openmedical/registry
← registry

MedVIGIL

imported

software/medvigil

MedVIGIL / MedVLM-Bench v1: a risk-stratified, multi-axis evaluation benchmark for medical Vision-Language Models.

Machine-generated from the listed sources and not yet reviewed by a human.

MedVIGIL project image
GitHub preview card for hq0709/MedVIGIL. Served by its origin, not stored here, and not covered by this registry’s licence.
record
Category
Software & Systems
Subcategory
unknown
License
CC-BY-4.0, MIT(mixed)
Status
active
Maturity
deployed
Organization
unknown
Country
unknown
Homepage
unknown
Documentation
unknown
Tags
benchmark · counterfactual · evaluation · hallucination · medical-imaging · radiology · vision-language-models · visual-grounding
Regulatory
unknown
similar by tags

Computed from shared tags, weighted so a rare tag counts for more than a common one. These are suggestions, not curated relationships.

  • MultiMedEvalbenchmark · evaluation · medical-imaging

    A Python tool to evaluate the performance of VLM on the medical domain.

  • causal-gencounterfactual · medical-imaging

    (ICML 2023) High Fidelity Image Counterfactuals with Probabilistic Causal Models

  • CACHEcounterfactual

    [ML4H 2022] This is the code for our paper `Counterfactual and Factual Reasoning over Hypergraphs for Interpretable Clinical Predictions on EHR'.

  • laibench-publicbenchmark · radiology

    A public reference benchmark for radiology finding-to-report generation.

  • histoboardbenchmark · medical-imaging

    Pathology FM dashboard centralizing literature and official benchmarks.

  • Brain_Tumor_Detection_Prototypemedical-imaging · radiology

    A research prototype for brain MRI segmentation, classification, and VLM-assisted analysis. Includes interactive segmentation-mask editing/export and NIFTI volume viewing with segmentation. Built…

sources
  1. api.github.com/repos/hq0709/MedVIGIL
    retrieved 2026-08-25 · via github-api

    Machine-imported from GitHub search. Last push 2026-05-07, 5 stars, license reported as NOASSERTION. Category and schematic were assigned by keyword heuristics and are unreviewed. GitHub reported NOASSERTION; the licence was read from the LICENSE file as CC-BY-4.0, MIT, because GitHub's detector does not recognise open hardware licences.

Not yet verified by a human. Correct this record →

machine-readable

/v1/entries/28.json→ .entries["medvigil"]

Entries are sharded 64 ways by a stable hash of the id, so a consumer can find any record without an index.