Long before surgical intelligence or artificial intelligence became fashionable phrases, I was drawn to the mathematics that describes structure in the physical world. Geometry is the most elementary and oldest of the sciences, yet it remains the most powerful way to understand complexity through precision.
During my PhD in Computer Vision at Queen Mary University of London, I worked on one of the hardest problems in perception: identifying and matching patterns in low-textured images. When there are no obvious edges, no clean features, no helpful contrast, machines struggle. Solving that requires precision, mathematical modelling, and a deep understanding of geometry.
It turns out operating theatres are not so different.
Surgery is complex, high-stakes, and often visually ambiguous. Critical signals are subtle. Errors are rarely dramatic in the moment, but their consequences can be. Having witnessed the impact of poor healthcare infrastructure in India, I became deeply motivated to work on problems that matter beyond academic benchmarks.
Academic Journey
My academic journey was made possible through scholarship and support. I studied mathematics at the Indian Institute of Technology Madras after securing a top national rank.
After IIT, I spent six years as a Lecturer in Mathematics at Alfaisal University in Saudi Arabia, teaching undergraduate courses in Precalculus, Calculus, Statistics, Differential Equations, Numerical Methods, and Linear Algebra. Alongside teaching, I received two internal research grants in computer vision and served on various academic and administrative committees. That period shaped how I think about rigour, structure, and communicating complex ideas clearly.
I was then awarded a full Principal’s Postgraduate Research Studentship at Queen Mary University of London for my doctoral research in computer vision.
Without that support, I would not be here.
I have always felt a responsibility to return that investment in the most meaningful way I can. For me, that means applying mathematics and engineering to problems that improve real systems at scale. Surgery touches millions of lives every year. If we can reduce preventable error and build reliable infrastructure around it, the societal impact is significant.
That conviction is one of the primary reasons I chose to build Scalpel.
It is also one of the reasons I wake up and work on it every day.
After ten years in academia, I left to embark on a new journey. I envisioned how modern technology could transform the entire surgical ecosystem and prevent errors during surgery.
Dissertations
Local Surface Models for Stereo Vision
Queen Mary University of London·Computer Vision·PhD·2018
Certain Topics on the Linear Complementarity Problem
Indian Institute of Technology Madras·Mathematics·MSc·2008
Bridging Mathematics and Medicine
As a trained mathematician and computer vision expert, my work primarily involves encapsulating the geometric structures in a scene using algebraic and machine learning models. That same discipline now underpins my approach to surgical safety challenges in the healthcare pathway.
In 2018, I co-founded Scalpel and now serve as its CTO.
At Scalpel, we are bringing the best of modern technology to the world of surgery by augmenting surgical intelligence using AI. We are building the infrastructure for Connected Surgical Intelligence — where every tray is tracked, every step is validated, and every stakeholder stays in sync.
We build surgical intelligence systems that transform operating theatres into measurable, data-driven environments. By combining computer vision, machine learning, and multimodal sensing, we analyse surgical workflows in real time, detect abnormalities, verify protocol compliance, and track instruments automatically.
Building Connected Surgical Intelligence
Surgery today relies on fragmented systems, manual checks, and institutional memory. What is missing is a connected intelligence layer that brings visibility, verification, and coordination across the entire surgical pathway.
Our work is structured around three core pillars:
Instrument Intelligence
We build systems for automated surgical instrument detection and tray verification. Every instrument can be tracked. Every count can be validated.
This reduces the risk of retained foreign objects, strengthens compliance, and introduces accountability beyond manual processes.
Workflow Intelligence
We analyse surgical workflows in real time. By combining computer vision, machine learning, and contextual signals, we understand the sequence of surgical steps and verify adherence to protocol.
This transforms invisible deviations into observable data.
Operational Intelligence
Surgery is also a logistical system. We provide data-driven visibility into inventory management, tray utilisation, and workflow coordination.
This synchronises clinical and operational stakeholders and creates continuous feedback across the system.
Connected Surgical Intelligence is not about adding another tool to the theatre. It is about creating the infrastructure that connects them.
Building Systems That Earn Trust
My role is to ensure that what we build is scientifically grounded, operationally robust, and trusted in high-stakes environments. In healthcare, innovation alone is not enough. It must be precise, reliable, and accountable.
Throughout my academic and entrepreneurial journey, my work has been supported through competitive research funding and innovation grants.
At Queen Mary University of London, I was awarded the Principal’s Postgraduate Research Studentship, covering full tuition and living expenses for three years during my PhD. The studentship recognised the strength and originality of my research in computer vision and mathematical modelling.
At Scalpel, our work in surgical intelligence has been supported by multiple Innovate UK grants. These competitive awards validated our early work in applying AI to surgical safety and helped accelerate the development of our infrastructure for Connected Surgical Intelligence.
As CTO, I am involved in various machine learning and computer vision projects. I currently lead the surgical instrument detection project, which has a significant impact, from automatic detection of retained foreign objects to enabling robotic surgery systems.
Leadership & Philosophy
Technology in healthcare carries responsibility.
My approach to leadership is grounded in mathematical rigour and systems thinking. Complex problems are rarely solved by isolated optimisation. They require structure, discipline, and a clear understanding of interdependencies.
At Scalpel, I focus on building teams that value precision over hype and robustness over shortcuts. In high-stakes environments, elegance is not enough. Systems must perform reliably under constraint, uncertainty, and scrutiny.
I believe infrastructure should be engineered with long-term accountability in mind. Models evolve. Tools improve. But the underlying system architecture must remain coherent, interpretable, and defensible.
As CTO, my role is not only to drive innovation, but to ensure alignment — between research and product, between engineering and clinical reality, and between ambition and responsibility.
Connected Surgical Intelligence is a technical challenge. But it is also a leadership challenge.
Building it properly requires patience, discipline, and a commitment to earning trust over time.
The Foundation
We are only at the beginning of making surgery measurable.
For decades, operating theatres have relied on human memory, fragmented systems, and invisible processes. The hardest problems in surgery are not purely technical. They are systemic. Workflow gaps. Communication breakdowns. Risk that accumulates quietly until it becomes visible too late.
These are not solved by adding isolated tools. They require connected systems that understand context, sequence, and consequence.
Connected Surgical Intelligence is not a feature or a product. It is an infrastructure layer.
A foundation that ensures every tray is tracked, every step is validated, and every stakeholder stays in sync. An intelligence layer that makes surgical processes observable, accountable, and continuously improvable.
Mathematics gave us the tools to model structure.
Computer vision enabled machines to see.
Now we must engineer systems that can understand.
Isolated AI models will not define the next decade of surgery. The infrastructure that connects them will.
That is the foundation I am building.