How milefisher/kneexpert works
KneeXpert is a clinical knee-osteoarthritis diagnostics platform: clinicians manage patients, submit X-ray images or MRI volumes for inference, and review diagnostic results and reports. The React UI communicates with a separate FastAPI service over REST. The backend provides X-ray ensemble predictions with Grad-CAM and an MRI volume-to-grade pipeline, alongside structured clinical feedback and model-compute reporting. The graph preserves the documented admin, patient, and reporting areas; unsampled frontend internals are represented at their supported source paths.
Main entry points: pipeline.py MRI inference pipeline · App.tsx App routes · app.py FastAPI endpoints · ensemble.py X-ray ensemble
Components 23
Clinical UI
- App routes
frontend/src/App.tsx - Dashboard
frontend/src/pages/DashboardPage.tsx - Patient management
frontend/src/pages/PatientsPage.tsx - Diagnostics workspace
frontend/src/pages/DiagnosticsPage.tsx - Report hub
frontend/src/pages/ReportsHubPage.tsx - Report detail
frontend/src/pages/ReportDetailPage.tsx - Admin console
frontend/src/pages/AdminPage.tsx - Diagnostic API client
frontend/src/lib/diagnosticApi.ts
API services
- FastAPI endpoints
backend/app.py - Model profiler
backend/model_profiler.py
X-ray inference
- X-ray ensemble
backend/xray/ensemble.py - X-ray model loader
backend/xray/loader.py - X-ray Grad-CAM
backend/xray/gradcam.py
MRI inference
- MRI inference pipeline
backend/mri/pipeline.py - MRI volume loading
backend/mri/volume_io.py - Slice preprocessing
backend/mri/preprocess.py - MACS-Net cleanup
backend/mri/macs_net.py - DeiT classification
backend/mri/deit_classifier.py - MRI Grad-CAM
backend/mri/gradcam.py - MRI label categories
backend/mri/label_summary.py
Clinical logic
- Clinical feedback
backend/feedback_engine.py - Shared findings
backend/shared/clinical_feedback.py
Other components
- Clinician
Connections 24
- Clinician → App routes: uses
frontend/src/App.tsx - App routes → Dashboard: routes
frontend/src/App.tsx - App routes → Patient management: routes
frontend/src/App.tsx - App routes → Diagnostics workspace: routes
frontend/src/App.tsx - App routes → Report hub: routes
frontend/src/App.tsx - App routes → Report detail: routes
frontend/src/App.tsx - App routes → Admin console: routes
frontend/src/App.tsx - Diagnostics workspace → Diagnostic API client: requests analysis
- Diagnostic API client → FastAPI endpoints: calls REST
README.md - FastAPI endpoints → X-ray ensemble: dispatches X-ray
backend/app.py - FastAPI endpoints → MRI inference pipeline: dispatches MRI
backend/app.py - FastAPI endpoints → Clinical feedback: generates feedback
backend/app.py - FastAPI endpoints → Model profiler: gets compute costs
backend/app.py - X-ray ensemble → X-ray model loader: loads models
backend/xray/ensemble.py - X-ray ensemble → X-ray Grad-CAM: generates overlays
backend/xray/ensemble.py - X-ray ensemble → Shared findings: gets findings
backend/xray/ensemble.py - MRI inference pipeline → MRI volume loading: loads volumes
backend/mri/pipeline.py - MRI inference pipeline → Slice preprocessing: prepares slices
backend/mri/pipeline.py - MRI inference pipeline → MACS-Net cleanup: cleans slices
backend/mri/pipeline.py - MRI inference pipeline → DeiT classification: classifies slices
backend/mri/pipeline.py - MRI inference pipeline → MRI Grad-CAM: generates overlays
backend/mri/pipeline.py - MRI inference pipeline → MRI label categories: resolves labels
backend/mri/pipeline.py - MRI inference pipeline → Shared findings: gets findings
backend/mri/pipeline.py - Shared findings → Clinical feedback: delegates findings
backend/shared/clinical_feedback.py