DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5
106 stars · Python

How to use Fle Xray: what you can do with it

What is Fle Xray? FleXray is a Python command-line tool and package that segments anatomy in X-ray images and can also train new full-body X-ray segmentation models.

How do I use it? Install the package with python -m pip install flexray; then run a single prediction with flexify --input ./image.png --output-dir ./predictions; To predict a whole folder, pass the folder to the same command with flexify --input ./xrays --output-dir ./predictions. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Segment X-ray images into anatomy masks from the terminal

    Run flexify on one image or a folder and get NumPy mask, probability, and logit arrays.

    View prompt
    In the FleXray repo (pip package flexray), run `flexify --input <input-path> --output-dir <output-dir>` on the target X-ray image or folder. Expect image_masks.npy, image_probabilities.npy, image_logits.npy, and label_names.json per image. Verify that the masks arrays are CxHxW with C equal to the number of labels in label_names.json.

  • Raise mask quality with the five-model ensemble

    Use --ensemble and --tta-samples to trade run time for more accurate anatomy masks.

    View prompt
    In the FleXray repo, run `flexify --ensemble --tta-samples 8 --input <image-path> --output-dir <output-dir>` on the target X-ray. Expect the same three .npy arrays plus label_names.json. Verify that the mask arrays are uint8 and that the channel count matches label_names.json.

  • Ask Claude Code to segment X-rays through Fle Xray MCP

    Register the fxr-mcp server so an AI client can run segment_image and inspect label protocols.

    View prompt
    Using the FleXray MCP server from the FleXray repo, call segment_image on <image-path> and report the per-label statistics. Expect a summary of each anatomical label and the output files. Verify the label names match the label_names.json written by the run.

  • Fine-tune Fle Xray onto your own X-ray label set

    Map your masks to the Fle Xray protocol, pack the data, and train from the released weights.

    View prompt
    In the FleXray repo, scaffold a dataset from <images-dir> and <masks-dir> with fxr-dataset, then dry-run fxr-train on CPU with --init-from VictorButoi/flexray --replace-head. Expect a dry run that completes without error and a packed ThunderDB dataset. Verify that the label mapping in the compiled protocol covers every mask id in your data.

Quick start with Fle Xray

  1. Check you have what it needs: Python 3.10 or newer and pip; One or more X-ray images in PNG, JPEG, TIFF, BMP, or DICOM (DICOM needs the dicom extra); Internet access to download pretrained weights from Hugging Face on first run.
  2. Open VictorButoi/FleXray on GitHub and read the README and license.
  3. Install the package with python -m pip install flexray.
  4. Run a single prediction with flexify --input ./image.png --output-dir ./predictions.
  5. To predict a whole folder, pass the folder to the same command with flexify --input ./xrays --output-dir ./predictions. (inferred, check the README)
  6. Open label_names.json to map channel numbers to anatomical labels, then load the .npy files with NumPy.

These steps come from our top use case, Segment X-ray images into anatomy masks from the terminal, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for VictorButoi/FleXray

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Best AI repos for Research

About this repo

  • Who it is forWritten for medical imaging researchers and ML engineers who need anatomy masks from X-ray images, and for AI agents that run the FleXray CLI or MCP server on their behalf.
  • Why it is hot106 stars, launched 39 days ago
  • LanguagePython
  • Sourcegithub.com/VictorButoi/FleXray · Back to Hot repos

Requirements

  • Python 3.10 or newer and pip
  • One or more X-ray images in PNG, JPEG, TIFF, BMP, or DICOM (DICOM needs the dicom extra)
  • Internet access to download pretrained weights from Hugging Face on first run
  • For training only: a labeled dataset, and a GPU or CPU for the dry run; the README says training is single-process with at most one GPU
  • For the MCP use case: an MCP-capable client such as Claude Code or Claude Desktop

Add this badge to your README

Maintain Fle Xray? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/VictorButoi/FleXray.svg)](https://dedupedai.com/use-cases/victorbutoi-flexray/?utm_source=github&utm_medium=badge&utm_campaign=VictorButoi-FleXray)

HTML 

<a href="https://dedupedai.com/use-cases/victorbutoi-flexray/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=VictorButoi-FleXray"><img src="https://dedupedai.com/badge/VictorButoi/FleXray.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Fle Xray

What is Fle Xray?

FleXray is a Python command-line tool and package that segments anatomy in X-ray images and can also train new full-body X-ray segmentation models. It is an open-source project on GitHub: https://github.com/VictorButoi/FleXray.

How do I use Fle Xray?

Install the package with python -m pip install flexray; then run a single prediction with flexify --input ./image.png --output-dir ./predictions; To predict a whole folder, pass the folder to the same command with flexify --input ./xrays --output-dir ./predictions. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Fle Xray for?

Written for medical imaging researchers and ML engineers who need anatomy masks from X-ray images, and for AI agents that run the FleXray CLI or MCP server on their behalf.

What can I do with Fle Xray?

4 use cases so far, for example: Segment X-ray images into anatomy masks from the terminal; Raise mask quality with the five-model ensemble; Ask Claude Code to segment X-rays through Fle Xray MCP. Each has steps and a copy-paste agent prompt.

What do I need to run Fle Xray?

Python 3.10 or newer and pip; One or more X-ray images in PNG, JPEG, TIFF, BMP, or DICOM (DICOM needs the dicom extra); Internet access to download pretrained weights from Hugging Face on first run; For training only: a labeled dataset, and a GPU or CPU for the dry run; the README says training is single-process with at most one GPU.

What are alternatives to Fle Xray?

Other hot AI repos in Research: Sam2, Docling, LightRAG, Ragflow, Markitdown.

Is Fle Xray safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.