Trending...
- DivX Unveils Revamped Resource Guide to Help Users Easily Convert MKV to MP4 - 162
- Visit Local Farms During 7th Annual Santa Barbara County Farm Day - 125
- California: Governor Newsom announces local progress in reducing homelessness - 120
LOS ANGELES - Californer -- 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 The Californer
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 The Californer
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 The Californer
- KIA BRINGS THE FUTURE TO THE HISTORIC KIA FORUM WITH THE "KIA CONNECTED HOME"
- California pre-deploys resources in Plumas, Nevada, and Sierra counties ahead of critical fire weather conditions
- Artbound: "The Cheech" Awarded Two 2025 LA Area EMMY Awards — Honored in ARTS & MUSIC COMPOSITION
- California: Governor Newsom issues emergency proclamation for storm-impacted counties
- Rising Conservative Star Jordan Brace Emerges as Influential Political Voice with Elite Washington Connections
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 The Californer
- Conservative Latinos for PA Shaping the Future of Hispanic Community, Guest State Treasurer Stacy Garrity
- California Patriots Organize Newsom Redial Rally 2025 At State Capitol To Address State Leadership Crisis
- White Glove Restoration Earns CIRSX Certification for Medically Important Mold Remediation
- California: Governor Newsom responds to latest Trump sledgehammer to clean air protections
- Long Beach Parks, Recreation and Marine to Offer a Variety of Recreation Classes This Fall
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 The Californer
- UseAPI.net Launches Video Generation Support for Third-Party Midjourney API
- California: Governor Newsom signs legislation 7.28.25
- TNT Removal & Disposal Celebrates Record Year Helping Pennsylvania Property Owners Reclaim Space
- SpaceWERX selects New Frontier Aerospace to Develop Bifröst Orbit Transfer Spacecraft
- Postmortem Pathology Offers Expert Autopsy Services with Dignity and Accuracy
- Private Autopsies Provide Families in Colorado with Answers and Closure
- Vijay Tirathrai named Managing Director in Dubai, UAE
- Cygnet Theatre Announces The Cast and Creative Team of Stephen Sondheim's Follies
- SunCity Advising Honored with 2025 Best of La Jolla Award for Internet Marketing Services
- Impact La To Host 6th Annual Back-to-school Backpack Giveaway In South Los Angeles
- How smart women use BAY Miner cloud mining to easily earn Bitcoin every day
- Qualis LLC Appoints Jeremy Mallicoat as Chief Financial Officer to Advance Growth and Acquisition Strategy
- PODS® Local Helps Households Looking to Downsize Belongings as Housing Market Slows
- Navore Market Introduces San Diego's First Online Marketplace for Local Farmers and Food Producers
- California: Governor Newsom statement on the passing of Wallis Annenberg
- Bynn Intelligence Reinvents Document Fraud Detection with Groundbreaking Acquisition and Revolutionary AI Model
- 2A Commerce Launches Firearms eCommerce Platform
- Biohaven Ltd. (BHVN) Investors Who Lost Money Have Opportunity to Lead Securities Fraud Lawsuit
- Digital Dropshipping VS Physical Products Dropshipping
- Mesa West Capital Originates $55 Million Loan to Refi Los Angeles Luxury Hotel