Product Management — OraScan AI Platform
94.7% accuracy across 11 oral disease categories — the product definition behind the AI.
0%
Accuracy Target Set & Met
0K+
Training Images Curated
0
Disease Classes Defined
Tools & Methods
The Challenge
Oral diseases affect over 3.5 billion people globally but go undiagnosed in low-resource settings due to the cost of specialist consultations. The PM challenge was defining a product that was both clinically credible and deployable on GPU-less kiosk hardware at dental clinics. This meant setting meaningful per-class accuracy targets — not just a single aggregate metric — across 11 disease categories with severe class imbalance (common: caries, calculus; rare: mucocele, hypodontia) and specifying dataset curation criteria that would drive a reproducible, bias-reduced training corpus. The go-to-market path had to be defined upfront: kiosk-first deployment with a REST API layer for future integrations, rather than cloud-first with a latency penalty.
Product Requirements Document
PRODUCT REQUIREMENTS DOCUMENT
OraScan — AI Oral Disease Detection
Varun Cumbanungam · AI Product Manager · Oralens HealthCare (2023)
Doc ID
ORS-PRD-V1
Status
Approved
Owner
Varun C.
Date
2023
Version
1.0
Problem Statement
Oral diseases affect 3.5B people globally but go undiagnosed. The product must classify 11 disease classes at ≥94% accuracy on GPU-less kiosk hardware in under 200ms.
Disease Classes & Dataset
- Caries, Calculus, Gingivitis — high-prevalence classes
- Periodontal disease, Oral cancer — critical recall required
- Hypodontia, Mucocele, Ulcer, Fluorosis + more
- 78,058 labelled images (DENTEX + SMART-OM datasets)
- Class imbalance: weighted sampling + CutMix augmentation
Model & Deployment Strategy
- EfficientNet-B0 backbone — 4.67M parameters
- PyTorch + AMD GPU (DirectML) training pipeline
- ONNX INT8 export — edge kiosk CPU deployment
- 23 training iterations tracked in Edge Impulse
Key Acceptance Criteria
- AC-1Overall test accuracy ≥94% across all 11 classes
- AC-2Oral cancer recall ≥97% — no false negatives
- AC-3ONNX INT8 inference on CPU under 200ms
- AC-4Model size under 20MB post-quantisation
- AC-5FastAPI inference server p95 under 300ms
- AC-6Accuracy drop post-INT8 quantisation under 1%
Key Risks
- HIGH
Oral cancer false negative — missed diagnosis
Recall ≥97% gate + clinical review threshold
- HIGH
INT8 accuracy regression on kiosk hardware
Per-class evaluation before deployment sign-off
- MED
Dataset class imbalance skews model
Weighted sampling + confusion matrix gate
Product Artefacts Delivered
- PRD V1 — disease scope, dataset strategy, ACs
- Model evaluation — per-class metrics, confusion matrix
- ONNX deployment spec — INT8 quantisation runbook
- Kiosk integration guide — FastAPI + hardware setup
CONFIDENTIAL · OraScan PRD · Property of Oralens HealthCare
PRD · Model Evaluation · ONNX Deployment Spec · Kiosk Guide
Full PRD and supporting artefacts available upon request
Results
The model shipped meeting the 94.7% test accuracy target across all 11 disease classes. ONNX INT8 quantisation met the <200 ms kiosk inference latency requirement without meaningful accuracy regression. The product was integrated into two workflows — automated scanning (MediaPipe FaceMesh-triggered) and manual desktop scanning — enabling OraScan to serve both high-throughput kiosk and assisted-diagnosis use cases from a single model artefact.
Gallery & Demos
Click any image or video to expand · ← → keys navigate
More from OraLens Healthcare Pvt. Ltd.
OraScan — Oral Disease Detection
AI-powered oral disease classification system: a custom EfficientNet-B0 model trained on 78,000+ dental images achieving 94.7% accuracy across 11 disease categories, deployed via ONNX to kiosk hardware.
OraScan H — Halitosis IoT Device
Full-stack IoT device for halitosis (bad breath) detection: a Raspberry Pi Zero 2W with H2S gas sensors communicates via BLE to a Flutter mobile app, with on-device TFLite AI classification and PHP backend.
Product Management — OraScan H IoT Device
Product ownership of OraScan H — a consumer IoT halitosis detection device combining a Raspberry Pi Zero 2W, H2S gas sensors, and a Flutter mobile app. Defined the BLE UX flow, consumer-grade pairing experience, and sprint milestones from concept to 92% software completion.
ArogyaLens — Dental AI Platform
Enterprise hospital management platform with AI-powered oral screening (AWS Rekognition + SentiSight), multi-language support across 13 languages, OPD/IPD bed management, pharmacy, lab integration, HR/payroll, e-commerce, and telemedicine — plus a Flutter mobile app for intraoral capture and automated PDF report generation.
Product Management — ArogyaLens Dental Platform
Product ownership of ArogyaLens — a comprehensive hospital management + AI diagnostics platform spanning 15+ modules (OPD/IPD, pharmacy, labs, HR/payroll, e-commerce, telemedicine), multi-language support across 13 languages, AI-powered oral screening, and a Flutter mobile capture app. Authored full PRD, SRS, and technology specification.
LuxySmile Oral Care — Product Website & Dashboard
Full product suite for LuxySmile Oral Care (Oralens Healthcare): a React + Vite marketing site targeting B2B dental wellness programs for schools and corporates, plus an internal case management dashboard with direct-to-S3 uploads and CSV bulk import.
Product Management — LuxySmile Oral Care Brand
Product and go-to-market ownership for LuxySmile Oral Care — OraLens Healthcare's B2B wellness brand. Defined the dual B2B/B2C positioning strategy, school and corporate wellness program inquiry flow, and the AI kiosk upsell path on a premium product website.
Interested in this work?
Full architecture walkthrough and code review available during interviews.