Book a demo

Surgical Navigation AI Patents: Who Leads, Where Filings Cooled 2026

Surgical Navigation AI Patents: Who Leads, Where Filings Cooled 2026
https://www.patsnap.com/resources/blog/rd-blog/surgical-navigation-ai-and-machine-learning-patent-landscape/ · Patsnap · data cut-off 2026-07-31 · downloaded from the live page
Patent Landscape · Biomedical Devices
Surgical Navigation AI and Machine Learning Patents
  • Filing activity peaked in 2020 at 38 families and has since flattened rather than kept climbing, with 2022 sitting at 30 and the trend roughly flat into the most recent data.
  • Registration and segmentation claims dominate citations the five most-cited records are all built around image-guided registration or automated anatomical segmentation, not general AI methods.
  • Momentum has swung to near zero for several established filers multiple assignees show 0 families in the latest year and a -100% year-over-year change, opening room for new entrants.
Get a prior-art report on your approach
211
Published Records
42%
Top-5 Share of All Records
-32%
Filing Growth 2021→2024
US
Leading Jurisdiction

Filing growth compares 2021 (25 records) with 2024 (17) — a three-year span. 2024 is the most recent year we treat as complete: publication lags filing by roughly 18 months, so 2025 onwards are still filling in and any growth rate that ends there would understate the field. Top-5 share is the combined record count of the five largest assignees divided by all 211 records in scope (CR5), not by the ranked leaders only.

Published byPatsnap Research··7 min readSourced from Patsnap Eureka
Overview

What the patent record shows

Surgical navigation AI sits at the intersection of image-guided surgery and machine learning, and the patent record reflects that split cleanly. A61B (diagnosis and surgery) covers 202 of 211 records, while G06T (image data processing) appears in 98 — together confirming that most claims are anchored in surgical hardware and workflow, with the vision or learning component layered on top rather than filed as a standalone software claim. Healthcare informatics (G16H, 28 records) and implants (A61F, 25) form smaller but persistent secondary clusters, and optical systems (G02B) and velocity/acceleration sensing (G01P) each register a modest single-digit-to-low-double-digit presence.

Filing office data shows the United States receiving the large majority of filings (120), well ahead of Europe (30), the PCT route (26), Australia (13), Canada (10) and China (5). That concentration, combined with a filing curve that rose sharply from 2017 through 2020 and then leveled off, suggests a field that established its core claim territory early and is now seeing incremental rather than exploratory filing. Publication lag of roughly 18 months means the most recent year's count is understated and should not be read as a real decline yet.

Filing activity by year, 2017-2026
  1. 1GLOBUS MEDICAL INC21
  2. 2INTUITIVE SURGICAL OPERATIONS INC20
  3. 3MAHFOUZ MOHAMED R17
  4. 4MAKO SURGICAL CORP15
  5. 5SMITH & NEPHEW INC15
  6. 6SMITH & NEPHEW ASIA PACIFIC PTE LTD15
  7. 7SMITH & NEPHEW ORTHOPAEDICS14
  8. 8TECHMAH MEDICAL LLC8
  9. 9THE BOARD OF TRUSTEES OF THE UNIV OF ILLINOIS7
  10. 10MEDTRONIC NAVIGATION INC6
Source: Patsnap Eureka. Assignee ranking and totals. Derived from a Patsnap search on Surgical Navigation AI and Machine Learning covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP

Let an AI agent run this analysis on your own technology

Pick a task. Every answer cites the patents behind it.

10,000 free credits to start
The data

Filing trends and technology composition

Two views of the same 211-family dataset: how filing activity has moved year over year, and how those families distribute across IPC subclasses.

A rise-then-plateau filing curve

Annual filings grew from 6 in 2017 to a peak of 38 in 2020, then eased toward 30 by 2022 and roughly held there. This is a plateau pattern, not a growth story — the technology's core claim space filled early, and later years show maintenance-level filing rather than expansion.

A rise-then-plateau filing curve01020304062017201820193820202021202220232024202562026Most recent year is partial — publication lag means later filings are not yet visible.

Concentrated in surgical hardware, layered with vision processing

A61B and G06T together account for the bulk of the corpus, confirming that surgical navigation AI patents are still primarily surgical-device filings with an image-processing or machine-learning layer, rather than software patents that happen to mention surgery.

Concentrated in surgical hardware, layered with vision processingA61B · Diagnosis & surgery20295.7%G06T · Image data processing & genera…9846.4%G16H · Healthcare informatics2813.3%A61F · Implants & prostheses2511.8%A61M · Devices for body fluids125.7%G02B · Optical elements & systems125.7%G06F · Electric digital data processi…125.7%G01P · Velocity & acceleration83.8%Other4420.9%

Shares are the percentage of the 211 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.

