Owned and led by clinicians. Healthcare is all we do.
We enrich healthcare data with clinical annotation, expert evaluation and review, for healthcare AI teams, annotation companies and researchers. Our in-house radiologists work together in person. Engage us directly or bring us into your delivery, with clinician sign-off on every engagement.
A T2 slice, outlined by one of our radiologists.
Watch the film: the second look, 12 s, silent01 / Two ways in
Camry Labs is owned and led by clinicians. Some teams engage us directly; others bring us into a delivery they run. Neither is the side door: the same radiologists, the same review and the same signature stand behind both.
Healthcare AI teams and research groups
You bring the model, the data or the study. We agree the task and the clinical scope with you, do the work, and deliver in your format with a clinician’s sign-off. There is no intermediary.
Discuss a projectAnnotation and data companies
You keep your platform, your project workflow and your customer. We join as the clinical part of your team, work to your project instructions and review criteria, and take responsibility for what we deliver.
Discuss working togetherYour platform, our clinical team. Our radiologists work in person at Camry Labs while using your project environment, a partner platform or a workspace agreed for the project.
This is hands-on experience within our team. The logos identify the platforms and tools. They do not indicate a partnership or an endorsement.
02 / Services
Each is a data service done by clinicians. We agree the task and the acceptance criteria with you, do the work, write down the decisions on hard cases, and sign off what we deliver.
Radiology annotation is our core specialty; we confirm clinical fit, reviewers and deliverables during scoping. None of these is regulatory approval, and none shows that a model is fit for clinical use.
Three kinds of work, on one instrument
Follow the annotation, review and correction. Drag the bar to replay any plate.
TrainAnnotated training data
You need labelled medical data.
Clinicians annotate to your label definitions and examples. For imaging, our in-house radiologists do the work together in one room, and every radiology annotation is reviewed before delivery.
Discuss this service: TrainEvaluateExpert review of model outputs
You need clinicians to judge what a model says.
Clinicians assess each output against criteria agreed with you: what is supported, what is wrong, what is missing, and why. Difficult cases are discussed and the reasoning is written down.
Discuss this service: EvaluateValidateReview of existing labels
You have labels and need them checked.
Radiologists review labels you already have against the instructions they were made under, correct what needs correcting, flag what is uncertain and leave the rest alone, with the reasons recorded.
Discuss this service: Validate03 / Radiology
Ultrasound, CT, MRI and X-ray, annotated by radiologists who sit together in our office. Every radiology annotation is reviewed by our in-house radiologists before delivery, and the people who decide whether it is good enough are the people who would have to rely on it in practice.
Ultrasound has equal standing with CT, MRI and X-ray here. Segmentation, landmarks and measurement across imaging modalities.
A vessel outlined and measured, on the lab’s screen
A demanding image for a machine to trace. Speckle, shadow and a moving probe scatter the edges a computer finds. Our radiologists outline regions, place calipers and landmarks, and apply structured labels to your protocol, frame by frame.
Discuss an ultrasound projectVessel outline and calipers on a liver ultrasound.
A stroke lesion segmented, on MRI
The same line, slice by slice. CT and MRI are read through a volume; an X-ray as one projection. Our radiologists segment structures, mark findings with structured labels, place landmarks and review annotations you already have, to the schema we agree with you.
Discuss a CT, MRI or X-ray projectLesion segmentation on an axial T2 MRI.
Each is a clinical decision.
Contours, masks and region labels, in 2D images and 3D volumes.
Finding locations and structured labels, at image, series or study level.
Anatomical points, coordinates and attributes, to an agreed schema.
A radiologist’s assessment of annotations you already have.
Difficult cases go onto a shared screen. Colleagues examine the interpretation together against the project instructions, move the line where they agree it belongs, and write the ruling down, so every later case is treated the same way.
From the first outline to a shared decision, with the ruling recorded.
Clinical direction and quality oversight
Dr Yash Jakhotia
Radiology
MBBS, MD, DNB
One room, one reading of the instructions. When a definition is unclear, it is settled once, out loud, and recorded for everyone.
Difficult cases are raised for discussion as the work progresses. Where a project needs independent readings, we record them before any discussion: sitting together does not make a reading independent, so we do not claim that it does.
Radiologists take part from the first conversation to the sign-off. Qualified engineers and technicians look after the tools and the working environment; the clinical work stays with the clinicians.
04 / How we work
Start with a focused pilot, in your workflow or ours. A clinician is in the conversation from the first brief to the sign-off, and the delivery carries the review records agreed for your project.
Delivered in the format you need. Review records, decisions and a summary of corrections accompany it, as agreed for the project, so your own quality process has something to read.
What a delivery can include
Labels, masks, coordinates or judgements in the schema we agreed.
Which items were reviewed, corrected, or returned flagged as uncertain.
The rulings on hard cases, and the instruction version each applies to.
What changed after review, and why.
What was checked against the agreed acceptance criteria, and who approved it.
