Popular on Amzeal
- Introducing The AI Bleederboard™
- L-Tron to Exhibit and Attend the 50th Annual Traffic Records Forum in Boston, MA
- Edtech Startup Young Commanders Launches 'Visionaries Without Sight' Collection Celebrating Blind and Visually Impaired Historical Figures
- IRF Builders Forum Brings Global Leaders to Washington, D.C. to Advance Religious Freedom Through Cooperative Engagement
- Patrick Aloni Joins Historic Gold and Copper Discovery in Argentina with Multimillion-Dollar Stake
- Innovative EDM Music Project, "Terms of War," Depicts an A.I. Takeover of Earth
- Startup TORmem Unveils High-Speed Networking Roadmap to Disrupt $20 Billion Data Center Market
- DivX Enhances AVI Playback Resources; Simplifies Guide to Playing AVI Files with DivX Software
- ResmarkWeb Launches Powerful AI Workshop Series to Help Tour Operators Succeed
- McDonagh Family Office Acquires RevSystems to Bolster Portfolio with AI and Operations Technology
Similar on Amzeal
- LIB and Nidec Rejoin Forces for Giant TH-0098 Temperature Humidity Test Chamber
- Deaths Spur Closures, but Troubled Teen Camps Must Be Banned, CCHR Warns
- AI-powered Virtual Staining of Biopsies for Transplant Diagnostics
- APA-Published Research Offers New Insight into School Shooter Behavior Patterns
- West Dentistry Welcomes New Oral Surgeon to Enhance Patient Care
- AI Performs Virtual Tissue Staining at Super-Resolution
- Prepare to Be Amazed: Dr. Roger Billings to Perform Live Magic at Acellus World
- Despite Global Calls for a Ban, US Child Psychiatry Pushes Electroshock for Kids
- Aerial Survey Equipment Rental Expands: RIEGL VQ-1560 II-S for Rent Now Available Worldwide from AerialSurvey.com
- Mensa Foundation Prize Awarded to Neuroscientist-Pianist
Autonomous detection of AI hallucinations in digital pathology
Amzeal News/10601386
LOS ANGELES - Amzeal -- Tissue staining is a cornerstone of medical diagnostics, used to highlight cellular structures and render tissue features visible under an optical microscope—critical for identifying diseases such as cancer. Traditionally, this process involves applying chemical dyes, like hematoxylin and eosin (H&E), to thinly sliced tissue samples. While effective, it is time-consuming, destructive, and resource-intensive. Virtual staining, powered by AI, offers a transformative alternative by digitally generating the equivalent of histochemically stained images from label-free autofluorescence microscopy data. This computational approach enables faster, more cost-effective, and scalable diagnostics without the need for physical dyes, while also preserving the tissue sample for further analysis. However, like other generative AI models, virtual staining carries the risk of hallucinations—errors where the AI adds or alters microscopic tissue features that are not present in the actual specimen. When these hallucinations appear realistic, they can mislead even experienced pathologists, jeopardizing diagnostic accuracy.
More on Amzeal News
To address this challenge, a team led by Professor Aydogan Ozcan at the University of California, Los Angeles (UCLA), in collaboration with pathologists from the University of Southern California and Hadassah Hebrew University Medical Center, developed an autonomous image quality assessment tool for detecting hallucinations in virtual staining and digital pathology. Named AQuA (Autonomous Quality Assessment), this AI-powered tool autonomously detects subtle hallucinations in digitally stained tissue slides—without requiring histochemical ground truth for comparison—and outperforms human experts in identifying potentially misleading tissue image artifacts.
Published in Nature Biomedical Engineering, AQuA operates independently of the original AI staining model and does not rely on paired histochemically stained images. It uses iterative image translation cycles between the H&E and autofluorescence domains, which amplify even subtle inconsistencies. These cycles produce sequences of images that are rapidly evaluated by an ensemble of neural networks—effectively a panel of digital judges—to determine image quality and flag hallucinations before the images reach pathologists. This architecture makes AQuA fast, adaptable, and scalable across different tissue types, staining styles, and pathology applications.
More on Amzeal News
In extensive testing on human kidney and lung biopsy samples, AQuA achieved 99.8% and 97.8% accuracy, respectively, in distinguishing high-quality from low-quality virtually stained images—all without access to the original histochemically stained tissue images or the AI model used to generate the virtually stained counterparts. It also showed over 98% agreement with board-certified pathologists and, in some cases, outperformed them—especially in detecting realistic-looking hallucinations that experts missed when ground truth staining was unavailable. Beyond virtual staining, the researchers demonstrated that AQuA could also assess the quality of conventional chemically stained tissue slides, automatically detecting common staining artifacts in clinical workflows.
