Skip to content

Work

Case studies, projects and writing.

Each project is labelled for what it is: professional, academic or independent. Results are shown only where the evidence supports them, and every figure names its source.

Case studies

WEB APPLICATION · CONTAINERISEDRadiographClassifierGrad-CAMReportCase history

Professional· Unicorn MedicsJun 2026 – present

Clinical X-ray AI · Unicorn Medics

My professional work as a Junior Computer Vision Engineer at Unicorn Medics: owning the path from X-ray data and model development to an explainable, containerised application used for clinical review.

  • Python
  • TensorFlow / Keras
  • OpenCV
  • Grad-CAM
A chest X-ray uploaded to the LungVision application.The same chest X-ray with the Grad-CAM heatmap from model C of the LungVision ensemble, concentrated over both lung fields (colours corrected).

Academic· Team of 4Mar 2025 – Jan 2026

LungVision

A final-year team project that combines chest X-rays, CT scans and clinical metadata for early lung cancer detection, with four-CNN ensembles per imaging modality and Grad-CAM and LIME explanations for every prediction.

1st place, final-year project evaluation

VALIDATION ACCURACY · 20 EPOCHS93%95%97%besttestedTEST · n = 231103101117DRNO DR95.2% ACCURACY
From the notebook’s saved outputs

Independent project2025

Diabetic retinopathy screening

A ResNet-18 transfer-learning model that screens retinal fundus images for diabetic retinopathy, served through a Flask app with a confidence score and a Grad-CAM heatmap, and audited honestly afterwards.

95.2%test accuracy on 231 held-out images (final-epoch model)Source: Repository notebook

More projects