Advisory

I advise medical imaging AI teams on technical decision-making, from early problem framing to R&D validation.

With a PhD in Computer Vision and over ten years of experience in applied medical imaging R&D, I bring structured perspective on problem formulation, data assumptions, experiment design, and technical feasibility throughout the R&D lifecycle.

My work ensures that technical choices, data constraints, and evaluation strategies remain aligned with real-world clinical and operational requirements, so that R&D efforts lead to robust and credible outcomes.

Engagements are scoped to project needs, from focused one-day assessments and technical reviews to longitudinal advisory mandates.

R&D Advisory Framework

A structured overview of how I intervene across the AI R&D lifecycle.

Download Framework PDF

How I Work

I collaborate with MedTech teams through structured technical advisory, either via focused interventions or sustained involvement across project phases.

Some engagements address a specific question, such as feasibility assessment, data readiness, experiment design, or validation strategy, and can be completed in one to three days. Others involve longitudinal advisory support, contributing regular technical input as projects evolve.


The format adapts to project maturity and team structure, with the objective of strengthening judgment and technical defensibility throughout the R&D lifecycle.

Where I Intervene


My advisory work strengthens the AI R&D lifecycle from early framing to long-term technical defensibility.

1. Technical Framing & Feasibility


Clarifying objectives, constraints, problem formulation, and downstream implications before development decisions become locked in.

2. Data & Project Readiness


Identifying structural risks in datasets, infrastructure, documentation, and project setup that may affect development, validation, or deployment.

3. Experiment Design & Evaluation Strategy

Structuring experiments and evaluation protocols to ensure results are interpretable, comparable, and aligned with real-world use.

4. State-of-the-Art Review & Technical Positioning

Reviewing and selecting appropriate methods and approaches in alignment with project constraints and strategic objectives.

5. Ongoing Advisory & Due Diligence

Providing independent technical review of systems, documentation, or R&D programs to support internal decisions, partnerships, or investment discussions, with optional continued advisory follow-up.

Case Study

Project: NIH ChestX-ray14 Data Readiness Evaluation

Dataset Scale: 112,120 images / 30,805 patients

Objective: Applying the VeraDP Data Readiness Protocol to identify the dataset’s strengths, limitations, and risks

Identified Risks:
(Selected examples; the exhaustive list remains proprietary and confidential)

  • Traceability & Provenance: Core documentation refers to an outdated version (CXR8), presenting traceability gaps for the extended 14-disease version.
  • Annotation Reliability: Labeling relies on NLP-based text mining of radiological reports, introducing a structural uncertainty (estimated ~10% error rate).
  • Patient-Level Leakage: The strong imbalance in the number of images per patient indicates that a small subset of patients contributes disproportionately to the dataset (up to 184 images/patient). This creates a significant risk of data leakage if splits are not handled at the patient level.
  • Pathology Sparsity: Extreme label disparities (e.g., Hernia at 0.2%) present a barrier to achieving statistical power for specific clinical claims.

Strategic Outcome:

The evaluation provides a framework for judgment under uncertainty, allowing R&D teams to account for data limitations before locking in technical and validation strategies.

Bar chart showing the distribution of the number of images per patient in the NIH Chest X-ray dataset, highlighting that the majority of patients have very few images while a small subset has a high frequency of repeat scans.
Bar chart showing the frequency of clinical labels in the NIH Chest X-ray14 dataset, illustrating the prevalence of specific pathologies (Infiltration, Effusion).

Who I Work With

  • MedTech startups and scaleups developing AI-based products
  • Healthcare and medical imaging teams advancing AI initiatives
  • Technical and executive leaders seeking an independent sparring partner on AI R&D decisions

What This Enables

  • Clearer technical positioning
  • Stronger evaluation rigor
  • Reduced hidden downstream risk
  • Defensible performance claims
  • Continuity of judgment over time

Why Work with Me

  • Deep Technical Authority
    PhD-level expertise in computer vision, combined with over ten years of applied MedTech R&D.
  • Experience at the R&D–Reality Interface
    Hands-on involvement in projects where research constraints, data realities, and real-world clinical requirements must align.
  • Independent and Structured Perspective
    An external technical reference bringing clarity and rigor to complex discussions.
  • Decision-Oriented Communication
    Complex technical issues translated into structured, decision-ready insight for both technical and executive stakeholders.
  • International and Bilingual Context
    Fluent in English and French, with experience across academic, clinical, and industrial environments.

Working on an AI project?

Let’s define a sound technical approach for your next decision.

Contact