✓ ABDM Compliant
✓ ISO 13485
✓ CDSCO · CE MDR
✓ SaMD
Forus Health · Medical AI Division · Bengaluru, India

The Eye as a
Window to
Human Health

We build and commercialize medical AI systems that transform retinal and anterior segment imaging into actionable diagnostic intelligence — for eye disease and beyond.

Explore AI Models See FH-POISE™ Platform
500K+
Screenings processed
9+
Conditions detected
65+
Countries deployed
20M+
Lives impacted
Scroll
About the Division

A focused AI team embedded in
ophthalmic innovation

The Forus Health AI Division is the dedicated machine learning and applied AI arm of Forus Health — a pioneering ophthalmic medical device company headquartered in Bengaluru, India, with a global footprint across 65+ countries.

Over the past six years, our team has developed, validated, and deployed AI systems powering the FH-POISE™ platform — enabling early detection of diabetic retinopathy, glaucoma, cardiovascular markers, dry eye disorders, and more.

We are a capability-first team open to applying our expertise in ophthalmic AI, multi-modal medical imaging, and regulatory-grade model development to new clinical and industry partners.

"We do not build AI for AI's sake — we build it to make specialist-level diagnostics available to every patient, everywhere, regardless of access to a specialist."

01 —

Deep Clinical Collaboration

Models developed in close partnership with ophthalmologists and graders, ensuring clinical validity at every iteration.

02 —

End-to-End Deployment

From data curation and model training to on-device inference and cloud API deployment — we own the full stack.

03 —

Regulatory-Grade Development

Development practices aligned with medical device AI guidelines — CE, CDSCO, and FDA submission pathways.

04 —

Built for Global Scale

Designed for low-resource settings — lightweight inference, offline capability, and multilingual reporting.


FH-POISE™ Platform

Precision Ocular Intelligence
for Systemic & Eye Health

Our flagship AI platform analyzes retinal and anterior segment images to deliver multi-condition diagnostic insights — in real time, at point of care.

FH-POISE™ Platform
AI Inference Pipeline
PRODUCTION · v4.2
01
📷
Image Acquisition
3nethra fundus / anterior
02
⚙️
Pre-processing
Quality check, CLAHE
03
🧠
Deep Learning
Multi-task CNN / Attention
04
🗺️
Explainability
Grad-CAM heatmaps
05
📊
Clinical Report
Risk scores, grading, flags
ACTIVE STAGE
📷
Image Acquisition
Fundus and anterior segment images captured from 3nethra portable devices. Supports non-mydriatic retinal imaging in low-resource, point-of-care environments with no pupil dilation required.
3nethra Classic Non-mydriatic JPEG / DICOM
PIPELINE PROGRESS
01 —
🎯

Multi-condition Detection

Single forward pass, 9+ conditions — retinal, systemic, and anterior segment pathologies simultaneously graded.

02 —
🗺️

Heatmap Explainability

Grad-CAM visualizations highlight lesion regions driving each decision — essential for clinician trust and audit trails.

03 —
📱

Edge Deployment

TensorRT-optimized models run on 3nethra devices directly, enabling AI diagnostics with zero internet dependency.

04 —
☁️

Cloud API Mode

REST API endpoints for FH TeleCare and TeleEye platforms, enabling remote screening at scale across partner networks.

05 —
📐

Calibrated Confidence

Softmax probability calibration and uncertainty estimation provide actionable confidence scores for clinicians.

06 —
🔄

Continuous Learning

Annotation pipelines and active learning loops allow models to improve continuously from deployment feedback.


AI Project Portfolio

Deployed models across
oculomics & systemic disease

Retinal DiseaseDeployed

Diabetic Retinopathy Grading ★ Flagship

95%+
Sensitivity
ICDR
Grading scale
5-class
Severity

Deep CNN classifier trained on 500K+ real-world screenings. Detects microaneurysms, hemorrhages, exudates, and neovascularization. Produces No DR → Proliferative scores with Grad-CAM heatmaps and macular edema co-detection.

EfficientNet-B4Multi-class classificationGrad-CAMMacular edema co-detection
Retinal DiseaseDeployed

Glaucoma Suspect Detection

CDR
Primary feature
RNFL
Layer analysis

Automated optic disc and cup segmentation with cup-to-disc ratio estimation. Identifies RNFL thinning and disc pallor indicative of glaucomatous damage. Outputs suspicion flag with segmentation overlay for referral triage.

Attention U-NetSegmentation + ClassificationCDR estimation
Retinal DiseaseDeployed

Age-Related Macular Degeneration

Drusen
Detection
Dry/Wet
Classification

Detects early, intermediate, and late AMD by identifying drusen deposits, geographic atrophy, and choroidal neovascularization. Supports dry vs. wet AMD differentiation to guide urgency of referral.

