AI Method for Sharpening Low-Dose PET Scans with Multi-Task Learning
This patent describes an AI method using a special type of neural network called a multi-task learning generative adversarial network (GAN) to improve the quality of medical images from low-dose PET scans, making them look like standard-dose scans.
Original patent title: “Method and system for generating multi-task learning-type generative adversarial network for low-dose PET reconstruction”
This patent describes an AI method using a special type of neural network called a multi-task learning generative adversarial network (GAN) to improve the quality of medical images from low-dose PET scans, making them look like standard-dose scans. Granted to Shenzhen Institutes of Advanced Technology in 2023 with 10 claims, and it is expected to expire in 2041.
Coverage
What does this patent actually cover?
The patent describes a method for creating an AI system that can take blurry, low-dose Positron Emission Tomography (PET) images and make them clearer, similar to standard-dose PET images. It starts by building a "U-Net type picture generator" by connecting an "encoder" and a "decoder" using "skip connections" (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1). Then, it creates multiple "generative adversarial networks" (GANs) by pairing these picture generators with "discriminators" (Claim 1). These GANs learn in parallel, sharing basic information, forming a "first multi-task learning-type generative adversarial network." The system is trained using a "joint loss function" that combines L1 type loss and cross entropy loss, comparing the AI's output to high-quality standard-dose PET images (ClaimsclaimsThe numbered statements at the end of a patent that legally define what the inventor owns.Read more → 1, 2). For example, if a patient receives a low-dose PET scan to reduce radiation exposure, this AI can process those images to produce diagnostic quality results.
The gap
What does this patent NOT cover?
- Does not cover methods for reconstructing PET images without using a "U-Net type picture generator" with "skip connections" (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1).
- Does not cover systems that use only a single generative adversarial network, as it specifies "a group of generative adversarial networks" and "plurality of picture generators" (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1).
- Does not cover methods where the "plurality of discriminators" do not use an "input modality," a "tag image," and an "output result" as input (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1).
- Does not cover methods that do not combine low-dose PET and MR images as input modalities for each GAN (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1).
- Does not cover training methods that do not use a "joint loss function 1" combining L1 type loss and cross entropy loss functions (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1, 2).
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Key facts
What made this novel
The noveltynoveltyThe requirement that an invention be different from anything publicly known before its priority date.Read more → lies in combining multiple "U-Net type picture generators" with "discriminators" into a "multi-task learning-type generative adversarial network," where these networks learn in parallel and share information. This parallel learning, guided by a specific "joint loss function" that considers both L1 and cross-entropy losses, allows the system to effectively reconstruct high-quality images from very low-dose PET data, leveraging additional MR image input.
The Patent Drawing
Schematic visualization of the patent's claim structure. Hand-drawn diagrams in progress for each landmark patent.
Where you've seen this
Real-world examples
Medical imaging software for PET scanners
AI-powered diagnostic tools in oncology
Radiology workstations
Research platforms for medical image enhancement
Why it matters
The bigger picture
Positron Emission Tomography (PET) scans are crucial for diagnosing diseases like cancer, but they expose patients to radiation. This patent matters because it offers a way to get high-quality images from lower radiation doses, making PET scans safer and potentially more accessible. By improving image quality from low-dose data, it could lead to earlier and more accurate diagnoses with reduced patient risk.
Filed
June 7, 2021
Granted
September 12, 2023
Market context
Who's building on this
Companies in this space
Companies like Siemens Healthineers, GE Healthcare, Philips, and various AI startups in medical imaging (e.g., Qure.ai, Aidoc) are actively developing and integrating AI for image reconstruction and enhancement in PET and other modalities. Shenzhen Institutes of Advanced Technology, the assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →, continues research in this area.
Market impact
This type of AI technology has a significant impact on the medical imaging market by enabling safer diagnostic procedures. It drives the development of new AI-powered features in PET scanners and radiology software, potentially reducing patient radiation exposure and healthcare costs. The ability to generate high-quality images from low-dose data can also expand access to PET scans, especially for vulnerable populations or for repeated follow-up scans.
Claim 1 — Plain English
What this patent covers
The patent describes a method for creating an AI system that can take blurry, low-dose Positron Emission Tomography (PET) images and make them clearer, similar to standard-dose PET images. It starts by building a "U-Net type picture generator" by connecting an "encoder" and a "decoder" using "skip connections" (Claim 1). Then, it creates multiple "generative adversarial networks" (GANs) by pairing these picture generators with "discriminators" (Claim 1). These GANs learn in parallel, sharing basic information, forming a "first multi-task learning-type generative adversarial network." The system is trained using a "joint loss function" that combines L1 type loss and cross entropy loss, comparing the AI's output to high-quality standard-dose PET images (Claims 1, 2). For example, if a patient receives a low-dose PET scan to reduce radiation exposure, this AI can process those images to produce diagnostic quality results.
The clever bit
The novelty lies in combining multiple "U-Net type picture generators" with "discriminators" into a "multi-task learning-type generative adversarial network," where these networks learn in parallel and share information. This parallel learning, guided by a specific "joint loss function" that considers both L1 and cross-entropy losses, allows the system to effectively reconstruct high-quality images from very low-dose PET data, leveraging additional MR image input.
What it does not cover
- Does not cover methods for reconstructing PET images without using a "U-Net type picture generator" with "skip connections" (Claim 1).
- Does not cover systems that use only a single generative adversarial network, as it specifies "a group of generative adversarial networks" and "plurality of picture generators" (Claim 1).
- Does not cover methods where the "plurality of discriminators" do not use an "input modality," a "tag image," and an "output result" as input (Claim 1).