Source: Patsnap Eureka. Filing trend and technology composition. Derived from a Patsnap search on Surgical Navigation AI and Machine Learning covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.

Go deeper on Surgical Navigation AI and Machine Learning with Eureka

This page is one run against one query. Ask Eureka your own question about surgical navigation ai and machine learning and every answer comes back with the patent numbers behind it.

Try Eureka
Key patents

The most-cited filings and a recent representative claim

Representative recent filing
US20260224207A12026-08-06

Machine learning system and method for real-time image-based anatomy segmentation (US20260224207A1)

ROBOTRON SURGICAL IP HOLDING LLC

A method for real-time surgical navigation, including: capturing an intraoperative image stream from a distal portion of an endoscopic instrument inserted into a patient's body; processing the intraoperative image stream with a machine learning-based segmentation algorithm configured to identify anatomical structures; and outputting segmentation data indicating the anatomical structures within the image stream.Filed by Robotron Surgical IP Holding LLC, published 2026-08-06 — one of the newest entries in the corpus and a useful marker of where current claim drafting is headed: real-time, endoscopic, ML-based segmentation rather than static pre-operative image registration.

US20260224207A1 — patent drawing 1US20260224207A1 — patent drawing 2
View full filing
Most-cited records in the corpus
#Publication no.Patent titleCitations
1US20180240237A1Systems and Methods of Registration for Image-Guided Surgery270
2US20180235709A1Systems and Methods of Registration for Image-Guided Surgery219
3US20190142519A1Graphical user interface for displaying automatically segmented individual parts of anatomy in a surgical nav…151
4US20200375666A1Systems and methods for augmented reality based surgical navigation141
5US10706543B2Systems and methods of registration for image-guided surgery96
6US20220151704A1Co-registration for augmented reality and surgical navigation84
7US20200364865A1Systems and methods of registration for image-guided surgery80
8US20190133693A1Surgical navigation of the hip using fluoroscopy and tracking sensors77
9US20170151021A1System and method for using a haptic device as an input device53
10US20220104884A1Image-Guided Surgery System43

Citation counts favour older filings simply by virtue of longer exposure in the corpus; treat these as markers of influence on subsequent filers, not as a ranking of current technical importance.

Each row carries its publication number; clicking a row searches Eureka by that number.

Source: Patsnap Eureka. Citation counts and representative records. Derived from a Patsnap search on Surgical Navigation AI and Machine Learning covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Run it yourself

Put your own technology through the same analysis

 
Where to run it
Fastest

Eureka on the web

When you want the answer in the next five minutes.

The agent works the prompt against patents and technical literature, citing every source.

Run your analysis now →
For builders

MCP server & REST API

When it has to run inside your own pipeline.

Patent search, landscape analysis and assignee resolution as MCP tools. Drop them into any agent framework, or call REST directly.

Browse MCP servers →
Insights

What the numbers mean for a filing decision

Three patterns stand out once family counts, citation weight and filing geography are read together.

Filing plateau
38 → 30
peak (2020) vs. midpoint (2022)

Growth has stalled, not stopped

The jump from 6 families in 2017 to 38 in 2020 marks the field's build-out phase. The subsequent settle to around 30 by 2022 indicates the core claim territory around registration and segmentation is largely staked out, and new filings now compete for narrower ground.

Read the full trend
Citation concentration
270 citations
top-cited record

Registration claims anchor the field's citation graph

The most-cited records in the corpus are all variants of image-guided surgery registration methods, with counts well above other records. Anyone filing near registration or segmentation claims should expect to be examined against this cluster first.

See the most-cited table
Geographic concentration
120 of 211
US-directed filings

Filing strategy is US-first by a wide margin

With 120 US filings against 30 at the EPO, 26 via PCT, and single-digit-to-low-teens counts in Australia, Canada and China, the current patent record is built overwhelmingly around US commercial priority, leaving China in particular thinly covered relative to its clinical device market.

Compare receiving offices
Eureka AI Agent
Looking for what nobody has claimed yet?

Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to surgical navigation ai and machine learning, with the prior art for and against each one.

Find the white space →
Source: Patsnap Eureka. Co-assignee relationships and derived observations. Derived from a Patsnap search on Surgical Navigation AI and Machine Learning covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
Players

Who is active, and who has pulled back

Recent-year momentum diverges sharply from historical filing volume: several assignees with established portfolios show no filings in the latest year, while co-assignee activity clusters around a small number of corporate pairings.

