To further accelerate Magnetic Resonance Imaging (MRI), reducing the acquisition of K-space information can be an effective approach. However, this approach can lead to degradation of MR image quality and the generation of artifacts. Therefore, post-processing of undersampled MR images is an essential part of clinical analysis. In this study, we proposed a method of reconstruction that combines an optimization algorithm with a convolutional neural network (CNN). Our method first performs an initial reconstruction of undersampled MR data using the efficient mathematical computational power of the optimization algorithm. Then we further improve the image quality by designing a lightweight CNN. The method requires only a few samples in the training process to obtain satisfactory reconstruction results. By comparing with other MRI reconstruction methods, we demonstrate better overall reconstruction performance in terms of PSNR and SSIM. Our method has the ability to map between undersampled MR images and fully sampled images, enabling it to perform well in reconstructing images.

为了形象直观表达磁共振成像原理,本教学团队经过多年的教学积累,创造性采用了"从宏观到微观,再从微观到宏观"的设计思想,利用数理模型和时空尺度转换,借助宏观场景串接微观要素进行表达,将可互动的宏观操作与微观状态改变直接关联起来,形成了磁共振成像原理"全过程可视化".本仿真实验既生动形象又不失科学性,学生自主发挥空间大,成就感强.对生物学工程等专业实验教学及医院相关科室人员技能培训都发挥了积极作用.

Background and Objective: Compressed sensing has been extensively studied as an advanced technique for fast MR image reconstruction. Current reconstruction algorithms often use total variation as the regular-ization term. Traditional total variation can easily lead to a staircase effect because it only pays attention to the variational information of the horizontal and vertical subbands. Methods: In this paper, we propose a novel algorithm to reduce the staircase effect by increasing the variational information of the two diagonal subbands, which named Double Total Variation (DTV). We optimize the conjugate gradient algorithm by Improved Adaptive Moment Estimation (IADAM) as the solution algorithm.Results: MR images of three body parts (head, knee and ankle) were used for simulations under different acceleration factor conditions. The conjugate gradient and fast conjugate gradient series algorithms were selected for comparison experiments. The results showed that the improved adaptive moment estimation conjugate gradient combined with DTV achieves the best reconstruction performance, therefore proved the superiority of DTV. After that, 64 different MR images of the three body parts were further simulated and the results demonstrated the general superiority from the proposed algorithm.Conclusions: The results of this study support that the proposed method may facilitate the development of the research field of image reconstruction algorithms and provide ideas for other algorithmic improve-ments.(c) 2023 Elsevier B.V. All rights reserved.

目的 探究自监督学习网络Patch2Self在多层同时扫描扩散张量成像(Multiband SENSE Diffusion Tensor Imaging,MB SENSE DTI)中降噪的可行性.方法 招募24名健康志愿在3T MRI上进行MB SENSE(MB factor 4)DTI扫描.利用自监督学习网络Patch2Self、非局部均值法(Non-Local Means,NLM)和局部主成分分析法(Local Principal Component Analysis,LPCA)给MB SENSE DTI去噪.使用峰值噪声比(Peak Signal to Noise Ratio,PSNR)、结构相似度(Structural Similarity,SSIM)进行客观评价;由放射科医生对图像噪声、对比度、整体质量以及各向异性分数(Fractional anisotropy,FA)图的整体质量进行主观评价.结果 在PSNR方面,Patch2Self优于NLM,但低于LPCA(P<0.05);在SSIM方面,Patch2Self优于NLM和LPCA(P<0.05);在噪声方面,Patch2Self明显优于NLM(P<0.05),而Patch2Self与LPCA之间图像质量比较无统计学差异(P>0.05);在对比度、整体质量和FA图的整体质量方面,Patch2Self优于NLM和LPCA(P<0.05).结论 自监督学习网络Patch2Self可以很好地完成去噪、保留脑部组织结构以及提高图像质量.

