We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress hp
Sign In
Advertise with Us

Download Mobile App




New Technology Autonomously Detects AI Hallucinations in Digital Pathology

By LabMedica International staff writers
Posted on 19 Jun 2025

Traditional tissue staining, a fundamental tool in diagnosing diseases like cancer, involves chemical dyes to highlight microscopic features in tissue samples. More...

While effective, the process is time-consuming, destructive, and dependent on physical resources. Virtual staining—an artificial intelligence (AI)-powered approach that simulates histochemical staining from autofluorescence microscopy—offers a faster, non-destructive alternative. However, it comes with a major challenge: hallucinations, or AI-generated features that do not exist in the real tissue, which can mislead even expert pathologists. Researchers have now introduced an autonomous image quality assessment tool to detect hallucinations in virtually stained images.

Developed by a research team at the University of California, Los Angeles (UCLA, Los Angeles, CA, USA), in collaboration with pathologists from multiple institutions, the AI tool named AQuA (Autonomous Quality Assessment) is specifically built to identify image inconsistencies without needing histochemically stained ground truth data or access to the virtual staining model itself. AQuA functions by using iterative image translation cycles between autofluorescence and H&E domains. These cycles amplify minute discrepancies within the image, generating sequences that are assessed by an ensemble of neural networks. This digital “panel of judges” evaluates image quality and flags hallucinations before the images reach clinical experts. The system operates independently from the original staining model and adapts to various tissue types and staining methods, making it both scalable and broadly applicable in digital pathology.

The researchers validated AQuA using human kidney and lung biopsy samples. The findings, published in Nature Biomedical Engineering, show that the tool achieved 99.8% and 97.8% accuracy, respectively, in distinguishing high-quality from flawed virtually stained images, without relying on traditional staining images. Moreover, AQuA showed over 98% agreement with board-certified pathologists and, in certain scenarios, outperformed them, particularly in identifying deceptive hallucinations in the absence of ground truth references. The team also demonstrated AQuA’s versatility by applying it to conventionally stained slides, where it successfully detected common clinical artifacts. With AI tools becoming more integral to diagnostic workflows, quality assurance systems like AQuA are essential to ensure reliability and safety. AQuA enables rapid, accurate, and automated validation of AI-generated pathology images, paving the way for scalable and trustworthy adoption of virtual staining and digital pathology in clinical practice.

“With AQuA, we are adding a layer of trust to AI-generated images in medicine,” said UCLA Professor Aydogan Ozcan, the study’s senior author. “It acts like a digital second opinion, tirelessly checking every virtually stained tissue slide to ensure it is safe for diagnosis.”

Related Links:
UCLA


Gold Member
Flocked Fiber Swabs
Puritan® Patented HydraFlock®
3-Part Differential Hematology Analyzer
Swelab Alfa Plus Sampler
New
Laboratory Software
ArtelWare
New
6 Part Hematology Analyzer with RET + IPF
Mispa HX 88
Read the full article by registering today, it's FREE! It's Free!
Register now for FREE to LabMedica.com and get access to news and events that shape the world of Clinical Laboratory Medicine.
  • Free digital version edition of LabMedica International sent by email on regular basis
  • Free print version of LabMedica International magazine (available only outside USA and Canada).
  • Free and unlimited access to back issues of LabMedica International in digital format
  • Free LabMedica International Newsletter sent every week containing the latest news
  • Free breaking news sent via email
  • Free access to Events Calendar
  • Free access to LinkXpress new product services
  • REGISTRATION IS FREE AND EASY!
Click here to Register








Channels

Molecular Diagnostics

view channel
Image: The ONC IN-CYT platform leverages cross indication biomarker cyto-signatures (Photo courtesy of OraLiva)

AI-Powered Cytology Tool Detects Early Signs of Oral Cancer

Each year, 54,000 Americans are diagnosed with oral cancer, yet only 28% of cases are identified at an early stage, when the five-year survival rate exceeds 85%. Most diagnoses occur in later stages, when... Read more

Hematology

view channel
Image: The microfluidic device for passive separation of platelet-rich plasma from whole blood (Photo courtesy of University of the Basque Country)

Portable and Disposable Device Obtains Platelet-Rich Plasma Without Complex Equipment

Platelet-rich plasma (PRP) plays a crucial role in regenerative medicine due to its ability to accelerate healing and repair tissue. However, obtaining PRP traditionally requires expensive centrifugation... Read more

Immunology

view channel
Image: PD-1 protein blockade is the standard treatment for advanced melanoma among the different types of immunotherapy (Photo courtesy of 123RF)

Precision Tool Predicts Immunotherapy Treatment Failure in Melanoma Patients

Melanoma, though accounting for only about 4% of skin tumors, is the deadliest form of skin cancer due to its high potential to metastasize. While immunotherapy, especially PD-1 protein blockade, has revolutionized... Read more
Copyright © 2000-2025 Globetech Media. All rights reserved.