fix(hf): avoid eager 27GB dataset download on /api/cases (#46)

refactor(data): use standard datasets.load_dataset() with neuroimaging-go-brrrr

feat(api): async job queue with comprehensive test coverage (#36)

feat(api): FastAPI REST backend for React frontend

feat: Gradio Custom Component for NiiVue (#29)

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

style: format test_app.py for CI (line length)

fix: remove silent failures and redundant checks

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

fix(docker): use subprocess bridge for Python version isolation (#18)

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(ui): lazy dataset loading to prevent HF Spaces timeout (#14)

fix(ci,docker): resolve CI disk space and HF Spaces entrypoint issues

fix(pipeline): copy input files to results_dir and add UI cleanup

fix(pipeline): prevent unbounded disk usage from HuggingFace temp files

feat(data): integrate HuggingFace dataset as primary data source (#11)

fix(inference): correct DeepISLES Docker volume mounts and CLI args

fix: resolve technical debt (P2/P3) with TDD validation (#9)

feat(hf-spaces): complete deployment infrastructure for Hugging Face Spaces (#8)

fix(ci): skip pipeline integration test when ISLES24 data missing

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

feat(phase-5): polish, observability, and documentation (#6)

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

feat(phase-3): End-to-end pipeline with metrics and CLI

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

feat(phase-1): implement data access layer with TDD (#2)

feat(phase-0): bootstrap project with TDD structure (#1)