PET and SPECT Imaging Patents: Who Leads, Where the Gaps Are 2026
- Five companies hold 49.5% of all 645 records in scope, concentrating detector and reconstruction claims among a small set of imaging OEMs.
- Filing peaked in 2021 at 58 records and has since flattened, with the 2022 midpoint at 34 suggesting the core architecture claims are largely staked out.
- G06N-tagged AI reconstruction sits at just 2.9% of records, a small sliver next to the 46.0% carrying G01T nuclear-measurement claims — a gap worth checking before filing.
What this landscape covers
PET and SPECT imaging patents span the physical detector stack — scintillator crystals, SiPM arrays and time-of-flight electronics — through to the software layer that turns raw counts into a diagnostic image: attenuation correction, scan-time reduction and dose management. This dataset pulls 645 published records filed between 2015 and 2026 under IPC classes A61B6, G01T1 and G06T11, capturing both the hardware claims filed by imaging OEMs and the reconstruction-software claims filed alongside them.
Because publication lags filing by roughly 18 months, the most recent year of the trend is necessarily incomplete and should be read as a floor, not a ceiling, on current activity.
Filing trend and technology composition
The filing curve and the IPC breakdown together show where claim density has built up and where it has not — read them before scoping a freedom-to-operate search.
A flat-to-declining filing curve since 2021
Filings rose from 35 in 2017 to a peak of 58 in 2021, then eased back toward the 2022 midpoint of 34 records — a pattern consistent with a maturing core architecture rather than an expanding one, though the partial 2026 count understates true recent activity.
Diagnosis claims dominate, AI reconstruction is thin
A61B (diagnosis and surgery) appears on 60.5% of the 645 records and G01T (nuclear and X-radiation measurement) on 46.0%, confirming that detector and scanning-method claims anchor the field. G06N-tagged AI-model claims sit at only 2.9%, and G16H healthcare-informatics claims at 3.7% — both far behind the hardware classes, since a record can carry more than one class these shares add to more than 100%.
Shares are the percentage of the 645 records in scope. A patent can carry several IPC classes, so the shares add up to more than 100%.
Go deeper on PET and SPECT Imaging Systems with Eureka
This page is one run against one query. Ask Eureka your own question about pet and spect imaging systems and every answer comes back with the patent numbers behind it.
Try EurekaMost-cited records and a representative claim
US9392958B2 — Attenuation correction for combined PET/MRT systems
Various embodiments relate to a method of attenuation correction of Positron Emission Tomography (PET) data based on Magnetic Resonance Tomography (MRT) data. A method of at least one embodiment further includes determining further data indicative of an iterative cycle of a physiological observable of a patient and matching the PET data with the MRT data based on the further data.Filed by Siemens Healthineers AG, published 2016-07-19 — one of the field's core attenuation-correction filings bridging PET and MRT data streams.
| # | Publication no. | Patent title | Citations |
|---|---|---|---|
| 1 | US5821541A | Method and apparatus for radiation detection | 392 |
| 2 | US20030128801A1 | Multi-modality apparatus for dynamic anatomical, physiological and molecular imaging | 345 |
| 3 | US5672877A | Coregistration of multi-modality data in a medical imaging system | 318 |
| 4 | US6449331B1 | Combined PET and CT detector and method for using same | 150 |
| 5 | US20030216631A1 | Registration of thoracic and abdominal imaging modalities | 141 |
| 6 | US6628982B1 | Internal marker device for identification of biological substances | 117 |
| 7 | US20100040197A1 | Large bore pet and hybrid pet/CT scanners and radiation therapy planning using same | 104 |
| 8 | US6236050B1 | Method and apparatus for radiation detection | 96 |
| 9 | US20040260176A1 | Systems and methods for correcting a positron emission tomography emission image | 80 |
| 10 | US20100108896A1 | Limited Angle Tomography With Time-Of-Flight PET | 79 |
Citation counts favour older filings simply because they have had more time to be cited; treat this list as a map of influential prior art, not of current filing activity.
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 decision
Three patterns stand out once you separate hardware claims from software claims and current activity from historical citation weight.
Detector and system claims sit with a small group
The top five assignees combined account for 319 of the 645 records in scope, or 49.5% — a concentration typical of a field where the core scanner architecture (detector ring, gantry, coincidence timing) was staked out early by the major OEMs.
Filing has plateaued since the 2021 peak
The trend climbed from 35 records in 2017 to 58 in 2021, then settled near the 2022 midpoint of 34 — a sign that the foundational claim space around PET/SPECT detection and correction has filled in, pushing new filings toward narrower refinements.
AI-based reconstruction is thinly claimed
Only 19 of 645 records carry a G06N AI-computing class, versus 251 carrying G06T image-processing claims. That gap suggests reconstruction pipelines are still largely claimed as conventional image processing rather than as learned models, leaving room to file narrowly on model-based approaches.
