In short. What the scan measures, what the software model adds, and the point at which a surgeon's judgement, not the software, decides the plan.
Key points
- A planning system is authorised to segment, measure and generate a plan.
- It is not authorised to determine what should be done, and a clearance that names the technical task is not a statement about the operation.
- The distinction is worth keeping, because a precise interface can make a judgement look like an output.
The mechanism claimed for three-dimensional planning is straightforward and mostly true as far as it goes: measure the structure accurately, decide the positions deliberately, and transfer the decision precisely. The interesting part is where the mechanism stops, because the gap between what is computed and what is decided is wider than the presentation suggests.
What the scan measures
Cross-sectional imaging records density in three dimensions, which is why it can distinguish bone from soft tissue and why it can show relationships that a flat film flattens. What it records is a position at a moment, with the person lying still in one posture. It does not record how tissue behaves under load, how it heals, or how a face looks in motion, and those are not small omissions. They are the things a patient is usually asking about.
What the model adds
The model adds manipulation and repeatability. Segmented structures can be moved, measured and compared, and a proposed position can be revisited weeks later without anything having been done to anybody. That is a real gain, and it is worth separating from the claim that the model knows where the structures should go. It does not know anything; it holds a decision in a form that can be examined.
Where judgement still decides
Somebody has to choose the target. How much movement, in which direction, at the cost of what, and whether the soft tissue will tolerate it — none of that is in the data. Experienced surgeons reach different plans from the same scan, and that is not a failure of the software. It reflects the fact that the plan is a judgement about a person, and judgements are not computed.
The software holds the plan, not the decision
A planning system is authorised to segment, measure and generate a plan. It is not authorised to determine what should be done, and a clearance that names the technical task is not a statement about the operation. The distinction is worth keeping, because a precise interface can make a judgement look like an output.
Where the errors enter
Error enters upstream and propagates. Segmentation boundaries are traced, and a boundary traced slightly wrong moves everything built on it. A scan taken in an unhelpful position or carrying an artefact does the same. Because the model is internally consistent, the result of a bad input looks as clean as the result of a good one, which is exactly what makes it hard to notice.
Three things the plan cannot tell you
- How the soft tissue over the moved structure will behave, settle or age.
- Whether the movement is worth its cost in healing, recovery and risk.
- Whether the person the plan belongs to wants the result it describes.
The mechanism is real and it is narrow. Read it as a way of holding a judgement steady and transferring it accurately, and most of the claims made around it become easier to sort.
Frequently asked questions
What does planning software actually compute?
It segments a scan into the structures that matter, measures relationships between them, and lets those structures be moved on screen. What it does not do is decide where they should go. The software holds a plan steady; the plan itself comes from a surgeon's judgement about the person in front of them.
Where does a planning error come from?
Almost always upstream. A boundary traced slightly wrong, a scan taken in an unhelpful position, or an artefact in the imaging feeds straight into the model, and everything computed afterwards inherits the mistake. A plan built on a poor scan is not an approximate plan; it is a precise plan of the wrong shape.
Does the plan decide the operation?
No. A plan describes intended positions. Whether those positions are worth achieving, and what happens to the soft tissue over them, are questions the plan does not address. Surgery still turns on healing, blood supply and how someone ages afterwards, none of which appear in the model.
Risks & Limitations
- A rendered simulation is an illustration of a plan, not a prediction of how a face will look.
- A plan built on a poor scan, or on a boundary traced wrongly, is a precise plan of the wrong shape.
- Planning software, printed guides and patient-facing images sit in three regulatory classes, and one approval is not another.
- No study has shown that planning lowers the overall complication rate.
- A scan records structure in one posture, and does not replace an examination of how tissue behaves.
When to Seek Care
- A wound that is opening, or spreading redness, warmth or discharge — contact the service that holds your records.
- Fever, or pain that is worsening rather than settling after an operation.
- Bleeding that does not stop with gentle pressure.
- If you were shown a simulation and are unsure what it represented, ask the team that showed it to you, and ask to see the plan behind it.
References & Further Reading
- U.S. Food and Drug Administration (FDA) — cleared and approved surgical planning software, guides and patient-specific implants
- European Medicines Agency (EMA) and national competent authorities — medical device regulation and custom-made device guidance
- National Medical Products Administration (NMPA, China) — approved medical devices and their indications
- National Institute for Health and Care Excellence (NICE, UK) — guidance on imaging and surgical planning
- Cochrane Library — systematic reviews of computer-assisted surgery
This page is patient education, not medical advice, and it does not cite individual studies. It reviews evidence and regulation; it is not a booking page and does not recommend a treatment. Discuss your own case with a qualified clinician. To ask a question about this review, see Contact & Consultation.