Signed off by a clinician. Every engagement carries a clinician’s sign-off before delivery. Every radiology annotation is reviewed by our in-house radiologists.
05 / Pilots and research collaborations
New imaging technologies and new kinds of model raise questions no annotation brief answers yet: what to mark, how to judge it, where expert readers disagree. We take these on as scoped pilots or research collaborations, with the clinical question agreed first and the findings written down.
Anatomical annotation and segmentation review for volumetric ultrasound, whole-body and body-composition imaging, and other new imaging technologies.
Anatomical critique of synthetic medical images: what is plausible, what is inconsistent, and what needs further investigation.
Difficult-case evaluation and analysis of model failures, with each of a model’s statements linked to the image evidence for or against it.
Studies of uncertainty and disagreement: independent initial readings, recorded before any discussion, and the team discussion recorded separately.
Frame selection, view annotation and acquisition-quality assessment, so a model learns from the frames a sonographer would keep.
Each is an offer to find out together, not a claim of past work. A pilot ends with a record of what was marked, judged and disagreed on, not a verdict on your technology.
06 / Research
Research groups engage us for study-specific annotation, expert image review and assessment of AI outputs, to the study protocol. Our clinicians bring experience from collaborative healthcare AI research, some of it published.
Research contributions by our clinicians
RadLE 1.0 and 2.0 compare AI image interpretation with radiologists. The second version also examines confidence, reliability and when to defer to a specialist.
CRASH Lab credits Dr Yash Jakhotia as a contributor to RadLE 2.0.
RadLE 1.0 paper (opens in a new tab)RadLE 2.0 report (opens in a new tab)
A chest X-ray research dataset connecting clinical reasoning with visual attention.
Dr Yash Jakhotia and other radiologists in our team contributed as individuals through the Global Radiology Consortium.
Before any project data is shared, we settle three things with you in writing.
Who needs access, where the work happens, and whether anything may be downloaded or copied locally.
How data moves, where it is stored, how it is protected, how long it is kept and who deletes it.
The agreements your project requires, who owns the data and the labels, and what each may be used for.
This website is for project briefs only. It has no patient-data upload, and patient images or identifiable health information must never be sent through it. Tell us which agreements and controls your project requires; we do not claim certifications on this page.
The practical things teams want to know before they write to us.
For procurement and research reviews, the same facts in one document: the capability brief.
Either. Healthcare AI teams and research groups engage us directly. Annotation and data companies bring us into their delivery as the clinical part of their team. In both cases our in-house radiologists do the clinical work and a clinician signs off what we deliver.
You coordinate the wider project and keep your platform and your customer relationship. Our in-house radiologists provide specialist annotation and review within the responsibilities we agree, following your project instructions, review criteria and delivery format.
Write to contact@camrylabs.ai or send a brief through the form on the homepage: the kind of data, the task, your label definitions or review criteria, volume, platform and timing. Your brief is saved for our team, we reply by email, and a clinician joins the first conversation about scope. A pilot on a representative sample usually follows.
Yes. We can scope a representative sample to align on instructions, review expectations and delivery format. Sample size, timing and price depend on the task and are agreed before work begins.
Our in-house radiologists lead annotation and clinical review, working together in the same office. Every radiology annotation is reviewed by our in-house radiologists before delivery, and every engagement carries a clinician’s sign-off. Dr Yash Jakhotia provides clinical direction and quality oversight. Qualified engineers and technicians support the tools and the working environment.
No. We make and review the data. Train means annotated training data, Evaluate means expert review of model outputs, and Validate means review of labels you already have. None of these is regulatory approval or a statement that a model is fit for clinical use.
Medical imaging is where the lab is deepest today: ultrasound, CT, MRI and X-ray. We agree the anatomy, the annotation task and the review criteria with you before work begins. For other kinds of healthcare data, tell us what your project needs and we will say plainly whether we can do it well.
Yes, as a scoped pilot or a research collaboration. We agree the clinical question first, work through a representative sample with you, and write down what we learn, including where our readers disagree. What we deliver is the record of that work, not a claim about your technology.
Yes. We can work in your platform, a partner environment or a workflow arranged for the project. Access, tooling and responsibilities are agreed during scoping.
Tell us the format and schema your workflow needs. We confirm compatibility with the chosen platform and agree the delivery contents before production. A sample export can be checked first.
The kind of data, the complexity of the task, volume, review requirements and the working platform. A representative sample helps establish a practical plan and quote. Pilot size, minimum scope and milestones are agreed for each engagement.
We do not claim any certification on this website. Access, transfer, storage, deletion, confidentiality and permitted use are agreed in writing for each project before any data is shared, and we say plainly which controls we can and cannot provide.
Ownership, permitted use, delivery rights and any restrictions on reuse are defined in the project agreement before work begins.
Tell us what the project needs: annotated data, expert review of model outputs, a check of labels you already have, or a pilot on something newer. Say whether you are engaging us directly or bringing us into a delivery, and which platform you work in.