How zeynepersoz/neurooncotrackai works
NeuroOncoTrack-AI’s ai branch is the AI HTTP microservice, not the full clinical platform. Its documented principal workflow is HTTP request → bridge orchestration → preprocessing, classification, XAI, and RAG report generation. Preprocessing and the RAG internals are supported by sampled source; the bridge’s stage links are documented in the README and partially visible in its excerpt. The README describes further segmentation, radiomics, and FHIR capabilities, but their runtime wiring is not fully established by the available excerpts, so those are not presented as confirmed pipeline stages.
Main entry points: bridge.py Pipeline bridge · pipeline.py Preprocessing pipeline · rag_pipeline.py RAG generation · end_to_end.py Report orchestrator
Components 20
Service entry
- HTTP service
ai_service/serve.py - Pipeline bridge
ai_service/bridge.py
Image preparation
- Preprocessing pipeline
ai_service/mert/preprocessing/pipeline.py - Input quality checks
ai_service/mert/preprocessing/qc.py - Skull stripping
ai_service/mert/preprocessing/skull_strip.py - Bias correction
ai_service/mert/preprocessing/bias_correction.py - Modality registration
ai_service/mert/preprocessing/registration.py - Resample and normalize
ai_service/mert/preprocessing/normalize.py
Inference and XAI
- V3 classifier
ai_service/zeynep/v3_predictor.py - V2 classifier
ai_service/zeynep/v2_predictor.py - Segmentation predictor
ai_service/zeynep/segmentation_predictor.py - XAI overlay
ai_service/mert/xai/overlay.py
Clinical reporting
- Report orchestrator
ai_service/mert/core/end_to_end.py - Text embedder
ai_service/mert/llm/embedder.py - Guideline search
ai_service/mert/llm/vector_store.py - RAG generation
ai_service/mert/llm/rag_pipeline.py - Report validation
ai_service/mert/llm/report_validator.py - Report instructions
ai_service/mert/llm/system_prompt.py
Other components
- Backend client
- Groq LLM service
Connections 21
- Backend client → HTTP service: sends request
README.md - HTTP service → Pipeline bridge: calls pipeline
ai_service/serve.py - Pipeline bridge → Preprocessing pipeline: runs preprocessing
README.md - Pipeline bridge → V3 classifier: classifies
ai_service/bridge.py - Pipeline bridge → V2 classifier: selects predictor
ai_service/bridge.py - Pipeline bridge → XAI overlay: builds overlay
ai_service/bridge.py - Pipeline bridge → Report orchestrator: generates report
README.md - Preprocessing pipeline → Input quality checks: checks inputs
ai_service/mert/preprocessing/pipeline.py - Preprocessing pipeline → Skull stripping: strips brain
ai_service/mert/preprocessing/pipeline.py - Preprocessing pipeline → Bias correction: corrects bias
ai_service/mert/preprocessing/pipeline.py - Preprocessing pipeline → Modality registration: registers modalities
ai_service/mert/preprocessing/pipeline.py - Preprocessing pipeline → Resample and normalize: normalizes images
ai_service/mert/preprocessing/pipeline.py - V3 classifier → V2 classifier: reuses preprocessing
ai_service/zeynep/v3_predictor.py - Report orchestrator → Text embedder: embeds query
ai_service/mert/core/end_to_end.py - Report orchestrator → Guideline search: builds and searches
ai_service/mert/core/end_to_end.py - Report orchestrator → RAG generation: requests report
ai_service/mert/core/end_to_end.py - RAG generation → Guideline search: retrieves context
ai_service/mert/llm/rag_pipeline.py - RAG generation → Report instructions: formats prompt
ai_service/mert/llm/rag_pipeline.py - RAG generation → Report validation: validates output
ai_service/mert/llm/rag_pipeline.py - Report validation → Report instructions: uses report rules
ai_service/mert/llm/report_validator.py - RAG generation → Groq LLM service: requests completion
ai_service/mert/llm/rag_pipeline.py