Momentum drop-off
-100% YoY
for several established filers

Established assignees have gone quiet

Multiple long-standing assignees in this space, including major orthopaedic and surgical robotics names, show zero families in the latest year and a -100% year-over-year change. That does not necessarily mean exit from the field — it may reflect the 18-month publication lag — but it does mean their most recent public claim positions are aging.

See momentum by assignee
New activity
1 filing
latest-year count, most active current filer

Activity has shifted toward smaller, newer filers

Where large incumbents show no recent filings, at least one newer-named entity shows continued, if modest, activity in the latest year. This is consistent with a plateaued field where large players consolidate existing claims while smaller entrants test adjacent ground.

Track new entrants
Co-assignee clustering
3 pairs
co-assignee pairings identified

Co-filing is limited and concentrated in one corporate family

Only three co-assignee pairs appear in the corpus, and all three involve the same cluster of related Smith & Nephew entities. This suggests joint filing is largely an artefact of corporate structure rather than a sign of active cross-company collaboration in this field.

Review co-assignee pairs
🔍
Under-claimed sub-areas worth checking before filing
These branches show thinner coverage relative to the core registration and segmentation cluster.
Surgical phase recognition from videoReal-time endoscopic anatomy segmentationRegistration learning for soft-tissue deformationVelocity/acceleration-based instrument trackingAR-based intraoperative guidance overlays
Rank all filers by momentum →
Recent-year filing momentum by assignee
AssigneeRecent yearYoY
Marko Surgical Corporation1
MAHFOUZ MOHAMED R0
Globus Medical, Inc.0-100%
Intuitive Surgical Operations, Inc.0-100%
Smith & Nephew Asia Pacific Pte. Limited0-100%
Smith & Nephew, Inc.0-100%
Smith & Nephew Orthopaedics AG0
TECHMAH MEDICAL LLC0
Source: Patsnap Eureka. Assignee-level momentum. Derived from a Patsnap search on Surgical Navigation AI and Machine Learning covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
What's next

Where to take this from here

The dataset points to specific next steps depending on whether the goal is freedom-to-operate, portfolio benchmarking or identifying open claim space.

Check freedom-to-operate against the registration cluster

Any filing touching image-guided registration or automated segmentation should be checked against the most-cited records in this corpus first, since they anchor the densest prior-art neighbourhood.

Run a freedom-to-operate check in Eureka

Watch for renewed filing from quiet incumbents

Several assignees show a sharp drop to zero in the latest year; given publication lag, some of that may reverse once pending filings publish. Monitoring these accounts directly is more reliable than reading the plateau as permanent.

Set up assignee monitoring in Eureka

Explore the under-claimed branches before drafting

Surgical phase recognition, soft-tissue registration learning and real-time endoscopic segmentation all show thinner coverage than the core registration cluster and may offer more open claim space.

Explore white space in Eureka
Source: Patsnap Eureka. Forward-looking reading of the same dataset. Derived from a Patsnap search on Surgical Navigation AI and Machine Learning covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP
FAQ

Common questions about surgical navigation AI patents

Answers are grounded in the same dataset. Derived from a Patsnap search on Surgical Navigation AI and Machine Learning covering 2015–2026, data cut-off 2026-07-31. Counts reflect published records only and shift as new filings publish.Run this in Eureka MCP

Research Surgical Navigation AI and Machine Learning in depth with Eureka

Go past this page: query the whole surgical navigation ai and machine learning corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.

Try Eureka

Disclaimer. This page is generated from Patsnap Eureka data drawn from a limited snapshot of global patent and scientific-literature records, and is provided for general information and reference only.

Patent data carries inherent limitations: recent filings (typically the most recent 18–24 months) are under-counted due to standard publication lag; counts may be reported at either a patent-family or a patent-record basis and are not always directly comparable; classification, applicant-name, and citation data may contain errors, duplicates, or omissions; and the underlying search query defines and constrains the scope shown. As a result, the analysis may be incomplete or inaccurate and may not reflect the full technology landscape.

Nothing on this page constitutes an exhaustive prior-art, novelty, freedom-to-operate, or validity search, nor does it constitute legal, financial, investment, or professional advice, and it should not be relied upon as such. Any patent, commercial, or strategic decision should be verified independently and reviewed with qualified patent, legal, and domain professionals. Patsnap makes no warranties, express or implied, as to the accuracy, completeness, or fitness for any particular purpose of the information presented.

Machine translation. Assignee and organisation names originally recorded in Chinese, Japanese or Korean have been rendered into English by an AI translation step so that the tables stay readable. These renderings are best-effort and may not match a company’s registered English name; the original name is what the underlying patent record carries, and it is what any Eureka query launched from this page uses.

Help us improve this page

Found incorrect or outdated information? Let us know and we'll get it fixed.