Vision · Healthcare · Patents

From research signals to real-world systems.

Six inventions, explained simply: helping computers understand where we look, how we interact, and what everyday health signals can tell us.

Soumil ChughSeptember 20266 minute read
01 · The common pattern

Useful AI begins with an unreliable signal.

A face image, a tiny reflection in an eye, watch measurements, or a photo of a blood sample can all contain useful information. The engineering challenge is making that information dependable enough to act on.

My work across computer vision and healthcare follows the same path: isolate a useful signal, understand its uncertainty, design for the device it must run on, and turn the result into a clear user action.

A note on scope

I am an inventor on 15 patents. This article explains six families with public records and links; filed work without a public document is not described as published.

02 · Computer vision

Make gaze tracking work outside the lab.

High-end eye trackers can use infrared cameras, carefully placed lights, and controlled conditions. Consumer devices do not always have that setup. These inventions attack different parts of that gap.

Open the public patent ↗
01

Estimate gaze on ordinary devices

Fuse information from the whole face with the eye that is most visible. The model keeps head pose and fine eye detail together while remaining suitable for mobile hardware.

Granted US patent
02

Track with one corneal reflection

Traditional geometry may depend on several reflections from infrared lights. Using one reflection reduces hardware complexity and keeps tracking possible when movement hides the others.

Published family
03

Calibrate once, simplify normal use

Use controlled calibration to learn person-specific eye geometry. During normal tracking, estimate gaze without requiring the same known light-source setup.

Published family
04

Let eyes handle distance and hands handle precision

Gaze quickly identifies a region across a large screen. A mouse, touchpad, or pen finishes the precise selection, avoiding the jitter of eye-only pointing.

Published family
03 · Healthcare

Turn passive signals into timely guidance.

Healthcare data is useful only when the full path works: collection, quality control, modeling, interpretation, and a clear next step for the patient or clinician.

Continuous signals from wearables

The digital-biomarker patent describes using signals from devices such as watches and phones to model correlations with blood characteristics relevant to cardiorenal metabolic conditions. The goal is not to present a watch as a laboratory; it is to make changes between clinical measurements more visible.

Read WO2025106664A1 ↗

Check an at-home sample before it travels

The sample-card patent uses image processing to judge whether an at-home biological sample is likely usable. Giving feedback before shipment can avoid waiting days for a laboratory to reject a poor sample.

Read WO2023091455A1 ↗
04 · Research to deployment

The last mile changes the research question.

Hardware is part of the modelA strong method must fit the cameras, lighting, compute, battery, and memory available in the actual device.
Failure needs a product responseA low-confidence output should trigger a retake, recalibration, or fallback—not an unexplained number.
Speed changes usabilityReducing inference latency matters because gaze and interaction systems sit inside a live feedback loop.
Accuracy is contextualHead motion, lighting, sensor gaps, and user behavior must be represented in validation, not removed from it.
Combine complementary inputsFace plus eye, gaze plus pointer, and several biomarkers are stronger than treating one signal as complete.
The output must help someoneThe useful endpoint is a cursor action, a quality instruction, or a timely health signal—not merely a model score.
The through-line

Across vision and healthcare, the work moved from algorithms to complete loops: sense, estimate, validate, and respond.

05 · Public evidence

Patent records and research foundations.

These links lead to the public documents behind the explanations above.

PatentMethods and devices for gaze estimationUS12175014B2 ↗
PatentGaze tracking using one corneal reflectionWO2024059927A1 ↗
PatentGaze tracking and gaze tracking calibrationWO2025113309A1 ↗
PatentMethods and systems for gaze-assisted interactionUS20240211034A1 ↗
PatentDigital biomarkers for cardiorenal metabolic conditionsWO2025106664A1 ↗
PatentQuality control of biological sample cardsWO2023091455A1 ↗
PaperCorneal-reflection detection and matching using deep learningICPR ↗
ThesisAn Eye Tracking System for a Virtual Reality HeadsetUniversity of Toronto ↗
More work

Explore the projects, papers, and complete patent list.

View research & patents →