Industrial X-Ray CT Patents: Top Companies & Filing Trends 2026
- Concentrated at the top. The top 5 assignees account for 60.9% of all 115 records in scope, and the top 10 reach 82.6% — this is a field with a short list of serious filers, not a fragmented one.
- Reconstruction, not hardware, is where the action is. G06T image data processing covers 51.3% of records and G06N AI-based computing sits at 9.6%, pointing to deep-learning reconstruction as the fastest-growing claim territory.
- Growth is real but recent years understate it. Filings rose from 2 in 2021 to 5 in 2024, a 150% increase; because publication lags filing by roughly 18 months, 2025-2026 figures will keep revising upward.
Filing growth compares 2021 (2 records) with 2024 (5) — 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 115 records in scope (CR5), not by the ranked leaders only.
What the industrial CT patent record actually shows
Industrial X-ray computed tomography sits at the intersection of imaging hardware and reconstruction software, and the patent record reflects that split. Filings cluster around two problems: getting a physically accurate scan (voxel size, scan parameter optimisation, beam hardening correction) and getting a usable reconstruction out of it fast enough for a production line. The 115 records in scope span 2015 to mid-2026, with a filing peak in 2019 and a second wave building around AI-assisted reconstruction. Dimensional accuracy and reconstruction artifact reduction are the two claim families that recur most often across assignees.
The applicant base leans toward organisations that already build CT hardware or serve inspection-heavy industries — aerospace components, dental imaging, and additive manufacturing quality control show up repeatedly in the classification mix alongside the core imaging classes.
Let an AI agent run this analysis on your own technology
Pick a task. Every answer cites the patents behind it.
Filing trends and technology composition
Two views of the same 115 records: how filing volume has moved year over year, and which IPC subclasses those filings actually claim into.
Filing trend: a 2019 peak, then a rebuilding AI-driven wave
Annual filings peaked at 29 in 2019, fell back, and have since grown from 2 in 2021 to 5 in 2024 — a 150% increase over that three-year span. Treat 2025 and 2026 as incomplete: publication typically lags filing by around 18 months, so the most recent bars will rise as more records surface.
Technology composition: reconstruction software dominates the class mix
G06T (image data processing) appears in 51.3% of the 115 records and G01N (material analysis and testing) in 40.0%, confirming that most filings combine a physical scanning claim with a software reconstruction claim. Smaller but notable branches include A61B diagnosis/surgery (18.3%), A61C dentistry (13.0%), B33Y additive manufacturing (11.3%), G06N AI computing (9.6%), B29C plastics shaping (8.7%) and G06K data recognition (7.0%). Because records can carry multiple IPC classes, these shares sum to more than 100% of the record total.
Shares are the percentage of the 115 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Go deeper on Industrial X-Ray Computed Tomography with Eureka
This page is one run against one query. Ask Eureka your own question about industrial x-ray computed tomography and every answer comes back with the patent numbers behind it.
Try EurekaThe most-cited records and a recent representative filing
System and method for artifact reduction of computed tomography reconstruction leveraging artificial intelligence and a priori known model for the object of interest
Filed by UT-BATTELLE, LLC and published 2025-09-02, this filing addresses beam-hardening artifacts in CT reconstruction by combining CAD-model priors with a deep neural network. The approach simulates high-quality reconstructions affected by noise and beam hardening, then uses those simulations to train a network that improves real reconstructions of the object being inspected.Illustrates how CAD-informed, AI-assisted reconstruction is being claimed as a distinct route to defect detection rather than as a generic denoising step.
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US6041132A | Computed tomography inspection of composite ply structure | 163 |
| 2 | US20180293762A1 | Tomographic reconstruction based on deep learning | 80 |
| 3 | US20190108441A1 | Image generation using machine learning | 70 |
| 4 | US20190328348A1 | Deep learning based estimation of data for use in tomographic reconstruction | 57 |
| 5 | EP0905509A1 | Computed tomography inspection of composite ply structure | 56 |
| 6 | US20220035961A1 | System and method for artifact reduction of computed tomography reconstruction leveraging artificial intellig… | 51 |
| 7 | US20200043204A1 | Iterative image reconstruction framework | 42 |
| 8 | WO2018126396A1 | Deep learning based estimation of data for use in tomographic reconstruction | 39 |
| 9 | US20190336254A1 | Methods of three-dimensional printing for fabricating a dental appliance | 27 |
| 10 | US20050185753A1 | Scatter and beam hardening correctoin in computed tomography applications | 24 |
Citation counts favour older records simply because they have had more time to accumulate citations within the searched corpus — read them as a signal of influence on the field, not of current technical relevance.
Each row carries its publication number; clicking a row searches Eureka by that number.
Put your own technology through the same analysis
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 →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 →What the data means for a filing or freedom-to-operate decision
Three read-throughs from the concentration, composition and citation data above.
A short list of serious filers controls most of the field
With the top 5 assignees holding 60.9% of all 115 records and the top 10 holding 82.6%, this is not a fragmented landscape. A new entrant is filing into space already occupied by a handful of established imaging and inspection players, and freedom-to-operate work should start with their claim scope rather than a broad landscape scan.