Eureka can read the same corpus for gaps instead of for coverage: under-claimed branches adjacent to pet and spect imaging systems, with the prior art for and against each one.
Who is filing, and where they are quiet
The ranked leaders are drawn from imaging OEMs and a smaller set of university and hospital-affiliated filers; recent-year momentum tells a different story from all-time volume.
One filer holds the largest single share
The leading assignee's 99 records sit well above fifth place at 23, underscoring how concentrated the top of this field is even though the ranking runs to 100 companies overall.
Established names have gone quiet in the latest year
Several of the historically largest filers, including major imaging OEMs, show zero records in the latest available year, with one recording a -100% year-on-year change — consistent with the broader plateau in the trend, though publication lag means recent activity is understated.
Collaboration is limited but concentrated
Ten co-assignee pairs appear in the dataset; the strongest links a Chinese detector-technology firm with a university research partner, and a separate pair links a major imaging OEM with its own regional subsidiary — patterns of internal and academic co-filing rather than broad industry consortia.
| Assignee | Recent year | YoY |
|---|---|---|
| Shanghai United Imaging Healthcare | 1 | — |
| Koninklijke Philips N.V. | 0 | — |
| Siemens Medical Solutions USA, Inc. | 0 | -100% |
| General Electric Company | 0 | — |
| Siemens AG | 0 | — |
| GE Precision Healthcare LLC | 0 | — |
| United Imaging Healthcare America | 0 | — |
| Canon Medical Systems Corporation | 0 | -100% |
Where to take this analysis
The trend and composition data point to specific next questions for an R&D or IP team scoping work in this space.
Map claim scope on the five most-cited records
The most-cited filings, several dating to the late 1990s and early 2000s, still anchor coregistration and combined-modality claims — check current filings against them before drafting new detector or fusion claims.
Explore prior art in EurekaCheck the AI-reconstruction gap before filing
With only 2.9% of records carrying a G06N class against 38.9% carrying G06T, a narrowly drafted learned-reconstruction claim may face lighter prior art than a conventional image-processing claim.
Run a white-space search in EurekaWatch for renewed filing from quiet incumbents
Several top-five assignees show zero recent-year filings; because publication lags filing by about 18 months, a resumption in activity may not be visible in this data for another year or more.
Track assignee activity in EurekaCommon questions about PET and SPECT imaging patents
The dataset ranks 100 assignees, with the leading filer holding 99 of the 645 records in scope and the top five combined accounting for 319 records, or 49.5%. This concentration is typical of imaging hardware fields, where a handful of large OEMs and their national subsidiaries file continuously across detector, gantry and reconstruction claims. Beyond the top ten, which together hold 60.2% of records, filing activity spreads across universities, hospital-affiliated research groups and smaller detector-technology firms with only a handful of records each.
Filing activity peaked in 2021 at 58 records and has since eased back toward the 2022 midpoint of 34, suggesting the field's core architecture claims are largely in place rather than still expanding. The most recent year in any dataset like this understates real activity because publication lags filing by roughly 18 months, so a firmer read on 2025-2026 filing will only be visible in a year or two. Even accounting for that lag, the shape of the curve since 2021 points to a plateau rather than continued growth.
The three IPC classes anchoring this dataset are A61B (diagnosis and surgery, 60.5% of the 645 records), G01T (nuclear and X-radiation measurement, 46.0%) and G06T (image data processing, 38.9%). Smaller shares of records also carry G01R electric/magnetic measurement, G06K data recognition, A61K medicinal preparations, G16H healthcare informatics and G06N AI-model classes. Because a single record commonly carries several of these classes, the shares add to well over 100% and should not be summed or treated as a partition of the field.
The clearest gap sits between the heavily claimed G06T image-processing class (38.9% of records) and the thin G06N AI-computing class (2.9%), suggesting learned or model-based reconstruction methods are not yet as densely claimed as conventional image-processing pipelines. G16H healthcare-informatics claims are similarly light at 3.7%, pointing to room around workflow and data-integration claims layered on top of the imaging hardware. Any freedom-to-operate check should still confirm this against the specific claim language of the most-cited records before relying on class-level gaps.
US9392958B2, filed by Siemens Healthineers AG and published in 2016, claims a method of attenuation-correcting PET data using MRT data, including determining data indicative of a patient's physiological cycle and matching PET to MRT data on that basis. It is a representative filing rather than the only one in this space, and its scope is limited to the specific matching method it describes rather than combined PET/MRT imaging generally. Anyone designing an attenuation-correction pipeline for combined PET/MRT systems should read its claims in full and compare them against the other most-cited records before assuming a design-around is needed.
Research PET and SPECT Imaging Systems in depth with Eureka
Go past this page: query the whole pet and spect imaging systems 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.