Quality Detection System
Academic Medical Research Institution — pathology, cancer detection.
2025
The challenge
What we found.
A leading academic medical center's pathology department was processing 2,400+ tissue samples daily for cancer detection. Manual microscopy review faced significant challenges, including inter-observer variability of 12–18% between pathologists.
Each slide required 15–20 minutes of expert review, creating an 8-hour turnaround for urgent cases and a growing backlog that threatened research timelines. They needed to augment (not replace) their experts with AI-assisted screening.
The approach
How we built it.
PRR developed a computer vision pipeline using custom-trained models:
- Ensemble of YOLOv8 and custom segmentation models trained on 180,000 annotated images
- Integration with 4 different microscopy systems and slide scanners for seamless ingestion
- Human-in-the-loop workflow where AI flags regions of interest for pathologist final determination
- Full audit trail and traceability for regulatory compliance
- 01IngestionMulti-source microscopy feed
- 02AnalysisYOLOv8 + segmentation
- 03ReviewPathologist confirmation
The outcome
The impact.
| Metric | Before | After | Improvement |
|---|---|---|---|
| Detection accuracy | 87% | 99.2% | +12 pts |
| False negative rate | 4.2% | 0.3% | 93% reduction |
| Review time per slide | 18 min | 4 min | -78% |
| Urgent case turnaround | 8 hours | 2 hours | -75% |
Stack
Tools used.
Keep reading
Related case studies.
Manufacturing · Enterprise
Agentic ERP automation
A conversational layer on SAP that cut procurement query time 90% — with zero ERP migration.
Read the case studyFinancial Services
Financial forecasting engine
Real-time time-series forecasting with ERP integration that surfaced $25M in annual savings.
Read the case studyRetail
Marketing-in-a-box
Automated campaign creation, spend forecasting, and personalization that cut launch time 75%.
Read the case study