Physician · Radiologist · Computer Science Student
I'm a physician and computer science undergraduate exploring how software engineering and artificial intelligence can enhance radiological practice. My work is focused on clinical radiology, artificial intelligence and modern software engineering to create practical, scalable solutions:
- DICOM visualization and PACS integration
- Generative AI (LLMs, local inference, RAGs/finetuning)
- Lightweight infrastructure for healthcare systems (DICOM viewers, NAS, containers, Proxmox)
- Full-stack development tailored to clinical workflows
- Languages: Python · Swift · C++ · Java · JavaScript · Dart
- Frameworks: Django · SwiftUI · Metal/SceneKit · Flutter
- Infra / DevOps: Docker · Proxmox · QNAP (& other open source NAS) · Tailscale · Git
- AI/ML: PyTorch · Transformers · scikit-learn · Ollama
- Medical Imaging: DcmSwift · DCMTK · GDCM · OsiriX/Horos · 3D Slicer · Orthanc
- DcmSwift — Swift-native DICOM core (DIMSE + DICOMweb) → https://github.com/ThalesMMS/DcmSwift
// Package.swift
dependencies: [
.package(url: "https://github.com/ThalesMMS/DcmSwift.git", branch: "main")
]
- Swift-DICOM-Decoder — Pixel decode & windowing pipeline → https://github.com/ThalesMMS/Swift-DICOM-Decoder
// Package.swift
dependencies: [
.package(url: "https://github.com/ThalesMMS/Swift-DICOM-Decoder.git", branch: "main")
]
- Isis DICOM Viewer (iOS) – mobile DICOM viewer with 2D/MPR/Volumetric rendering and PACS integration.
- JFlutter — modern Flutter port of the classic JFLAP tool for automata & formal language theory. Mobile‑first, touch‑optimised UI for creating and simulating automata/CFGs.
- TotalSegmentator Horos Plugin - bringing the modern Total Segmentator to the open source Horos Project!
- WALL-ET - Mobile Bitcoin wallet
- Orthanc for QNAP – Custom
.qpkg
packaging - LLMs + Radiology – Fine-tuning and RAG pipelines with anonymized radiology data
- macOS + Windows (development/testing)
- NAS: QNAP QTS with Dockerized services
- Preferred stack: Django + Python APIs, Swift/Flutter
- Experimenting with LM Studio, Ollama, ComfyUI
- DICOM Viewers
- DICOM servers in low-resource environments
- AI-assisted radiological decision-making
- Local-first imaging platforms
- E-mail: thalesmmsradio@gmail.com