AI repository intelligence

FR-AI / ANALYSIS

Why it is worth attention

It demonstrates a fully offline, privacy-preserving approach to medical image viewing, with no accounts, analytics, or runtime network requests, making it suitable for sensitive data handling in a prototype context.

Who it is for

Radiologists and medical imaging professionals exploring offline tools
iOS developers interested in integrating medical image viewers
Researchers needing a customizable MRI series browser
Privacy-conscious users working with local DICOM archives

Use cases

Browsing and organizing MRI studies on a local device
Annotating images with freehand drawings, targets, and comments
Teaching or demonstrating MRI anatomy without internet access
Testing and prototyping new viewer features for medical imaging

Strengths

Fully local and offline with no backend, accounts, or analytics
Responsive grid with anatomy and orientation filters
Supports annotations, bookmarks, and full-screen swipe/zoom/scrub
Cross-platform: web viewer and SwiftUI iOS wrapper

Considerations

Prototype only – not a medical device or diagnostic tool
No bundled DICOM studies; requires private archive to see real images
Source is public for evaluation only; copying, modification, and deployment require written permission

README quick start

MRI Grid Viewer

A local-first interface for browsing MRI series on the web and iOS. It provides a responsive study grid, full-screen image viewing, search, filters, annotations, and saved frames.

The viewer runs entirely on-device. It has no accounts, analytics, backend, or runtime network dependency.

[!WARNING] This is an interface prototype—not a medical device or diagnostic tool. The repository does not include a DICOM archive or raw patient dataset.

Screenshots

Series overview

Drawing annotations

Target annotations

The screenshots were expressly selected and supplied by the repository owner. They are the only clinical imagery included here and are covered by a separate screenshot notice.

Features

Responsive MRI series grid
Anatomy and orientation filters
Search across names, tags, protocols, and metadata
Full-screen frame viewer with swipe, zoom, and scrub controls
Freehand drawing, target markers, comments, and local bookmarks
SwiftUI iOS wrapper using WKWebView
Offline, local-only runtime

Repository structure

viewer/             Web viewer source and empty sample manifest
ios-app/            SwiftUI wrapper with a bundled copy of the viewer
docs/screenshots/   Owner-approved documentation screenshots

Run the web viewer

Requirements: Python 3 and a modern browser.

python3 -m http.server 5177 --directory viewer

Open .

No study is bundled, so the default archive is empty. Run the search smoke test with:

node viewer/scripts/check_search.js

Run the iOS app

Requirements: Xcode 16 or newer and an iOS 17+ simulator or device.

Open ios-app/MRIGridViewer.xcodeproj.
Select the MRIGridViewer target.
Choose your own development team and bundle identifier for device builds.
Build and run.

After editing the web viewer, synchronize the iOS bundle:

python3 viewer/scripts/sync_web_bundle.py

Use a private local DICOM archive

Install the optional generator dependencies:

python3 -m pip install numpy pillow pydicom

Generate local assets from a directory outside the repository:

MRI_DICOM_SOURCE=/path/to/private/dicom python3 viewer/scripts/generate_assets.py

The generator writes to the ignored viewer/data/ directory. To load that output locally, change the manifest script in `viewe

Description

Local-first MRI series grid viewer with a SwiftUI iOS wrapper

Related repositories

Similar projects matched by category, topics, and programming language.

react

Featured

react

React is a JavaScript library for building user interfaces with declarative, component-based, and cross-platform design.

Web DevelopmentFrontend Frameworks

246,741

tandpfun

Featured

wardrobe

A GPT‑image powered app that extracts individual garment cutouts from photos, organizes them into a digital wardrobe, and generates modeled outfit previews.

JavaScript

1,570

mshumer

Featured

Claude-of-Duty

A browser-based first-person shooter built entirely with procedural generation and orchestrated AI agents, featuring 55k lines of Three.js/WebGL2 code and no art assets.

AI & Machine LearningAI Agents

1,234