We build and commercialize medical AI solutions that transform retinal and anterior segment imaging into actionable diagnostic intelligence - for eye disease and beyond.
Our AI Hub is a gateway to the technologies, research and innovations shaping the future of healthcare.
A key area of our work is Oculomics - The science of using the eye as a window into overall health. By analyzing retinal images with advanced AI, we are unlocking insights that extend beyond vision, enabling the early detection of systemic conditions and supporting a future where a simple eye scan can provide valuable information about an individual's overall health.
Beyond our existing AI solutions, we partner with healthcare organizations, medical device companies, startups, researchers and innovators to co-create the next generation of intelligent healthcare technologies. Whether you're looking for custom AI model development, medical device integration, clinical validation, or research collaborations, our multidisciplinary team brings the expertise to accelerate your journey from concept to clinical impact.
Our flagship AI solutions analyze retinal and anterior segment images to deliver multi-condition diagnostic insights - in real time, at point of care.
One of our most advanced AI solutions, it predicts 10-year risk for CVD, aligned with clinically established Framingham's Risk Score (FRS) and (Atherosclerotic Cardiovascular Disease) ASCVD. Leverages retinal vascular geometry - fractal dimension, arteriovenous nicking, vessel tortuosity, caliber asymmetry - as surrogate markers for CVD risk. Using these, our AI system estimates systemic biomarkers including SysBP, HbA1c, total cholesterol and heart age. Composite cardiovascular risk score is generated from non-invasive fundus images, without any blood draw or ECG.
Employs sophisticated deep learning models to instantly evaluate multiple images of the neonatal retina, classifying its severity across clinical stages (1, 2, 3 and above) and identifying it's Zone (I, II, or III) with expert-level accuracy. By meticulously analyzing vascular dilation and tortuosity at the posterior pole, the AI also quantifies and characterizes Plus and Pre-plus disease markers - the critical drivers of treatment decisions. This fast and objective, characterization empowers clinical teams with reliable, decision-ready insights when every second counts to protect a newborn's vision.
Trained on a large corpus of real-world retinal images, our advanced deep CNN-based classifier ensures robust clinical performance. The system looks for clinically relevant biomarkers for DR - including microaneurysms, hemorrhages, exudates, and neovascularization - with a specialized focus on identifying early-stage DR. By mapping findings to the ICDR 5-class severity scale, the AI delivers an immediate, actionable output of referable versus non-referable cases to streamline clinical triage. The assessment is further enhanced by intuitive heatmaps that visually localize lesions, when detected.
Our Glaucoma Analysis Tools features automatic and precise optic disc and cup segmentation for objective cup-to-disc ratio estimation. The system comprehensively evaluates the optic nerve head, identifying critical structural risk factors such as RNFL defects, peripapillary atrophy, disc hemorrhages, and neuroretinal rim notching. By analyzing these subtle markers of damage, the AI instantly categorizes the patient's overall risk into three clear, actionable levels: low risk, glaucoma suspect, or high risk. This automated assessment streamlines early detection and empowers clinical teams to prioritize care where it is needed most.
Our AI solution for age-related macular degeneration (AMD) screening is engineered to detect AMD across all stages - including its earliest onsets. The system analyzes retinal fundus images to precisely identify key biomarkers of progression, ranging from hard and soft drusen deposits to geographic atrophy (dry AMD) and choroidal neovascularization (wet AMD). To support clinical decision-making, the AI generates intuitive heatmaps that visually localize these lesions, ensuring a rapid, objective, and clear assessment that streamlines patient triage and preserves vision.
This system is designed to evaluate anterior segment eye images and instantly detect cataract risk. To ensure complete clinical transparency, the system automatically generates a detailed pupil opacity representation for at-risk cases, highlighting the exact areas of localized cloudiness within the pupil region. By delivering this immediate visual evidence directly into clinical workflows, the AI provides objective validation that streamlines patient education and supports surgical triage.
By analyzing subtle microvascular alterations in retinal images, this AI system detects clinical markers such as arteriovenous nicking, focal arteriolar narrowing, and the classic copper or silver wiring of arterioles, alongside retinal hemorrhages - and provides heat-map localization for the same. This automated evaluation provides clinicians with an objective assessment of retinopathy driven by systemic hypertension.
This AI system analyzes a video spanning a few blinks to look for subtle interference fringe patterns (similar to colors on soap bubbles), within the tear film's lipid layer component to score its thickness. Furthermore, the system automatically tracks and quantifies patient dynamics - including average blink frequency and average inter-blink duration - providing clinicians with a comprehensive assessment to guide personalized treatment strategies.
This AI solution provides an automated measurement of tear meniscus height from anterior segment images using semantic segmentation of the tear that pools above the lower eyelid. It provides an objective tear meniscus height measurement (mm) that serves as a rapid and reliable biomarker for aqueous-deficient dry eye screening.
Our Meibomian Gland Dysfunction (MGD) AI solution is designed to automatically segment and quantify gland morphology from infrared meibography images. The system meticulously computes precise, objective metrics including gland atrophy percentage, a tortuosity index, and the gland-to-gap ratio, culminating in a standardized meiboscore. This comprehensive, fully automated assessment transforms complex structural data into actionable insights that help to detect early meibomian gland loss, track disease progression and choose appropriate interventions.
By leveraging our patented computer vision algorithms, this system automatically segments the cornea into distinct sectors, tracking micro-fluctuations in the tear film stability and break-up over time. The AI detects the exact millisecond and precise location of tear film rupture across each zone, mapping localized evaporation patterns without the need for irritating dyes.
Performance figures are rounded aggregates of multi-site studies, subject to change.
Great healthcare innovations begin with the right collaboration. If you're developing the next breakthrough in healthcare and need deep AI expertise, we're here to help. With years of experience building AI solutions for ophthalmology and medical imaging, we're expanding our expertise to help organizations accelerate innovation across healthcare. If you're looking for a trusted AI partner, let's start the conversation.
Select all that apply - we'll tailor our response accordingly.
Help us understand the clinical scope and current stage.
This helps us scope a realistic collaboration plan.
Share more context - or tell us anything not covered above.
Last step - tell us who you are so we can route your enquiry to the right team.
Thank you for completing the questionnaire. Our team will review your answers and reach out within one business day.
Field-deployed across 65+ countries, our AI systems have processed hundreds of thousands of real patient screenings.
500K+ screenings milestone. CVD validation ongoing. Exploring ROP, neonatal retinal AI, and LLM-assisted report generation.
LLI, TMH, and MGD models deployed. Meibography segmentation launched. Dry eye AI suite complete.
Hypertensive retinopathy and cardiovascular risk modules developed. Anterior segment AI work begins.
Glaucoma detection, AMD, and cataract models added. FH-POISE™ platform architecture established.
First DR grading model trained on proprietary Forus fundus dataset. Proof-of-concept validated with clinical partners.
Glaucoma screening is the attempt to find optic nerve damage before the patient notices any loss of vision. That is harder than it sounds, because glaucoma…
Diabetic retinopathy screening is the routine examination of the retina in people with diabetes to detect vascular damage before it threatens sight. The need in India…
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.
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.
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.
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.
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.
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.
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.
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: converge@forushealth.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 LLT, Tear Meniscus Height, and Meibomian Gland Dysfunction. Forus Health AI has production models in both domains.