针对生物医学工程专业内容广、知识"碎片化",学生对专业缺乏系统认知的问题,建设相应的课程,是生物医学工程人才培养亟待解决的问题.团队依托南京医科大学丰富的医学资源,遵循生物医学工程"医工结合,贴近临床、注重创新"的发展思路,构建了《生物医学工程创新设计》课程.课程结合前沿热点、开放性项目提高挑战,无缝链接课程思政.开课以来,学生的学习兴趣显著提升,依托本课程孵化的项目,医工融合度高,在学科竞赛中表现优异.

Background: Low-resolution magnetic resonance imaging (MRI) has high imaging speed, but the image details cannot meet the needs of clinical diagnosis. More and more researchers are interested in neural network-based reconstruction methods. How to effectively process the super-resolution reconstruction of the low-resolution images has become highly valuable in clinical applications. Methods: We introduced Super-Resolution Convolution Neural Network (SRCNN) into the reconstruction of magnetic resonance images. The SRCNN consists of three layers, the image feature extraction layer, the nonlinear mapping layer, and the reconstruction layer. For the feature extraction layer, a multi-scale feature extraction (MFE) method was used to extract the features in different scales by involving three different levels of views, which is superior to the original feature extraction in views with fixed size. Compared with the original feature extraction only in fixed size views, we used three different levels of views to extract the features of different scales. This MFE could also be combined with residual learning to improve the performance of MRI super-resolution reconstruction. The proposed network is an end-to-end architecture. Therefore, no manual intervention or multi-stage calculation is required in practical applications. The structure of the network is extremely simple by omitting the fully connected layers and the pooling layers from traditional Convolution Neural Network. Results and Conclusions: After comparative experiments, the effectiveness of the MFE SRCNN-based network in super-resolution reconstruction of MR images has been greatly improved. The performance is significantly improved in terms of evaluation indexes peak signal-to-noise ratio and structural similarity index measure, and the detail recovery of images is also improved.

As an advanced technique, compressed sensing has been used for rapid magnetic resonance imaging in recent years, Two-step Iterative Shrinkage Thresholding Algorithm (TwIST) is a popular algorithm based on Iterative Thresholding Shrinkage Algorithm (ISTA) for fast MR image reconstruction. However TwIST algorithms cannot dynamically adjust shrinkage factor according to the degree of convergence. So it is difficult to balance speed and efficiency. In this paper, we proposed an algorithm which can dynamically adjust the shrinkage factor to rebalance the fidelity item and regular item during TwIST iterative process. The shrinkage factor adjusting is judged by the previous reconstructed results throughout the iteration cycle. It can greatly accelerate the iterative convergence while ensuring convergence accuracy. We used MR images with 2 body parts and different sampling rates to simulate, the results proved that the proposed algorithm have a faster convergence rate and better reconstruction performance. We also used 60 MR images of different body parts for further simulation, and the results proved the universal superiority of the proposed algorithm.

目的 足底压力数据可为下肢关节性疾病的康复过程进行评估,基于此设计了足底压力信号采集分析与评定系统.方法 系统分为数据采集模块和数据接收、处理模块,分析结果采用可移动端和电脑端两种模式显示,可移动端以OLED屏显示足底压力中心(COP)轨迹结果值,电脑端利用LabVIEW和Matlab软件联合编程,并以图形化的界面进行足底压力实时动态显示.结果 通过对试验者进行模拟测试,该系统可以获得准确的测试结果.结论 该系统具有一定的可靠性和稳定性,后期通过增加对压力数据的分析算法,来获取其它有意义的数据指标.

