数据挖掘理论基础,实践能力和综合素养等,并应用数据挖掘技术解决医学相关的实际问题的能力.在实际教学中已取得了一些较好的效果,为医学院校的新工科建设提供了良好的示范作用.

Most non-coding RNAs interacting with corresponding RNA-binding proteins are important for the post-transcriptional gene regulation and other biological processes. The identification of RNA-protein interactions (RPIs) is carried out through biological experimental technology, which is time-consuming and expensive. In this research, we design a parallel convolutional neural network, which employed two 1D convolution neural network for RNA and protein sequence feature extraction and one 2D convolution neural network for cross-correlation information, to predict ncRNA-protein interactions. Our method was tested on five benchmark datasets (RPI369, RPI488, RPI1807, RPI2241 and NPInter2.0), and got an AUC of 0.761, 0.91, 0.991, 0.929 and 0.981, respectively. The results show that cross-correlation information is an effective supplement to the features of RNA and protein sequence.

The valid prediction of unanticipated difficult tracheal intubation (DTI) is very important in clinic anesthesia. The purpose of this study was to develop a machine learning model for predicting unanticipated DTI. A comprehensive analysis of two prospective observational difficult airway research programs was performed. In total, 3958 patients who underwent tracheal intubation were included in this study. Data were split into a training set and a test set according to 70%:30% randomly. XGBoost machine learning was used to develop a machine learning model for predicting unanticipated DTI. The F1 score was used as the main performance metric because of data imbalance. The model parameter tuning was performed in the training set via pipeline grid search with the aim of optimizing the F1 score. Then, the tuning model were used for unanticipated DTI prediction in the test set. The indicators feature importance and decision rule were analyzed. With the XGBoost machine learning model for unanticipated DTI prediction, the best F1 score of 0.500 ± 0.102 was obtained on the training set with ten-fold cross-validation. The XGBoost model had the area under the precision recall curve (AUPRC) 0.600 and the area under the receiver operating characteristic curve (AUROC) 0.924 with an F1 value of 0.57 in the test set. XGBoost was an effective machine learning model for unanticipated DTI prediction.

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.

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.

The early diagnosis of skin cancer is an urgent problem in public health, which helps to improve the survival rate of patients. In order to improve the model generalization ability, we propose an ensemble model, which first uses multiple different neural network models to train each model on the training set and then integrates the output of different models to form a rich feature representation to classify skin lesions. The experimental results show that the proposed ensemble model is effective, and its performance is better than the single model, with an accuracy of 89.5%.

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.

针对磁共振(MR)成像具有灰度不均匀、部分容积效应等缺陷,给出一种粗糙集自适应粒度的脑肿瘤MR图像分割方法,从而提高脑肿瘤分割质量.利用粗糙集自适应粒度方法选取最优分割粒度,并用粗糙集模拟目标和背景区域的上下近似,通过优化目标和背景区域的粗糙度,获得MR脑肿瘤图像分割的最佳阈值.粗糙集自适应粒度方法能够较好地提取出脑肿瘤区域.实验结果表明,该方法优于传统粗糙集分割法,且具有一定实用性和灵活性.

膀胱癌的发病呈现增高的趋势,对放射科医生来说,检测和分类膀胱恶性肿瘤是一项耗时较大的工作.近年来,计算机辅助诊断系统的进步以及深度学习(Deep learning)的发展,使其成为医学图像处理的有力工具.文章提出一种基于深度卷积神经网络的膀胱癌MRI图像的优化模型,得到适合膀胱肿瘤MRI图像分级和分期预测的算法,取得较好的预测诊断效果,膀胱肿瘤分级预测准确率93.75％,膀胱肿瘤分期预测准确率98.96％,为膀胱肿瘤的无创预测提供了新的手段.

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.

腺体病变引起的疾病如结肠腺癌、乳腺癌等的发病率逐年增高,病理检查是临床诊断的"金标准",从病理图像中准确分割病灶范围对疾病的诊疗至关重要,然而这是一项费时费力的工作,同时与病理医生的水平与经验有关.近年来,计算机辅助诊断系统和深度学习(Deep learning)在医学图像处理领域快速发展并得到广泛应用,为进一步减轻医生的工作负担,采用经典神经网络对腺体病理图像进行区域分割,并使其能够适用于更加广泛的腺体分割,在腺体病理图像中取得较好的分割效果,为辅助早期诊断及减小误诊概率提供可能.

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.

