基于织物电极的非接触便携式睡眠心电监测系统设计

目的 为通过心电信号检测睡眠分区及睡眠呼吸障碍等疾病,设计一种基于织物电极的心电监测系统.方法 使用医用级导电织物电极代替传统电极,可在不与人体接触的情况下实时、准确地采集生理电信号,对被测者进行长时间心电监测.使用ARM11嵌入式系统代替医用主机进行数据处理、波形显示等.采用无线宽带设备代替串口线与预定主机进行通信.结果 该系统可有效降低被测者的不适感,准确检测、处理、记录大量心电数据并通过无线网络实时进行远距离数据交换.结论 该系统使用方便,兼顾可靠性、安全性及舒适性,适用于睡眠分析等长时间心电信号监测.     

一种模拟视觉机制的图像分割模型

提出一个小波域多尺度马尔柯夫随机场模型用于模拟视觉系统在图像分割中的若干功能。针对人类视觉系统具有特征检测器、等级层次性、双向连接性、学习机制等功能,对输入场景,该模型用小波变换提供该场景图像的稀疏表示,模拟特征检测器功能;用金字塔结构模拟等级层次性;用两类信息流模拟双向连接性,分别刻画自底向上的输入图像特征提取过程以及自顶向下的反馈过程;用迭代过程模拟学习机制;采用多尺度马尔柯夫随机场模型实现图像分割。实验表明,该模型对真实采集到的不同类型的生物医学图像进行分割,取得优于一些传统分割算法的结果。     

Potential for plasmid DNAs as vaccines for the new millennium

The advent of new technology and the unmet needs of old and new epidemics of infectious diseases have stimulated a new era of vaccinology. One of the most novel approaches employs plasmid DNA engineered to express one or more genes of the pathogen in mammalian cells. Plasmids may also express cytokine or costimulatory molecules to ‘direct’ the immune response and/or express altered forms of the antigen to direct it to a specific intracellular compartment or a specific extracellular receptor. The quality of immune responses generated by DNA vaccines in animals has previously only been equaled by live attenuated viral vaccines. The immune stimulating activity of DNA vaccines, combined with their versatility, suggests vast potential for these vaccines.     

Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room

The fine-grained localization of clinicians in the operating room (OR) is a key component to design the new generation of OR support systems. Computer vision models for person pixel-based segmentation and body-keypoints detection are needed to better understand the clinical activities and the spatial layout of the OR. This is challenging, not only because OR images are very different from traditional vision datasets, but also because data and annotations are hard to collect and generate in the OR due to privacy concerns. To address these concerns, we first study how joint person pose estimation and instance segmentation can be performed on low resolutions images with downsampling factors from 1x to 12x. Second, to address the domain shift and the lack of annotations, we propose a novel unsupervised domain adaptation method, called AdaptOR, to adapt a model from an in-the-wild labeled source domain to a statistically different unlabeled target domain. We propose to exploit explicit geometric constraints on the different augmentations of the unlabeled target domain image to generate accurate pseudo labels and use these pseudo labels to train the model on high- and low-resolution OR images in a self-training framework. Furthermore, we propose disentangled feature normalization to handle the statistically different source and target domain data. Extensive experimental results with detailed ablation studies on the two OR datasets MVOR+ and TUM-OR-test show the effectiveness of our approach against strongly constructed baselines, especially on the low-resolution privacy-preserving OR images. Finally, we show the generality of our method as a semi-supervised learning (SSL) method on the large-scale COCO dataset, where we achieve comparable results with as few as 1% of labeled supervision against a model trained with 100% labeled supervision. Code is available at https://github.com/CAMMA-public/HPE-AdaptOR.     