Convolutional neural networks (CNNs) are effective models for image classification and recognition. Gradient descent optimization (GD) is the basic algorithm for CNN model optimization. Since GD appeared, a series of improved algorithms have been derived. Among these algorithms, adaptive moment estimation (Adam) has been widely recognized. However, local changes are ignored in Adam to some extent. In this paper, we introduce an adaptive learning rate factor based on current and recent gradients. According to this factor, we can dynamically adjust the learning rate of each independent parameter to adaptively adjust the global convergence process. We use the factor to adjust the learning rate for each parameter. The convergence of the proposed algorithm is proven by using the regret bound approach of the online learning framework. In the experimental section, comparisons are conducted between the proposed algorithm and other existing algorithms, such as AdaGrad, RMSprop, Adam, diffGrad, and AdaHMG, on test functions and the MNIST dataset. The results show that Adam and RMSprop combined with our algorithm can not only find the global minimum faster in the experiment using the test function but also have a better convergence curve and higher test set accuracy in experiments using datasets. Our algorithm is a supplement to the existing gradient descent algorithms, which can be combined with many other existing gradient descent algorithms to improve the efficiency of iteration, speed up the convergence of the cost function, and improve the final recognition rate.

本文从自身教学实践出发,就人体解剖学课程中视觉传导通路的难、重点和突破点进行了剖析、梳理.用"反射弧"抛砖引玉,引导学生在框架上理解视觉传导通路与反射弧的前半程有着对应关系——视觉传导通路起于视觉感受器,止于视觉中枢;视觉神经冲动上行传导过程中遵循"三级传导,二级交叉"的规律,并以单侧眼球视野光线的投射与视网膜的对应关系剖析"视神经""视交叉""视束",以此为基础,进而剖析视觉传导通路不同部位受损时出现的视野缺失情况.本次课程用"反射弧"作为"故事开头",将"视神经""视交叉""视束"作为"故事高潮",用"传导损伤引起视野障碍"作为"故事结尾",能帮助学生在理解的基础上掌握视觉传导通路,为学习后续相关临床诊疗知识夯实解剖基础.

在新工科多学科交叉融合的理念下,医科院校生物医学工程专业的人才培养,需要高度契合医疗卫生行业人才需求的发展趋势.南京医科大学生物医学工程专业充分发挥医科院校临床资源优势,以学生发展为中心,建设了明显有别于其他工科及综合型院校的"临床导向型"创新创业人才培养目标,通过打造"医工复合"师资平台、完善"医工融合"型课程平台、深化"医工交叉"型实践平台、推动"协同创新"型转化平台,探索三维模块化创新创业能力培养体系,提高学生的综合素质.人才培养卓有成效,学生"双创"成果丰硕.

骨关节炎是中老年人群最常见的关节疾病,该疾病及其并发症占据了全球10％的医疗问题.其中膝关节骨关节炎最为严重,致残风险极高.尽早发现并介入治疗对于缓解其症状,减少其危害有着至关重要的意义.首先收集了大量膝关节DR影像数据,对获得的数据进行多种纹理特征和融合特征的提取,将提取的特征向量进行各种组合作为输入训练SVM模型,使用网格搜索法进行了进行参数寻优.训练完成的模型在测试集上的准确率最高可以达到84.29％,具有良好的智能分类诊断性能.使用训练完的SVM模型,可以有效的对膝关节骨性关节炎进行分级,辅助医生进行诊断,对膝关节骨关节炎的早期诊断,尽早介入治疗有着重要意义.

颅底界于颅腔底部与眼眶、鼻腔、蝶窦、筛窦、鼻咽腔及颞下窝顶部之间,骨壁厚薄不一,有众多的孔、管、裂、缝等重要结构,是脑、脑神经、脑血管和特殊感受器集中的部位[1].医学类本科院校《系统解剖学》课程教学大纲明确指明,颅底解剖包括颅底内面解剖和颅底外面解剖,是临床专业学生必须掌握的教学内容.

