Zhejiang Lab

Zhejiang University

Yu Tian

Jingsong Li

Tianshu Zhou

Peijun Hu

Youtong Fang

Hongtao Wang

Jiabin Liu

Liang Meng

Litian Wang

Ran Xin

Xin Gao

Yuqing Xu

Guangyuan Deng

Bin Liu

Feng Wang

Jun Li

Jing Ma

Shengqiang Chi

Weiguo Chen

Lixin Shi

Zongfeng Yang

Hongyi Ni

Wenchao Xiang

Zhuoxin Li

Baochen Wang

Shiqiang Zhu

Zhenchuan Zhang

Jinnan Hu

Feixiang Song

Yong Shang

Yiwei Gao

A pancreatic postoperative diabetes prediction system based on supervised deep subspace learning. A deep convolutional neural network and the MITK software are used to obtain postoperative residual pancreas area, so as to taken as the region-of-interest. Traditional image radiomics features and deep semantic features are extracted from the residual pancreas area, and a high-dimensional image feature set is constructed. Clinical factors related to diabetes, including pancreatic excision rate, fat and muscle tissue components, demographic information and living habits are extracted, and a clinical feature set is constructed. Based on a supervised deep subspace learning network, image and clinical features are represented and fused in subspace in dimensionality reduction, while a prediction model is trained to mine sensitive features highly relevant to the prediction risk of a patient suffering postoperative diabetes mellitus with a high degree of automation and discriminative accuracy.

Pancreatic postoperative diabetes prediction system based on supervised deep subspace learning

The present disclosure discloses a method and system for automatically and quickly deploying a front-end processor based on gray release. The system includes a user management module, a front-end processor engineering configuration module, a version iteration module and an engineering code version management repository, where the version iteration module is connected with the engineering code version management repository, the user management module and the front-end processor engineering configuration module, a code is obtained through the engineering code version management repository to perform updating or rollback of a current code, an operating permission of the front-end processor is obtained by using the user management module, an engineering configuration parameter is obtained from the front-end processor engineering configuration module for engineering gray release of a plurality of front-end processors, and a task scheduling function therein is called.

Method and system for automatically and quickly deploying front-end processor based on gray release

Disclosed is a page multiplexing method, a page multiplexing device, a storage medium and an electronic apparatus. After obtaining the page frame information of pages to be configured in a client to be developed, a component relational tree corresponding to the plurality of pages can be determined. The component relational tree is compared with a pre-constructed reference relational tree to determine a target tree structure composed of target components from the reference relational tree. Dependencies between target components in the reference relational tree match those in the component relational tree. The component code of the target component used by the developed client is queried to multiplex the component code. The component relational tree corresponding to pages to be developed can be compared with the reference relational tree corresponding to each page included in the developed client to determine the component code that can be multiplexed.

Page multiplexing method, page multiplexing device, storage medium and electronic apparatus

The present disclosure discloses a medical ETL task dispatching method, system and apparatus based on multiple centers. The method includes following steps: step S: testing and verifying ETL tasks; step S: deploying the ETL tasks to a hospital center, and dispatching the ETL tasks to a plurality of executors for execution; step S: screening an executor set meeting resource demands of ETL tasks to be dispatched; step S: calculating a current task load of each executor in the executor set; step S: selecting the executor with a minimum current task load to execute the ETL tasks; and step S: selecting, by the dispatching machine, the ETL tasks from executor active queues according to a priority for execution. The present disclosure selects the most suitable executor by analyzing a serving index as a task to be dispatched on a current dispatching machine.

Medical ETL task dispatching method, system and apparatus based on multiple centers

Provided are a system and a method for displaying a high-resolution liver cancer pathological image based on an image pyramid. The system includes a data source processing module and an image display module. The data source processing module is configured to acquire original images in various states, process the original images, acquire an image pyramid, name image blocks in the image pyramid, and store the image blocks in a folder set for the image pyramid in a server. The image display module is configured to acquire the image blocks in the folder set for the image pyramid in the server, acquire the image blocks according to a user's request, and splice and display the image blocks in an image display area. For the spliced image blocks, enlargement, reduction and translation operations are supported.

System and method for displaying high-resolution liver cancer pathological image based on image pyramid

The present application discloses a label-free adaptive CT super-resolution reconstruction method, device and system based on a generative network, which comprises the following modules: an acquisition module configured for acquiring low-resolution original CT image data; a preprocessing module configured for performing super-resolution reconstruction on original CT images based on total variation to obtain an initial value; and a super-resolution reconstruction module configured for performing high-resolution reconstruction on the initial value. According to the present application, a parameter fine-tuning method is adopted, and a CT reconstruction network which is not suitable for a certain patient is adjusted into a network which is suitable for the patient's situation on the premise of not using a large number of data sets for training; only the low-resolution CT data of the patient is used in this process, and the corresponding high-resolution CT data is not needed as a label.

Label-free adaptive CT super-resolution reconstruction method, system and device based on generative network

The present disclosure discloses a general speech enhancement method and apparatus using multi-source auxiliary information. The method includes following steps: S: building a training data set; S: using the training data set to learn network parameters of a model, and building a speech enhancement model; S: building a sound source information database in a pre-collection or on-site collection mode; S: acquiring an input of the speech enhancement model; and S: taking a noisy original signal as a main input of the speech enhancement model, taking auxiliary sound signals of a target source group and auxiliary sound signals of an interference source group as side inputs of the speech enhancement model for speech enhancement, and obtaining an enhanced speech signal.

