The machine learning research group at Mohn Medical Imaging and Visualization Center
Official@mmiv-ml · Bergen, Norway
See also https://github.com/mmiv-center
Agent Skills by The machine learning research group at Mohn Medical Imaging and Visualization Center
Showing 7 vetted skills indexed across 1 GitHub repositories.
MMIV-MLstaff-review
Assess technical plans for risks and missing details with structured reviews.
MMIV-MLdocker-local-dev
Generate Docker-based development environments for PHP, Node.js, and Python stacks.
MMIV-MLskill-creator
Generate, package and validate Claude skill scaffolds with Python scripts and SKILL.md templates.
MMIV-MLcode-reviewer
Review Python code for quality, security, and performance issues.
MMIV-MLror-workflow
Explore DICOM datasets and set up ROR research workflows.
MMIV-MLfastmonai-upstream-guide
Consult MONAI, TorchIO, and nnU-Net docs and source code to align fastMONAI implementations with upstream patterns.
MMIV-MLclaude-docs-consultant
Fetch official Claude Code documentation on demand for API usage and feature references.
Frequently Asked Questions About The machine learning research group at Mohn Medical Imaging and Visualization Center
FAQPage SchemaWhat specific medical imaging tasks does this group support?▼
The group enables the exploration of DICOM datasets and provides guidance on aligning fastMONAI implementations with upstream patterns from MONAI, TorchIO, and nnU-Net. These capabilities facilitate standardized research environments for medical imaging analysis and model development.
Who is the target audience for these research resources?▼
These resources are designed for medical imaging researchers, data scientists, and software engineers working within clinical or academic environments. The technical support focuses on maintaining high-quality research code and ensuring compatibility with established medical imaging frameworks.
What are the prerequisites for utilizing these research environments?▼
Users require a local environment capable of running containerized stacks, specifically configured for PHP, Node.js, and research-oriented languages. Access to the specific DICOM datasets and familiarity with the MONAI ecosystem are necessary to effectively leverage the provided research guidance and documentation.