fix(ui): use head_paths for NiiVue loading on HF Spaces (#24) (#25)

fix(ui): vendor NiiVue library to bypass HF Spaces CSP (#24) (#24)

fix(ui): prediction overlay invisible, race condition, thread safety (#23) (#23)

fix(ui): replace base64 data URLs with Gradio file serving (#19)

docs: add spec for Issue #19 (base64 → file URL optimization)

fix(ui): NiiVue viewer re-initializes after segmentation completes (#21)

fix(ui): use js_on_load for NiiVue viewer instead of script tags (#20)

fix(docker): relocate app to /home/user/demo to preserve DeepISLES modules (#17)

fix(data): bypass load_dataset() to fix HF Spaces streaming hang and OOM (#16)

fix(data): use streaming mode to fix HF Spaces dataset hang (#15)

fix(ci): add pytest-timeout and HF Spaces deployment spec

feat(phase-4): Gradio UI with NiiVue visualization (#5)

docs: document SEALS model selection and scientific rationale

feat: Phase 1A + Phase 2 - Local data loader and DeepISLES Docker wrapper (#3)

Refactor documentation for Docker and Gradio implementation. Removed outdated permission fix code and fallback matplotlib rendering section. Updated Gradio approach to use direct Base64 injection instead of FastAPI endpoints, enhancing simplicity and performance.

Add initial project structure and documentation for stroke-deepisles-demo