General speech enhancement method and apparatus using multi-source auxiliary information

The present disclosure discloses a multi-component abstract association and fusion method and apparatus in page design. The method includes the following steps: step S: a construction demand is acquired, and the construction demand is analyzed through a speech recognition method to obtain a natural language text; step S: an abstract model is constructed by predefining a component library, a rule library and a relationship library, and the abstract model performs components fusion to obtain a JSON structure of a fused component; step S: the JSON structure of the fused component is escaped into a virtual DOM by using a rendering function, and attributes and events of a virtual DOM node are mapped to obtain a fused component drawing result; and step S: a real DOM structure is created and interpolated into a real DOM node, so as to realize display of the fused component on a view.

Multi-component abstract association and fusion method and apparatus in page design

Disclosed is an image denoising method and apparatus based on wavelet high-frequency channel synthesis. Image data are expanded to a plurality of frequency-domain channels, a plurality of 'less-noise' channels and a plurality of “more-noise” channels are grouped through a noise-sort algorithm, and a denoising submodule and a synthesis submodule based on style transfer are combined to form a generative network. A discriminative network is established to add a constraint to the global loss function. After iteratively training the GAN model described above, the denoised image data can be obtained through wavelet inverse transformation. The disclosed algorithm can effectively solve the problem of “blurring” and “loss of details” introduced by traditional filtering or CNN-based deep learning methods, which is especially suitable for noise-overwhelmed image data or high dimensional image data.

Image denoising method and apparatus based on wavelet high-frequency channel synthesis

The present application discloses a system and a device for functional connectivity matrix processing based on feature selection using a filtering method, which comprises the following steps: acquiring a preprocessed resting state brain functional magnetic resonance image of a subject; extracting time series; calculating a Pearson correlation coefficient to obtain a Pearson correlation coefficient matrix; vectorizing the Pearson correlation coefficient matrix; calculating quantitative correlation indices using a filtering method, and selecting a quantitative correlation index based on a preset threshold; performing weighting processing a selected functional connectivity feature by using the corresponding quantitative correlation index with high correlation with a disease diagnosis result to obtain a functional connectivity matrix; and obtaining a prediction result from the functional connectivity matrix.

Functional connectivity matrix processing system and device based on feature selection using filtering method

Disclosed is a method and an apparatus NER-orientated Chinese clinical text data augmentation, and unannotated data and annotated data of label linearization processing through data preprocessing. A concealed part is predicted based on retained information by using the unannotated data and concealing part of information in text, and meanwhile an entity word-level discrimination task is introduced for pre-training of a span-based language model; and a plurality of decoding mechanisms are introduced in a fine-tune stage, a relationship between a text vector and text data is obtained based on the pre-trained span-based language model, linearized data with entity labels is converted into the text vector, and text generation is performed through forward decoding and reverse decoding in a prediction stage of a text generation model to obtain enhanced data with annotation information.

Method and apparatus of NER-oriented chinese clinical text data augmentation

Discloses a method and an apparatus for visual construction of a knowledge graph system. In the present disclosure, data permission of a distributed client is determined through a central server. The central server obtains a master template of a knowledge graph system and sends it to the distributed client. The distributed client receives a natural language inputted by a user and parses to generate an abstract syntax tree. The user completes customization of a subtemplate of the knowledge graph system through visual operation. The distributed client encrypts the subtemplate and then sends it to the central server. When the knowledge graph system is to be used, any knowledge concept is inputted, the central server calls and decrypts the subtemplate and then searches a database, and a tree structure knowledge graph is generated and sent to the distributed client.

Method and apparatus for visual construction of knowledge graph system

Disclosed is an system for predicting end-stage renal disease complication risk based on contrastive learning, including an end-stage renal disease data preparation module, configured to extract structured data of a patient by using a hospital electronic information system and daily monitoring equipment, and process the structured data to obtain augmented structured data; and a complication risk prediction module, configured to construct a complication representation learning model and a complication risk prediction model, perform training and learning on the augmented structured data through the complication representation learning model to obtain a complication representation, and perform end-stage renal disease complication risk prediction by using the complication representation through the complication risk prediction model.

System for predicting end-stage renal disease complication risk based on contrastive learning

Provided is a cross-departmental decision support system for early diagnosis of a chronic kidney disease based on knowledge graph, which comprises a patient information model building module, a patient information model library storage module, a knowledge graph association module, a knowledge graph inference module and a decision support feedback module. According to the present application, by constructing a patient information model and utilizing an OMOP CDM standard terminology system, patient electronic medical record data is constructed into a patient information model with unified concept coding and unified semantic structure; making full use the advantages of semantic technology in data interactivity and scalability, so that the system has better adaptability and scalability to heterogeneous data in different hospitals.

Cross-departmental chronic kidney disease early diagnosis and decision support system based on knowledge graph

The present invention discloses an automatic pancreas CT segmentation method based on a saliency-aware densely connected dilated convolutional neural network. Under a coarse-to-fine two-step segmentation framework, the method uses a densely connected dilated convolutional neural network as a basis network architecture to obtain multi-scale image feature expression of the target. An initial segmentation probability map of the pancreas is predicted in the coarse segmentation stage. A saliency map is then calculated through saliency transformation based on a geodesic distance transformation. A saliency-aware module is introduced into the feature extraction layer of the densely connected dilated convolutional neural network, and the saliency-aware densely connected dilated convolutional neural network is constructed as the fine segmentation network model. A coarse segmentation model and the fine segmentation model are trained using a training set, respectively.

Growing community of inventors

Hangzhou, China

Yu Tian