EfficientNet-V2Drusen segmentationAREDS grading
Retinal DiseaseDeployed

Cataract Detection & Grading

LOCS III
Reference scale

Detects lens opacity and grades cataract severity from retinal images using image quality degradation as proxy signal. Enables opportunistic cataract screening during routine retinal examination — no separate slit-lamp required.

Image quality regressionLens opacity scoringReferral calibration
Systemic BiomarkerDeployed

Hypertensive Retinopathy

KW
Keith-Wagener grading
4-class
Severity

Identifies vascular changes associated with systemic hypertension — arteriovenous nicking, silver/copper wiring, focal arteriolar narrowing. Non-invasive hypertension screening signal for community health programs.

ResNet-50Vascular feature extractionA:V ratio estimation
Systemic BiomarkerIn Validation

Cardiovascular Risk from Retina

Non-inv.
CVD screening

Leverages retinal vascular geometry — fractal dimension, vessel tortuosity, caliber asymmetry — as surrogate markers for CVD risk. Predicts composite cardiovascular risk score from fundus image alone, without blood tests or ECG.

Vision Transformer (ViT)Vascular geometryMulti-ethnic validation
Anterior SegmentDeployed

Lipid Layer Interferometry (LLI)

Dry Eye
Biomarker

Analyzes interference fringe patterns in the tear film lipid layer. Classifies lipid layer thickness and uniformity as an objective dry eye biomarker — replacing subjective grading with AI-scored metrics correlated with OSDI severity.

Texture CNNFringe pattern analysisOrdinal classification
Anterior SegmentDeployed

Tear Meniscus Height (TMH)

Sub-mm
Measurement precision

Automated measurement of tear meniscus height from anterior segment slit images using semantic segmentation. Provides an objective tear volume surrogate — a key parameter in the TFOS DEWS II dry eye diagnostic algorithm.

Semantic segmentationSub-pixel regressionDEWS II integration
Anterior SegmentDeployed

Meibomian Gland Dysfunction (MGD)

Gland
Morphology AI

Segments and quantifies Meibomian gland morphology from infrared meibography. Computes gland dropout score, tortuosity index, and gland density — fully automated pipeline replacing manual grader assessment.

Instance segmentationGland dropout scoringTortuosity index

Real-World Impact

From models to millions

Field-deployed across 65+ countries, our AI systems have processed hundreds of thousands of real patient screenings.

500K+
AI-analyzed retinal screenings
65+
Countries with deployed AI
9
AI models in production
6 yrs
Continuous AI R&D investment
Development Timeline
2018–2019

Foundations

First DR grading model trained on proprietary Forus fundus dataset. Proof-of-concept validated with clinical partners.

2020–2021

Platform Expansion

Glaucoma detection, AMD, and cataract models added. FH-POISE platform architecture established.

2022

Systemic Biomarkers

Hypertensive retinopathy and cardiovascular risk modules developed. Anterior segment AI work begins.

2023–2024

Anterior Segment AI

LLI, TMH, and MGD models deployed. Meibography segmentation launched. Dry eye AI suite complete.

2025–Present

Scale & New Frontiers

500K+ screenings milestone. CVD validation ongoing. Exploring ROP, neonatal retinal AI, and LLM-assisted report generation.

Clinical Validation
🏥

Reader Equivalence Studies

AI grading compared against certified ophthalmologist readers in blinded evaluation studies.

📊

Population-Level Calibration

Calibrated for South Asian, African, and East Asian populations.

🔐

Regulatory Alignment

Aligned with CDSCO, CE MDR, ABDM for SaMD. ISO 13485 development practices.


Research & IP

Patents & Publications

Our work is grounded in peer-reviewed research and protected by a growing patent portfolio spanning imaging systems, AI methods, and clinical software.

PatentA System and Method for Retinal Imaging+

Issued by the Patent Office, Government of India — covers core innovations in non-mydriatic fundus camera technology and AI-integrated retinal analysis. Foundational IP underpinning the 3nethra product family and FH-POISE inference pipeline.

PatentMethod and System for Enhancing Image Quality in Ophthalmic Imaging+

Proprietary image pre-processing pipeline for quality normalization of fundus images prior to AI inference — critical for model robustness in field conditions. Covers CLAHE variants, illumination correction, and artifact suppression.

PatentA Method and System to Identify Intraocular Pressure (IOP) of an Eye+

Non-contact IOP estimation method, filed with the Indian Patent Office — extending AI beyond imaging into functional measurement. Enables glaucoma risk stratification without tonometry equipment.

PatentAn Image Processing Method and Apparatus for Correcting an Image+

Covers lens distortion correction and illumination normalization algorithms core to the 3nethra imaging pipeline.