To accelerate the scanning speed of magnetic resonance imaging (MRI) and improve the quality of magnetic resonance (MR) image reconstruction, a fast MRI technology based on compressed sensing is proposed. Nesterov's accelerated gradient descent (NAG) algorithm uses Nesterov acceleration to optimize the gradient descent (GD) method. However, this form of acceleration factor uses a fixed iteration curve update and can not adapt to different iteration processes. A generalized Nesterov acceleration concept is proposed. Combining the total variation model, a generalized Nesterov accelerated conjugate gradient based on total variation (GNACG_TV) algorithm is proposed. It extends the acceleration factor in a generalized manner, introducing the Frobenius norm of the objective function as a parameter, so that the acceleration factor is related not only to the number of iterations but also to the iteration process and guarantees the convergence of the iterative process. Experiments on three MR images (abdomen, head, and ankles) at different sampling ratios show that the proposed GNACG_TV algorithm compares favorably with conjugate gradient (CG), conjugate gradient based on total variation (CG_TV), Nesterov accelerated conjugate gradient based on total variation (NACG_TV), and conjugate gradient based on adaptive moment estimation (ADAMCG) algorithms in the MSE, PSNR and SSIM exhibit better performance and robustness in denoising performance for the proposed algorithm. Comparing with the result of qualitative and quantitative analysis, it was concluded that the proposed method can better reconstruct under-sampled MR images than other 4 methods. GNACG_TV can further improve the convergence speed based on Nesterov acceleration and get better reconstruction performance.

设计一套磁定位数据采集系统,使用永磁定位技术完成空间内点的定位,并在实际测试中计算定位结果的误差,从而实现步态参数的采集.设计步态参数采集系统中关键部分磁传感器的外围电路,对获取的信号进行放大、滤波、模数变换等信号处理,上位机通过蓝牙串口读取数据.通过数据采集系统采集数据距离,进行3次测试实验.由预实验得到在8～12 cm的距离为电压与距离的线性部分,将小磁体放置于传感器轴方向上,在小磁体位于三轴±6～12 cm内每隔0.5 cm上,每次放置后进行一次定位获取,在上位机读取定位数据,与标准距离相比X轴最大误差出现在负方向6 cm与7 cm处,误差为1.7 mm,线性部分误差在1 mm以内;Y轴最大误差出现在负方向7 cm处,误差为1.65 mm,线性部分误差在1.2 mm内;Z轴最大误差出现在负方向6 cm处,误差为1.8 mm,线性部分误差在1.3 mm内.结果 表明,研究使用的磁定位方法对于距离的测量较为精准,可以用于医学测量领域.研究所采取的磁定位法使用单个磁传感器对单个永磁体进行定位,永磁体尺寸仅为直径2 mm、长度3 mm,尺寸极小,测量时产生的运动阻碍极低.且测试结果较为精准,能够满足医学上一般进行的步态数据获取.相对于其他方法,研究对患者步行时障碍较小、对人体安全性较高、易于集成,适合用于对下肢运动功能障碍的患者进行步态参数的采集,制定下一步康复治疗计划.

Background: Infected bone defect (IBD) is still a great challenge in orthopaedic clinic. Scaffolds with dual-functional biological properties for antibacterial and bone regeneration may be a reasonable candidate for IBD repair. This study aims to develop a PCLIPDA/AgNPs scaffold with both antibacterial and bone regeneration ability for IBD repair. Materials and Methods: Porous polycaprolactone (PCL) scaffolds were prepared by 3D printing technology, with the enrichment of nano Argentum (nAg) achieved by modified bionic surface using self-assembly mussel-inspired polydopamine (PDA). The biomechanical strength, bone regeneration and anti-infection performance of the PCLIPDA/AgNPs scaffold, cultured in vitro and implanted in vivo, were examined to evaluate its suitability in infected bone repair. Results: Results demonstrated that the obtained PDA/PCL composite scaffolds and nAg/PDA/PCL composite scaffolds showed remarkable modification of surface with micro-nano self-assembly PDA and nAg particles observed, compared to PCL scaffold. No significant difference of scaffold density and compressive strength observed between composite scaffolds and PCL scaffolds. In vitro study showed that nAg/PDA/PCL scaffolds could decrease bacterial adhesion and reproduction. Meanwhile, nAg/PDA/PCL scaffolds showed a multiple action in the promotion of bone regeneration propriety by rBMSCs cell accommodation, attachment, proliferation. Furthermore, after 8 weeks of in vivo implantation, nAg/PDA/PCL scaffolds showed a superior performance in mineralized bone tissue accumulation, compared to PCL scaffolds. Conclusion: These findings suggest that PDA surface modification and drug enrichment can be a highly efficient and reliable method, which may improve the antibacterial and bone regeneration performance of 3D printed PCL scaffold. The nAg/PDA/PCL scaffold with bi-lineage bioactivity is a candidate for treating infected bone defect repair. (C) 2019 Published by Elsevier Ltd.

