Construction method and system for integrating neural image data analysis environment

Abstract

The invention relates to the technical field of neural image processing, and particularly discloses a construction method and system for integrating a neural image data analysis environment, and the method comprises the steps: constructing a docker mirror image according to a preset Dockerfile; creating a container according to the docker mirror image; in the created container, cancelling the access control of the host machine by controlling the cancelling instruction, so that the graphical interface in the container can be correctly displayed on the host machine; performing backup storage on the docker mirror image according to a preset storage format and a preset storage path; and decompressing the constructed and backed-up docker mirror image according to a decompression instruction, and transmitting the decompressed docker mirror image into a loading instruction through a pipeline as standard output for mirror image loading and the like. According to the invention, the construction and deployment process of the neural image data analysis and processing environment is simplified, and the purposes of one-button construction, operation, backup and deployment of the neural image data processing environment which is stable and repeatable and can be used for machine learning and deep learning are achieved.

Description

technical field [0001] The invention relates to the technical field of neuroimage processing, in particular to a method and system for constructing an integrated neuroimage data analysis environment. Background technique [0002] In the field of neuroimaging (brain magnetic resonance data) processing and analysis, it is necessary to call multiple professional software for collaborative processing in the Linux environment, such as AFNI, FSL, FreeSurfer, ANTs, etc.; at the same time, the research frontiers of machine learning and deep learning in the field of neuroimaging, There are many excellent machine learning and deep learning frameworks for researchers to use; however, the dependencies of each software or tool are more complicated, installation and configuration consume a lot of time and resources, and the configuration environment is different on different workstations or servers, which is not conducive to The streamlining of post-processing steps consumes a lot of ener...

AI Technical Summary

Problems solved by technology

The main disadvantages of fmriprep are: 1. The processing flow cannot be freely defined by the user, which is not conducive to innovative research and development; 2. It does not consider the execution of the visual user interface application, and cannot view the processing and analysis results in real time, which is not conducive to personal computers or ordinary workstations. Establish a process prototype; 3. The built environment does not consider the needs of GPU accelerated computing; 4. The issue of docker's read and write permissions for external files; 5. The framework of machine learning and deep learning is not integrated

The main disadvantages of neurodocker are: 1. The generated Dockerfile does not solve the software dependencies; 2. Only the Dockerfile is generated, and does not include image building, backup, deployment, etc.; 3. The software integrated into the analysis process is not All are official release versions, and their security cannot be guaranteed; 4. The built environment does not consider the needs of GPU accelerated computing; 5. The execution of the visual user interface application is not considered in the generation of Dockerfile; 6. Docker reads and writes external files Permission issues; 7. Not integrating machine learning and deep learning frameworks, etc.

Images