摘要：【中文】本发明涉及一种多种形态医疗影像数据标注方法及系统，包括：接收用户上传的图片，根据预设的图片格式核对格式是否正确；若正确则上传图片，若不正确则提醒用户重新上传；提取图片信息与信息库进行匹配，判断图片是否有标注或属性信息；设置标注图片的权限；根据疾病种类为用户提供标注工具箱；接收用户对图片进行的标注信息，并将标注信息上传存储；提取同一级别用户对所述图片的标注信息并进行对比，判断同一级别用户的标注信息是否有差异，若无差异则生成最终标注结果，若有差异则交由下一级用户进步标注。本发明可以使用不同的标注工具对图像进行标注，满足多种形态的医疗影像的标注需求，并采用分级标注的流程，提高对图片标注的准确性。 【EN】The invention relates to a method and a system for labeling medical image data in various forms, which comprise the following steps: receiving a picture uploaded by a user, and checking whether the format is correct according to a preset picture format; if the picture is correct, uploading the picture, and if the picture is incorrect, reminding the user to upload again; extracting picture information to match with an information base, and judging whether the picture has label or attribute information; setting the authority of marking the picture; providing a labeling tool box for a user according to the disease types; receiving the marking information of the user on the picture, and uploading and storing the marking information; and extracting the labeling information of the users at the same level on the pictures, comparing the labeling information, judging whether the labeling information of the users at the same level is different, if not, generating a final labeling result, and if so, submitting the final labeling result to the next user for further labeling. The invention can label the image by using different labeling tools, meets the labeling requirements of medical images in various forms, and improves the accuracy of labeling the image by adopting a hierarchical labeling process.

摘要：【中文】本发明公开了一种系统故障定位方法，包括：建立节点‑故障‑测试相关矩阵；基于待测系统的几何拓扑模型和测试结果，并结合待测系统监测传感器故障检测率与建立的节相关矩阵，计算待测系统的单点报警概率矩阵，进而建立待测系统的整体报警概率矩阵；计算实时故障观察向量和待测系统的整体报警概率矩阵的马氏距离，按马氏距离的从大到小排序，选取前s个马氏距离值对应的单点故障或者故障组合，按照从大到小原则输出系统故障定位结果。该方法在考虑监测设备故障检测率的基础上，通过衡量实时故障观测向量与待测系统的测试结果的概率空间相似度，实时快速定位系统故障原因，适用于单点故障和多点故障的情况，具有强操作性和高正确性，便于工程实现。 【EN】The invention discloses a system fault positioning method, which comprises the following steps: establishing a node-fault-test correlation matrix; based on a geometric topological model and a test result of the system to be tested, and in combination with the fault detection rate of the monitoring sensor of the system to be tested and the established section correlation matrix, calculating a single-point alarm probability matrix of the system to be tested, and further establishing an integral alarm probability matrix of the system to be tested; and calculating the Mahalanobis distance between the real-time fault observation vector and the overall alarm probability matrix of the system to be tested, sorting the Mahalanobis distances from large to small, selecting single-point faults or fault combinations corresponding to the first s Mahalanobis distance values, and outputting a system fault positioning result according to the principle of large to small. The method is suitable for the conditions of single-point faults and multi-point faults, has strong operability and high correctness and is convenient for engineering realization by measuring the probability spatial similarity between a real-time fault observation vector and a test result of a system to be tested on the basis of considering the fault detection rate of monitoring equipment and quickly positioning the fault reason of the system in real time.