Project 03 / 04Data VisualisationHealthcare · Medical Imaging

Organ Disease Progression VisualizerImaging-Driven 3D Lung Model

A deterministic pipeline that turns chest CT images into a live, signal-driven 3D lung visualisation.

03 · Data VisualisationOverview

3D lung mesh rendered by the pipeline for Case 01: advanced disease, progression score 0.809, deep fibrotic red with strong deformation

Role: Technical Lead, full system implementation (COMP8851 team project)
Stack: Python, OpenCV, PyVista, Trimesh, NumPy
Scope: 8 clinical CT cases · scored 0.218–0.809
Source: View on GitHub

8
Clinical CT cases scored
3
Signals extracted per scan
0.218–0.809
Progression score range
100%
Runs with a JSON audit trail

The build

How it came together.

01
The system
Can you tell what stage a lung disease is at just from a CT scan? Most people can't, so as technical lead on this Macquarie COMP8851 project I built a system that can, and that shows you exactly why. It's a deterministic Python pipeline that processes real chest CT images and maps quantitative signals directly onto an anatomical 3D lung mesh, with interactive case switching in the viewer.
02
The signals
From each scan the pipeline extracts three numbers: severity (mean pixel intensity), texture (standard deviation), and HDR, the proportion of pixels above a density threshold, standing in for dense lesion and fibrosis coverage. Those combine into one progression score: 0.65 × Severity + 0.20 × Texture + 0.15 × HDR. Every number on screen came from a pixel in the CT image.
03
Driving the model
That score then drives the 3D model: colour, lesion spread, surface roughness, and structural deformation all respond to it. I ran 8 clinical cases through the system, spanning 0.218 (near-healthy) through to 0.809 (advanced fibrosis), so the reference lung visibly deforms from smooth and light to darkened, volume-lost, and fibrotic as the disease advances.
04
Traceability
Because this is a medical context, traceability was non-negotiable. Every run writes a JSON audit trail logging each pipeline decision: the extracted values, the weighting calculation, the disease-staging transition, and the exact count of affected mesh vertices. Eight cases, eight audit logs, every decision traceable back to the input.

Visuals

What it produced.

05 figures

Raw axial chest CT slice for Case 01 showing extensive honeycombing and fibrosis — The raw CT input for Case 01: extensive fibrosis, which the pipeline scores at 0.809.

Fig. 02
Case 08: near-healthy (0.218). Light colour, smooth surface, minimal deformation.
Fig. 03
Case 02: moderate (0.668). HDR-dominant, mild fibrotic texture emerging.
Fig. 04
Case 04: advanced (0.754). Strong deformation and darkening, HDR the dominant driver.
Fig. 05
The raw CT input for Case 08: clear lung fields, scored near-healthy at 0.218.