To reduce the magnetic resonance imaging (MRI) data acquisition time and improve the MR image reconstruction performance, reconstruction algorithms based on the iterative shrinkage thresholding algorithm (ISTA) are widely used. However, these traditional algorithms use global threshold shrinkage, which is not efficient. In this paper, a novel algorithm based on local threshold shrinkage, which is called the local shrinkage thresholding algorithm (LSTA), was proposed. The LSTA can shrink differently for different elements from the residual matrix to adjust the shrinkage speed for each element of the image during the iterative process. Then, by taking advantage of the sparser characteristics of the curvelet transform, the LSTA combined with the curvelet transform (CLSTA) can make the construction process more efficient. Finally, compared with ISTA, the generalized thresholding iterative algorithm (GTIA) and the fast iterative shrinkage threshold algorithm (FISTA), when analysing human (brain and cervical) MR images, a conclusion can be drawn that the proposed method has better reconstruction performance in terms of the mean square error (MSE), the peak signal to noise ratio (PNSR), the structural similarity index measure (SSIM), the normalized mutual information (NMI), the transferred edge information (TEI) and the number of iterations. The proposed method can better maintain the detailed information of the reconstructed images and effectively decrease the blurring of the images edges.

肿瘤热疗(hyperthermia)是利用肿瘤组织对温度敏感性高于正常组织的性质,即人体正常细胞在42.5～43℃下不会受到损伤,但大部分肿瘤细胞在该温度下会被诱导进入凋亡过程.临床上应用超声、微波或红外等作为加热源,加热并杀死肿瘤组织而使得正常组织基本不受损伤.但是对于如何精确测量肿瘤热疗的温度从而控制热疗剂量仍然是一个难题.本文综述了目前肿瘤热疗过程中电阻抗断层成像(ectrical impedance tomograph,EIT)测温、红外热图引导技术、微波辐射测温法、超声无损测温、磁共振成像测温(magnetic resonance imaging,MRI)等无损测温方法及其研究现状,展望了如何有效精确测量肿瘤热疗时的温度,为控制肿瘤热疗的热剂量提供参考,以期在不伤害正常组织的前提下,使肿瘤组织产生不可逆的损伤.

目的 该文设计了基于永磁体标记的胶囊内镜旋转测量定位模型,为实现人体内胶囊内镜的定位奠定理论基础.方法 根据Biot-Savart定律及环形电流的空间磁场分布模型,建立了全新的旋转定位模型;采用GF708型单轴磁传感器对磁场数据进行获取,并对旋转测量的定位数据进行求解.结果 永磁体位于平面内随机位置时定位结果显示,磁体距离圆心r平均误差为0.19 cm,永磁体所在半径与正北方向的偏转角的平均误差为0.019 rad,永磁体轴向同所在半径所成夹角α的平均误差为0.049 rad,实验结果证明该设计切实可行.结论 旋转检测具有复杂度低、精度高、成本低等优点,对人体内胶囊内镜的定位具有潜在的应用价值.