Work
Production AI/ML at aycan Medical Systems / Paratus — conceived, deployed, and maintained inside FDA-regulated PACS workflows. Closed-source by necessity; each is a case study of problem, architecture, and measured result.
aycan Medical Systems / Paratus · 2025
Automated vertebral and disc segmentation that renders labels straight into the radiologist's PACS viewer — C1 to sacrum, in minutes, demoed at RSNA 2025.
aycan Medical Systems / Paratus · 2025
A vision-language model that finds and redacts burned-in PHI from DICOM pixel data on-premise — a novel application of Florence-2 with no published prior art.
aycan Medical Systems / Paratus · 2025
Real-time radiology dictation with a from-scratch German medical text corrector — dual-Whisper transcription, structured LLM reports, fully local inference.
aycan Medical Systems / Paratus · 2025
A three-model stacking ensemble that recovers laterality and view position from real-world mammography — trust-gated to lean on metadata when it's reliable and pixels when it isn't.
aycan Medical Systems / Paratus · 2025
A fully-local natural-language query interface for the PACS database — fine-tuned 270M Gemma, three-stage NL → JSON → SQL, no cloud API and no equivalent shipping from any commercial vendor.
aycan Medical Systems / Paratus · 2024 — 2026
The production imaging pipeline for the Xeltis aXess FDA Breakthrough-Device trial — email intake, token uploads, five-phase DICOM verification, pixel anonymization, and PACS ingestion.
aycan Medical Systems / Paratus · 2023 — 2026
The backbone under the AI: the PostgreSQL data-access layer, the HL7 interoperability suite, twenty PACS-viewer extensions, and the WireGuard VPN that connects every customer site.