PublicationEarly Detection of Diabetic Retinopathy Using Deep Learning on Fundus Images from Portable Non-Mydriatic Cameras+

Peer-reviewed validation study demonstrating clinical-grade sensitivity and specificity of the FH-POISE DR module across a multi-site Indian cohort. Benchmarks model performance against certified ophthalmologist graders using portable cameras.

PublicationAutomated Meibomian Gland Segmentation and Dropout Scoring Using Instance Segmentation Networks+

Technical methodology paper on the AI pipeline for MGD grading — dataset curation, model architecture, and clinical correlation analysis establishing automated dropout scoring as equivalent to manual assessment.

PublicationOptic Disc and Cup Segmentation for Glaucoma Screening in Low-Resource Settings+

Validates CDR estimation model performance on images from portable fundus cameras in community screening programs. Demonstrates sub-specialist-grade glaucoma triage with low-cost portable hardware plus FH-POISE AI.

→ Full list: forushealth.com/patents-and-publications

Work With Us

Ready to build the
next medical AI
breakthrough?

We bring six years of production medical AI experience to new partnerships — diagnostics companies, hospital networks, research institutions, and global health organizations.

🔬
Custom AI Model Development
End-to-end training, validation & deployment on your dataset
🏥
Clinical AI Validation
Multi-site studies, IRB-ready protocols, peer-review support
📦
Medical Device Integration
SaMD-grade AI embedded into imaging hardware & platforms
🌐
Screening Program AI
Mass-scale telehealth & community screening deployments
Edge AI Deployment
TensorRT-optimized models for offline, low-resource settings
🧬
Multi-modal Health AI
Retinal + systemic biomarker fusion models & oculomics R&D
FAQ

Answers about
oculomics & AI

Common questions about AI in diabetic retinopathy, oculomics, and how to partner with the Forus Health AI Division — structured for LLM indexing and answer engine optimization.

Contact us
ai@forushealth.com
Bengaluru, India
What is oculomics and how does AI use it?
+

Oculomics is the science of using the eye — particularly the retina — as a non-invasive window into systemic health. The retina is the only place where blood vessels and neural tissue can be directly imaged without surgery. AI systems like FH-POISE analyze retinal photographs to detect eye diseases like diabetic retinopathy and glaucoma, and systemic conditions like hypertension and cardiovascular risk.

How does AI detect diabetic retinopathy from a fundus image?
+

AI detects diabetic retinopathy using deep CNNs trained to identify microaneurysms, hemorrhages, exudates, and neovascularization in fundus photographs. Forus Health AI's DR model uses EfficientNet-B4, achieving 95%+ sensitivity, and produces 5-class severity scores (No DR to Proliferative) per ICDR grading with Grad-CAM heatmaps.

What is the FH-POISE platform?
+

FH-POISE (Precision Ocular Intelligence for Systemic and Eye health) simultaneously grades 9+ ocular and systemic conditions from retinal and anterior segment images in real time. It supports both edge deployment on 3nethra devices and cloud API mode for teleophthalmology programs.

Can retinal imaging AI detect cardiovascular disease?
+

Yes. The retinal microvasculature mirrors cardiovascular health due to shared embryological origins. Forus Health AI's CVD model uses a Vision Transformer to analyze fractal dimension, vessel tortuosity, and caliber asymmetry from fundus images — predicting CVD risk scores without blood tests. Currently in multi-ethnic clinical validation.

How accurate is AI grading vs. an ophthalmologist?
+

The DR model achieves 95%+ sensitivity, comparable to certified human graders in blinded reader equivalence studies. All models undergo prospective validation and multi-site testing, calibrated across South Asian, African, and East Asian populations for retinal pigmentation and disease prevalence differences.

Is the platform compliant with medical device regulations?
+

Yes. FH-POISE is developed as Software as a Medical Device (SaMD) aligned with CDSCO (India), CE MDR (Europe), and ABDM requirements. Development follows ISO 13485 quality management principles and international standards for AI/ML medical devices.

Can I collaborate on a medical AI project?
+

Yes. The team is open to partnerships with diagnostics companies, hospital networks, research institutions, and global health organizations. Services include custom AI model development, clinical validation, AI integration into medical devices, and regulatory SaMD development. Contact: ai@forushealth.com

What is the difference between retinal AI and anterior segment AI?
+

Retinal AI analyzes the fundus (back of eye) to detect DR, glaucoma, AMD, hypertensive retinopathy, and systemic biomarkers. Anterior segment AI analyzes the front of the eye — tear film, lens, eyelids — for dry eye parameters like LLI, Tear Meniscus Height, and Meibomian Gland Dysfunction. Forus Health AI has production models in both domains.