Software reconstruction claims outnumber pure hardware claims
More than half of the 115 records touch G06T image data processing, ahead of G01N material analysis and testing at 40.0%. That ordering suggests the differentiating claims in recent filings are increasingly about how the scan data is processed, not just how it is captured.
Growth is concentrated in the AI-reconstruction branch
Filing volume grew from 2 in 2021 to 5 in 2024, a 150% increase, coinciding with the emergence of G06N AI-computing classifications (9.6% of records). Because publication lags filing, the true growth rate for 2025-2026 will only become visible over the next year or two.
Composite-ply inspection claims anchor the citation graph
The most-cited record in the dataset covers computed tomography inspection of composite ply structure, and a related filing on the same subject also ranks among the top-cited. Newer deep-learning reconstruction filings are already accumulating citations quickly despite their shorter time in the corpus.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to industrial x-ray computed tomography, with the prior art for and against each one.
Who is filing, and where the gaps sit
The ranked list covers 29 companies; filings are heavily weighted toward a small group of imaging and inspection specialists, with a long tail of single- or few-filing entrants behind them.
One assignee filed nearly a quarter of the dataset alone
The top-ranked assignee holds 29 of the 115 records in scope, well ahead of the fifth-place assignee at 8 and the tenth-place assignee at 4. That gap between first and fifth place is where most of the field's concentration comes from.
Joint filings cluster around one university-industry hub
The dataset shows 10 co-assignee pairs, with the strongest links running between a leading imaging company and several US research universities, each pairing appearing three times. This points to sponsored or joint research programmes rather than arm's-length licensing.
Recent-year activity has thinned even among top filers
Only one assignee in the recent-momentum data shows a filing in the latest year; several previously active filers, including the overall leader, show zero filings in that year with one logging a -100% year-on-year change. Given the ~18-month publication lag, this likely reflects incomplete data rather than a real pullback.
| Assignee | Recent year | YoY |
|---|---|---|
| Baker Hughes Holdings LLC | 1 | — |
| General Electric Company | 0 | -100% |
| Dentsply Sirona Inc. | 0 | — |
| University of Stuttgart | 0 | — |
| TRIPLE RING TECH | 0 | — |
| Siemens Healthineers | 0 | — |
| Rigaku Corporation | 0 | -100% |
| Delavan Inc. | 0 | — |
Where to take this next
The landscape points to two practical next steps depending on whether the goal is filing or clearance.
Map claim scope against the top assignees
Before drafting into a crowded branch like beam-hardening correction or AI-based reconstruction, review the granted claim scope held by the top-5 assignees, who together account for 60.9% of the 115 records in scope.
Explore assignee claims in Eureka →Track the AI-reconstruction branch as it matures
G06N-classified filings are still a minority of the field at 9.6% of records, but the 2021-2024 growth trend suggests this branch is where new claim activity is concentrating.
Set up a monitoring search in Eureka →Common questions about industrial X-ray CT patents
The dataset's ranked list covers 29 companies, and the leading assignee alone accounts for 29 of the 115 records in scope. The top 5 assignees combined hold 60.9% of all records, and the top 10 hold 82.6%, so filing activity is concentrated rather than spread evenly across the field. Anyone assessing freedom to operate should start by reviewing the claim scope of that top group before looking at the longer tail of single-filing entrants.
Filings grew from 2 in 2021 to 5 in 2024, a 150% increase over that span, after an earlier peak of 29 filings in 2019. The apparent dip in the most recent one to two years is not a reliable signal of slowdown, because patent publication typically lags actual filing by around 18 months. The 2024 figure is the most recent year that can be treated as reasonably complete.
Image data processing (IPC class G06T) appears in 51.3% of the 115 records, ahead of material analysis and testing (G01N) at 40.0%, meaning more than half of filings include a software reconstruction claim alongside or instead of a pure hardware claim. Smaller but active branches include additive manufacturing quality control (B33Y, 11.3%) and AI-based computing methods (G06N, 9.6%). Because a single record can carry multiple IPC classes, these percentages add up to more than 100% of the record total, and should not be read as mutually exclusive categories.
US12406104B2, assigned to UT-BATTELLE, LLC and published in September 2025, claims a method for reducing beam-hardening artifacts in CT reconstruction using a deep neural network trained with CAD-model priors of the object being scanned. It is a recent example of the AI-assisted reconstruction branch that is growing within the broader G06T and G06N classification overlap. Teams working on defect-detection pipelines that combine known object geometry with learned denoising should review its claim scope closely rather than assume it only covers generic noise reduction.
The classification data shows AI-assisted scan parameter optimisation and in-line CT integration for additive manufacturing quality control appearing at lower density than core reconstruction and material-analysis claims, suggesting room for narrower, well-drafted claims in those areas. Dimensional accuracy validation workflows and dental-specific artifact reduction also show comparatively thinner coverage relative to the general reconstruction art. These are read from low relative filing density in the IPC mix, not from an absence of prior art, so a proper search is still required before drafting.
Research Industrial X-Ray Computed Tomography in depth with Eureka
Go past this page: query the whole industrial x-ray computed tomography corpus yourself, in your own scope.
Every answer comes back with patent numbers you can open.
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.