Paper: https://www.nature.com/articles/s41551-025-01421-9
More on Amzeal News
- Levata Acquires Logiscenter to Accelerate Growth in Enterprise IT and Data Capture Solutions
- Smart Resnse Unveils Smart Resnse(SRMS) Token-Powered AI Orchestration Platform to Revolutionize Multi-Billion Dollar Market
- Josh and Heidi Follow Up the Much Anticipated and Successful Launch of the "Spreading the Good BUZZ" Podcast with a Personal Request
- Revolutionary Blockchain Platform Okh Finance Announces Okh Finance(OKKH) Token Launch to Transform Global Asset Leasing Market
- Cover Girl Finalist Teisha Mechetti Questions Legitimacy of Inked Originals Competition, Demands Transparency
To address this challenge, a team led by Professor Aydogan Ozcan at the University of California, Los Angeles (UCLA), in collaboration with pathologists from the University of Southern California and Hadassah Hebrew University Medical Center, developed an autonomous image quality assessment tool for detecting hallucinations in virtual staining and digital pathology. Named AQuA (Autonomous Quality Assessment), this AI-powered tool autonomously detects subtle hallucinations in digitally stained tissue slides—without requiring histochemical ground truth for comparison—and outperforms human experts in identifying potentially misleading tissue image artifacts.
Published in Nature Biomedical Engineering, AQuA operates independently of the original AI staining model and does not rely on paired histochemically stained images. It uses iterative image translation cycles between the H&E and autofluorescence domains, which amplify even subtle inconsistencies. These cycles produce sequences of images that are rapidly evaluated by an ensemble of neural networks—effectively a panel of digital judges—to determine image quality and flag hallucinations before the images reach pathologists. This architecture makes AQuA fast, adaptable, and scalable across different tissue types, staining styles, and pathology applications.
More on Amzeal News
- Easton & Easton, LLP Files Suit Against The Dwelling Place Anaheim & Vineyard USA Over Abuse Allegations
- AI Visibility: The Key to Beating Google's AI Overviews and Regaining Traffic
- Stuck Doing Math or Figuring Out Life's Numbers? Calculator.now Makes It Stupidly Simple
- Colbert Packaging Announces WBENC Recognition
- 321 Insight Launches StartSharp and StaffSharp
In extensive testing on human kidney and lung biopsy samples, AQuA achieved 99.8% and 97.8% accuracy, respectively, in distinguishing high-quality from low-quality virtually stained images—all without access to the original histochemically stained tissue images or the AI model used to generate the virtually stained counterparts. It also showed over 98% agreement with board-certified pathologists and, in some cases, outperformed them—especially in detecting realistic-looking hallucinations that experts missed when ground truth staining was unavailable. Beyond virtual staining, the researchers demonstrated that AQuA could also assess the quality of conventional chemically stained tissue slides, automatically detecting common staining artifacts in clinical workflows.
Paper: https://www.nature.com/articles/s41551-025-01421-9
Source: ucla ita
Filed Under: Science
0 Comments
Latest on Amzeal News
- Heartfelt Dreams Foundation Launches Campaign to Build CHD Hospital
- Radarsign Tackles Intersection Safety with Launch of Grid-Free Solar LED Stop Sign
- Integro Bank named a Banking Partner for Arizona Technology Council
- Miami Real Estate Agent Drastically Increases Interest In Homes
- Adostics & Genmega Announce the Introduction of A-POD
- Blue Fox Group Safeguards Business Continuity with Data Backup and Recovery Services
- LIB and Nidec Rejoin Forces for Giant TH-0098 Temperature Humidity Test Chamber
- Heritage at South Brunswick Offers Immediate Townhome Appointments and Special Mortgage Incentive Fast-Moving Sales
- Inframark Expands Automation & Intelligence Capabilities, Acquires Systems East, Inc.
- NASA Collaborative Agreement for Supply of Thin-Film Solar Tech for Orbital Application to Advance Development of Thin-Film PV Power Beaming: $ASTI
- Build your game collection with pre-owned 8 liner game boards
- Exciting New Era of Sports, Entertainment & Gaming Innovation Spotlighted by Rebrand of Expanding AI Driven, Online Fan Engagement Company: SEGG Media
- Hyperglance Wins 'Best Cloud Security & Compliance Automation Solution' at UK Enterprise Awards
- Service Ninjas Debuts First-of-Its-Kind "Membership" Platform for Home Service Pros
- Project Management Institute San Francisco and TalentCheetah Inc. Announce New Strategic Partnership
- BIYA Forecasts 2025 Surge with ¥300M ($41.8 M USD) in Revenue and ¥25M Profit from Cloud Based HR Solutions: Baiya Intl. Group (N A S D A Q: BIYA)
- Paul E. Saperstein Co. Announces Geographic Expansion of Auction Services
- Florida Broker Bent Danholm Featured in the Daily Mail's U.S. Real Estate Coverage
- Robin Launches Legal Intelligence Platform to solve intelligence gap in Fortune 500 legal teams
- Melissa B. Releases Digitally Independent: Empowering Music Artists with AI and Brand Strategy