Comparative validation of multi-instance instrument segmentation in endoscopy: Results of the ROBUST-MIS 2019 challenge

Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and robotic-assisted interventions. While numerous methods for detecting, segmenting and tracking of medical instruments based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, the reliable performance of state-of-the-art methods when run on challenging images (e.g. in the presence of blood, smoke or motion artifacts). Secondly, generalization; algorithms trained for a specific intervention in a specific hospital should generalize to other interventions or institutions.In an effort to promote solutions for these limitations, we organized the Robust Medical Instrument Segmentation (ROBUST-MIS) challenge as an international benchmarking competition with a specific focus on the robustness and generalization capabilities of algorithms. For the first time in the field of endoscopic image processing, our challenge included a task on binary segmentation and also addressed multi-instance detection and segmentation. The challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures from three different types of surgery. The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap. While the average detection and segmentation quality of the best-performing algorithms is high, future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts).     

A fetal mouse model of ventricular non-compaction using retinoic acid

ObjectiveTo develop a fetal mouse model of non-compaction of ventricular myocardium (NVM) using All-trans retinoic acid (ATRA).MethodsPregnant mice were divided into blank control group, dimethyl sulfoxide (DMSO) control group and ATRA group. The pregnant mice at 8.5 days after pregnancy were given 70 mg/kg ATRA in DMSO to induce fetal mouse model of NVM in ATRA group. All the hearts were acquired and sliced in short axis from the neonatal mice sacrificed after delivery. Pathological changes were visualized under 40- and 100-fold magnification with Hematoxylin-eosin (HE) staining at different ventricular levels. The criteria for pathological diagnosis of classical NVM were: prominent trabeculations on the endocardial surface and deep intertrabecular recesses communicating with the ventricular cavity and the thickness ratio of non-compacted layer (N) to compact myocardium layer (C) N/C > 1.4. Analysis of variance (ANOVA) and least significant difference (LSD) were used to analyze the differences of three groups, with P < 0.05 considered as significant.ResultsThe typical characteristics of NVM histopathological findings of ATRA fetal mouse were confirmed: compared to the hearts of blank control group (n = 20) and DMSO control group (n = 15), all the hearts of ATRA group (n = 17) showed the obviously thinner compacted layer and the much thicker non-compacted layer. The N/C ratio of left ventricles (LVs) in ATRA group was 2.735 ± 1.634, higher than those in DMSO control group 0.178 ± 0.119 and blank control group 0.195 ± 0.118 with significant difference (F = 32.550, P <0. 0001); N/C ratios of right ventricles (RVs) in the ATRA group were (6.068 ± 4.394), higher than those in the DMSO control group 0.459 ± 0.24 and in the blank control group 0.248 ± 0.182 with significant difference (F = 20.069, P <0.0001). LSD of LVs and RVs showed a significant difference between ATRA and blank control group (P < 0.0001), and between ATRA and DMSO control group (P < 0.0001). LSD showed no significant difference in two control groups of LVs (P = 0.963) and of RVs (P = 0.848) .ConclusionExcess ATRA could be used to induce NVM of fetal mice heart. This animal model might provide a platform for fundamental research of NVM pathogenesis and potential targeting treatment.     

Extracting keyframes of breast ultrasound video using deep reinforcement learning

Ultrasound (US) plays a vital role in breast cancer screening, especially for women with dense breasts. Common practice requires a sonographer to recognize key diagnostic features of a lesion and record a single or several representative frames during the dynamic scanning before performing the diagnosis. However, existing computer-aided diagnosis tools often focus on the final diagnosis process while neglecting the influence of the keyframe selection. Moreover, the lesions could have highly-irregular shapes, varying sizes, and locations during the scanning. The recognition of diagnostic characteristics associated with the lesions is challenging and also faces severe class imbalance. To address these, we proposed a reinforcement learning-based framework that can automatically extract keyframes from breast US videos of unfixed length. It is equipped with a detection-based nodule filtering module and a novel reward mechanism that can integrate anatomical and diagnostic features of the lesions into keyframe searching. A simple yet effective loss function was also designed to alleviate the class imbalance issue. Extensive experiments illustrate that the proposed framework can benefit from both innovations and is able to generate representative keyframe sequences in various screening conditions.