- Does not cover methods that do not combine low-dose PET and MR images as input modalities for each GAN (Claim 1).
- Does not cover training methods that do not use a "joint loss function 1" combining L1 type loss and cross entropy loss functions (Claim 1, 2).
Patent timeline
Application submitted to the patent office
Application published, typically 18 months after filing
Patent officially issued
Patent enters public domain
PatentBrief Score
Impact Score
Early stage
Citation count
0/40
No citations yet
Claim breadth
7/20
Moderate scope
Recency
20/20
Granted within 5 years
Assignee scale
0/20
Independent or smaller assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →
PatentBrief Impact Score — based on citation count, claim breadth, recency, and assignee scale. Not a legal assessment.
Heuristic Value Estimate
What this patent might be worth
$29K – $92K
Midpoint $58K · 14.6 yr remaining · industry ×1.6
Heuristic only — blends forward/backward citation counts, claim scope, time remaining, litigation history, and CPC-derived industry baseline. Real valuations need a professional appraisal.
Claim text not yet imported for this patent
The original legal language
Original claims
10 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Liu, X., Zhang, N., YANG, Y., Liang, D., Zheng, H., HU, Z., & Sun, H. (2023). AI Method for Sharpening Low-Dose PET Scans with Multi-Task Learning (U.S. Patent No. 11,756,161). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/11756161/method-and-system-for-generating-multi-task-learning-type-generative-adversarial
Auto-generated from the patent record. Double-check author order and the issue date against the official USPTO document before submitting.
Embed
Add this patent to your site
Drop this plain-English patent card into any blog post or article — free, no signup. It always links back to the full breakdown here.
<div data-patentlens-widget data-patent-number="US11756161"></div> <script src="https://patentbrief.org/embed.js" async></script>
Stay in the loop
Get a weekly digest of new patents.
One email per week. No spam. Unsubscribe anytime.
Keep exploring
Related patents you should know
US 4683195 · 1987
How to Make Billions of Copies of a DNA Segment
This patent describes the Polymerase Chain Reaction (PCR), a method to rapidly create many copies of a specific piece of DNA or RNA, enabling its detection and analysis.
Cetus Corp
US 8697359 · 2014
How to Edit Genes in Human Cells Using an Engineered CRISPR System
This patent describes an engineered CRISPR-Cas9 system for precisely cutting DNA in eukaryotic cells to change how genes work, opening the door for gene editing in complex organisms.
Massachusetts Institute of Technology
US 7657849 · 2010
How the iPhone's Slide-to-Unlock Gesture Works
Apple's 2010 patent describes unlocking a device by dragging a specific graphical image across the touchscreen along a predefined path, a gesture that became iconic with the original iPhone.
Apple Inc
US 4733665 · 1988
How Doctors Implant a Permanent Stent Using a Balloon
This patent describes the method for placing a permanent, expandable wire mesh tube inside a blood vessel or other body tube using a balloon-tipped catheter to widen it and keep it open.
Expandable Grafts Partnership
US 4965188 · 1990
How to Make Many Copies of a DNA Piece with Heat
This patent describes the Polymerase Chain Reaction (PCR) method, a technique to make millions of copies of a specific DNA segment using a heat-resistant enzyme and repeated temperature changes.
Cetus Corp
US 4235871 · 1980
How to Encapsulate Active Materials in Lipid Bubbles Efficiently
This patent describes a method for trapping biologically active substances inside tiny, multi-layered fat bubbles called liposomes, using a specific water-in-oil emulsion and gel-forming process to improve how much material gets captured.
Individual
Semantically similar
You might also find these interesting
US 11422217 · 2022 · Siemens Healthcare
How AI Reconstructs Clearer MRI Scans Using Progressive Networks
US 11580646 · 2023 · Nanjing University of Posts and Telecommunications
Improving Medical Image Segmentation with AI and Fake Data
US 12141700 · 2024 · Naver
How AI Generates Images Based on Style and Content Cues
US 12154036 · 2024 · Shenzhen Institutes of Advanced Technology
How an AI Learns to Recognize Objects by Generating Its Own Examples
More to explore
More in Biotech & Medicine
US 4683195 · 1987 · Cetus Corp
How to Make Billions of Copies of a DNA Segment
US 8697359 · 2014 · Massachusetts Institute of Technology
How to Edit Genes in Human Cells Using an Engineered CRISPR System
US 4733665 · 1988 · Expandable Grafts Partnership
How Doctors Implant a Permanent Stent Using a Balloon
US 4965188 · 1990 · Cetus Corp
How to Make Many Copies of a DNA Piece with Heat
New to patents?
Common Questions
Frequently Asked Questions
What does AI Method for Sharpening Low-Dose PET Scans with Multi-Task Learning cover?
This patent describes an AI method using a special type of neural network called a multi-task learning generative adversarial network (GAN) to improve the quality of medical images from low-dose PET scans, making them look like standard-dose scans.
Who owns patent US 11756161?
Shenzhen Institutes of Advanced Technology owns this patent, granted in 2023.
When does this patent expire?
This patent is expected to expire on June 7, 2041, when the invention enters the public domain.
What problem does this patent solve?
Positron Emission Tomography (PET) scans are crucial for diagnosing diseases like cancer, but they expose patients to radiation. This patent matters because it offers a way to get high-quality images from lower radiation doses, making PET scans safer and potentially more accessible. By improving image quality from low-dose data, it could lead to earlier and more accurate diagnoses with reduced patient risk.
What does this patent NOT cover?
Does not cover methods for reconstructing PET images without using a "U-Net type picture generator" with "skip connections" (Claim 1).
Same assignee
More from Shenzhen Institutes of Advanced Technology
Patent monitoring