Skip to content
Nat Lee

Keyboard shortcuts

Turn these off if they get in the way of a screen reader or voice control. The setting is saved in this browser.

1
Home
2
Projects
3
About
4
Experience
/
Search projects
?
Show this panel

Medical Imaging

Brain MRI Pipeline

From a T1 scan to tissue maps and QC

An end-to-end Nipype pipeline with FSL FAST, K-means and ANTs Atropos segmentation, tissue volumes, bias-correction metrics and an interactive 3D brain.

Source4040 stars on GitHub(opens in a new tab)
Role
Creator & Maintainer
Period
2018 – 2026.11
Status
Completed
Theme
AI, vision & medical imaging
Brain MRI Pipeline, screenshot 1

Overview

A research and learning pipeline for T1-weighted MRI: AC-PC alignment, MNI152 registration, skull stripping and N4 bias correction, followed by a choice of FSL FAST, K-means or ANTs Atropos. It compares segmentation agreement, reports tissue volumes and QC metrics, and produces a 3D view and HTML report per scan. Demo scans come from openly licensed OpenNeuro data.

The problem

  • Keeping specialised imaging tools reproducible
  • Comparing tissue segmentation methods on the same corrected scan

What I did

  • A focused Docker image containing the required tools
  • Shared N4-corrected inputs with selectable primary segmentation

Results

  • Reproducible CPU pipeline with openly licensed demo scans
  • Per-scan tissue maps, quantitative QC and HTML reports

Features

  • AC-PC alignment, registration, skull stripping and N4 correction
  • Selectable FAST, K-means or Atropos segmentation
  • Tissue volumes, Dice agreement and before/after QC
  • Interactive 3D brain, turntable GIF and HTML reports
  • AI, vision & medical imaging33 stars on GitHub

    QWOP with PPO

    A PyTorch PPO agent plays the real QWOP browser game through Playwright. Six evaluation races, six 100 m finishes. Grace was not part of the reward function.

    2019Completed
  • AI, vision & medical imaging11 stars on GitHub

    Street Scene OCR

    Compare EasyOCR, RapidOCR and PaddleOCR on Traditional Chinese street signs, with text boxes, timings and a small public-domain benchmark.

    2026Completed
  • AI, vision & medical imaging11 stars on GitHub

    Sentiment Bundle Benchmark

    TF-IDF, embeddings, fine-tuned encoders and a local language model, evaluated on fixed splits across six sentiment datasets. The successor to GURA.

    2026Completed