Physician · Radiologist · Computer Science Student
I'm a physician and computer science undergraduate exploring how software engineering and artificial intelligence can advance radiological practice. My work focuses on clinical radiology, artificial intelligence, and modern software engineering to create practical, scalable solutions:
- DICOM viewers with 2D/MPR/volumetric rendering and DIMSE/DICOMweb integration
- Generative AI in medicine (LLMs/Agents, local inference, RAG/finetuning)
- Infrastructure for healthcare systems (PACS, NAS, containers, Proxmox)
- Full-stack development tailored to clinical workflows
- Languages: Python · Swift · C++ · Dart · JavaScript · Java
- Frameworks: Django · SwiftUI · Metal · Flutter
- AI/ML: PyTorch · TensorFlow · scikit-learn
- Medical Imaging: DCMTK · GDCM · VTK · ITK · DcmSwift · OsiriX/Horos · 3D Slicer · Orthanc
- Infra / DevOps: Docker · Proxmox · QNAP (& other open source NAS) · Tailscale · Git
- Setup: macOS + Windows, Linux VMs, NAS with Dockerized services
- Experimenting with: CUA (Computer Use Agents), Ollama, ComfyUI
- Local-first imaging platforms and DICOM viewers
- AI applications in medicine
- PACS servers in low-resource environments
- AI-assisted radiological decision-making
DcmSwift: Swift-native DICOM core (DIMSE + DICOMweb)
DICOM-Decoder: DICOM Pixel decode & windowing pipeline
MTK — Metal Toolkit: Modern Swift/Metal toolkit for high-fidelity medical imaging (volume rendering, SceneKit integration, SwiftUI components)
Isis DICOM Viewer (iOS/iPadOS/macOS): Native Swift DICOM viewer with 2D/MPR/Volumetric rendering and PACS integration (closed source)
Isis DICOM Viewer (Windows): Lightweight DICOM viewer with VTK integration
JFlutter: Cross-platform interactive educational tool to design and simulate automata, regular expressions, and formal languages. Mobile‑first, touch‑optimised UI.
TotalSegmentator Horos Plugin: Bringing the modern TotalSegmentator to the open-source Horos Project!
WALL-ET: Mobile Bitcoin wallet (WIP)
Orthanc for QNAP: Custom .qpkg packaging
LLMs + Radiology: Fine-tuning and RAG pipelines with anonymized radiology data