N-(4-hydroxyphenyl)retinamide (4-HPR or fenretinide), which is a synthetic analog of all‑trans retinoic acid (ATRA), effectively inhibits the growth of several types of tumor cells; however, its molecular mechanism remains unclear. We found that 4‑HPR altered the morphology of human liver cancer HepG2 cells and also inhibited their proliferation and suppressed the colony formation in a dose‑ and time‑dependent manner. A wound healing assay revealed that 4‑HPR significantly hindered HepG2 cell migration, and that this was accompanied by the phosphorylation of p38‑MAPK (mitogen‑activated protein kinase). Mechanistically, the MAPK‑specific inhibitor SB203580 attenuated the inhibitory effects of 4‑HPR on the migration of HepG2 cells. Moreover, we also observed that 4‑HPR inhibited the activation and expression of myosin light chain kinase (MLCK) in HepG2 cells. Simultaneously, 4‑HPR lowered the expression of F‑actin and promoted the expression of E‑cadherin. ML‑7, a selective inhibitor of MLCK, significantly inhibited the migration of HepG2 cells while increasing the phosphorylation of p38‑MAPK and the expression of E‑cadherin, and decreasing the activation of MLCK and the expression of F‑actin. In conclusion, 4‑HPR inhibited the proliferation and migration of HepG2 cells, and p38‑MAPK plays an important role in regulating these 4‑HPR effects by reducing the activation of MLCK. The present study suggests that 4‑HPR may be a potent antimetastatic agent.

Informative gene selection is an essential step to perform tumor classification with large scale gene expression profiles .However ,it is difficult to select informative genes related to tumor from gene expression profiles because of its characteristics such as high dimensionality and relatively small samples , many noises ,and some of the genes are superfluous and irrelevant .To deal with the challenging problem of finding an informative gene subset with the least number of genes but the highest classification per-formance ,a novel hybrid gene selection algorithm named SUNRS is proposed based on the symmetric un-certainty (SU) and neighborhood rough set (NRS) .Firstly ,the symmetric uncertain index ,which aims to eliminate redundant and irrelevant genes ,is used to select top-ranked genes as the candidate gene sub-set .Secondly ,the neighborhood rough set reduction algorithm is used to obtain the target gene subset by optimizing the candidate gene subset .Experimental results show that the proposed algorithm can obtain higher classification accuracy with less informative gene ,which not only improves the generalization per-formance of the algorithm ,but also enhances the time efficiency .

For most of the cells, water permeability and plasma membrane properties play a vital role in the optimal protocol for successful cryopreservation. Measuring the water permeability of cells during subzero temperature is essential. So far, there is no perfect segmentation technique to be used for the image processing task on subzero temperature accurately. The ice formation and variable background during freezing posed a significant challenge for most of the conventional segmentation algorithms. Thus, a robust and accurate segmentation approach that can accurately extract cells from extracellular ice that surrounding the cell boundary is needed. Therefore, we propose a convolutional neural network (CNN) architecture similar to U-Net but differs from those conventionally used in computer vision to extract all the cell boundaries as they shrank in the engulfing ice. The images used was obtained from the cryo-stage microscope, and the data was validated using the Hausdorff distance, means ± standard deviation for different methods of segmentation result using the CNN model. The experimental results prove that the typical CNN model extracts cell borders contour from the background in its subzero state more coherent and effective as compared to other traditional segmentation approaches.

Brain tumor segmentation on MR images has significant clinical meaning due to glioblastomas which are the most lethal form of these tumors. Compared to manual segmentation, automatic segmentation system is superior in timesaving and experience-insensitivity for doctors during clinical practice. However, its inherent contradiction is not addressed yet. i.e. imbalance of multi-class of different brain tissues. As such, we proposed a multi-class focal loss to make the loss function emphasis on bad-classified voxels in MR images. Our experiments based on the 3D UNet model proved that this method can significantly improve labeling and segmentation accuracy as compared to other loss layers.

It remains a great challenge to achieve sufficient cancer classification accuracy with the entire set of genes, due to the high dimensions, small sample size, and big noise of gene expression data. We thus proposed a hybrid gene selection method, Information Gain-Support Vector Machine (IG-SVM) in this study. IG was initially employed to filter irrelevant and redundant genes. Then, further removal of redundant genes was performed using SVM to eliminate the noise in the datasets more effectively. Finally, the informative genes selected by IG-SVM served as the input for the LIBSVM classifier. Compared to other related algorithms, IG-SVM showed the highest classification accuracy and superior performance as evaluated using five cancer gene expression datasets based on a few selected genes. As an example, IG-SVM achieved a classification accuracy of 90.32% for colon cancer, which is difficult to be accurately classified, only based on three genes including CSRP1, MYL9, and GUCA2B.

移动互联网、大数据、云计算等新兴信息技术的发展为医学教育信息化改革提供了新的契机.该文通过分析国内医学教育发展的现状,阐述了智慧课堂教学模式在医学教育中的优势,并立足"互联网+"背景下构建医学智慧课堂,即利用"互联网+"思维和大数据、云计算等先进的信息技术打造智慧型课堂.以期实现实现教学环境和教学模式的变革与创新,从根本上促进信息技术与传统医学教育教学的深度融合,推动医学信息化进程,有助于医学创新型人才的培养.

在大数据视角下对大学生心理健康促进模式研究是心理学研究的一个重要方面.在大数据领域一般对数据采用数据采集、数据分析、数据重构和数据挖掘四个方面来进行,以此建立起基于大数据"四层"结构的大学生心理健康促进模式.采用数据挖掘算法理论构建心理健康预测模型,为大学生心理健康教育提供决策依据.