MERIT AI Research

From Ultrasound to Diagnosis in 48 Hours

MERIT AI is our flagship research initiative — a clinically deployed ophthalmic AI system built to screen, classify, and triage 250+ blinding conditions using a portable ultrasound device guided by on-premise AI.

The Problem

A Crisis of Access

India faces a critical shortage of ophthalmologists in rural areas, where the 48-hour diagnostic window determines whether a patient retains their sight.

250+ blinding conditions48-hour critical window1 per 70,000 rural residents

With one ophthalmologist per 70,000 rural residents, delayed diagnosis is the primary cause of preventable blindness across India. The 48-hour window — the critical period where intervention prevents permanent sight loss — is routinely missed. MERIT AI was conceived to bring expert-level diagnostic capability to the point of care, wherever the patient is.

Our Solution

MERIT AI — On-Premise, Zero Cloud

A portable Butterfly iQ3 ultrasound probe feeds into an on-premise AI engine that delivers diagnosis without any data leaving the facility.

  • Butterfly iQ3 portable ultrasound — wireless, hand-held
  • On-premise AI engine — GPU-accelerated, no internet required
  • 4-stage diagnostic pipeline: classify → segment → detect → diagnose
  • Zero-cloud, HIPAA & DPDPA compliant
  • Teleguidance-capable for remote specialist review
Dr. Hadi's Framework

The AIID Research Framework

Application → Implementation → Integration → Dissemination. The four-stage translational philosophy that drives every decision in MERIT AI's development.

A

Application

25 years of clinical vision translating into a defined problem: preventable blindness caused by delayed ophthalmic diagnosis. The clinical need drives everything.

Identifying 250+ blinding conditions with a 48-hour critical window across under-served regions.

I

Implementation

Research, phantom lab training, animal testing, and data collection. Phase 1 (Classification) complete at 91% accuracy; Phase 2 (Segmentation) active.

175 phantom images, 600 frames/scan, 10,000-image collection target, De Cure patient pipeline.

I

Integration

Software development, on-premise deployment, and clinical workflow embedding. Zero-cloud, HIPAA/DPDPA compliant. GPU-accelerated inference on Butterfly iQ3 input.

Docker-orchestrated stack, SHA-256 data security, RBAC, teleguidance-capable interface.

D

Dissemination

Making the technology available — in rural clinics, District Hospitals, and globally via teleguidance. NIH SBIR grant in pursuit for Phase I expansion.

Athreya Inc. (US) + Validus Institute co-applicant. Target: accessible AI diagnostics worldwide.

Research Focus

What We Are Working On

Active investigation across ophthalmic imaging, biometry, and clinical AI deployment. Peer-reviewed output is listed here once it carries a resolvable DOI.

Automated Ocular Biometry

Active

Deriving axial length and related biometric measurements from B-scan ultrasound without manual calliper placement, so that measurements are reproducible between operators rather than dependent on individual technique.

U-Net globe localisationDeterministic meridian extractionOperator-independent measurement

Optic Nerve Sheath Diameter Assessment

Active

Standardising how optic nerve sheath diameter is measured on ocular ultrasound, including where along the nerve the measurement is taken — a known source of disagreement between studies.

Standardised measurement depthInter-observer variability analysis

Portable Point-of-Care Ultrasound

Active

Evaluating handheld ultrasound for orbital assessment outside tertiary centres, where access to conventional imaging is limited. Focus on what portable hardware can and cannot reliably resolve.

Handheld probe evaluationTeleguidance workflowsLow-resource deployment

Phantom Lab & Synthetic Data

Active

Building physical eye phantoms and synthetic B-scan datasets so that algorithms can be developed and stress-tested against known ground truth before any clinical data is involved.

Physical eye phantomsSynthetic B-scan generationGround-truth validation

On-Premises Clinical AI

Active

Running diagnostic models inside the clinic rather than sending patient imaging to third-party infrastructure, so that data residency and DPDPA obligations are met by architecture rather than by policy.

On-premises inferenceData residency by designDPDPA-aligned deployment

Clinician-Supervised Decision Support

Exploratory

Positioning model output as decision support reviewed by an ophthalmologist, including how confidence is surfaced so that a clinician can tell when the system is uncertain.

Confidence reportingOphthalmologist-in-the-loop review

Interested in Collaborating?

We welcome research partnerships, clinical data contributions, and institutional collaborations that advance MERIT AI toward full clinical deployment.

Contact Us