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




AI Tool Enhances Interpretation of Tissue Samples by Pathologists

By LabMedica International staff writers
Posted on 09 Jul 2025

Malignant melanoma, a form of skin cancer, is diagnosed by pathologists based on tissue samples. More...

A crucial aspect of this process is estimating the presence of tumor-infiltrating lymphocytes (TILs), immune cells that significantly influence the body's response to cancer. However, TIL assessments can vary depending on the pathologist, which compromises medical safety and can lead to inaccuracies in determining the severity of the disease. This variability is critical as TILs play a role in prognosis and treatment decisions, with a high presence being considered favorable. Now, an artificial intelligence (AI)-based tool that quantifies TILs in tissue samples has been found to improve the consistency and accuracy of these assessments. The tool provides more reliable data, which is vital for determining treatment options.

The AI tool, developed through a collaboration between Karolinska Institutet (Stockholm, Sweden) and Yale University (New Haven, CT, USA), was designed to support pathologists in quantifying TILs. The solution aims to reduce variability in assessments and help make more accurate predictions about a patient's disease prognosis. The researchers used a set of digital images of stained tissue sections from patients with malignant melanoma to develop and test the tool. This AI support was incorporated into the workflow of experienced pathologists and other professionals with some experience in assessing pathological images. The tool works by analyzing the tissue samples and providing a quantification of the TILs, offering a clearer picture of the disease's progression.

The study tested the AI-assisted assessments by comparing them to those made by pathologists working without AI support. The research involved 98 participants who evaluated 60 tissue samples. The results showed that AI-supported assessments were superior in terms of reproducibility, with high consistency across different assessors. Additionally, the AI-enhanced assessments led to more accurate prognoses, as the results closely aligned with the retrospective 'correct answer'. These findings, published in JAMA Network Open, suggest that AI can be a powerful tool for clinical pathology, particularly in melanoma diagnosis. The researchers plan to conduct further studies to refine the AI tool and explore its potential for broader clinical use.

"Understanding the severity of a patient's disease based on tissue samples is important, among other things, for determining how aggressively it should be treated," said Balazs Acs, associate professor at the Department of Oncology-Pathology at Karolinska Institutet. “We now have an AI-based tool that can quantify the TIL biomarker, which could help with treatment decisions in the future. However, more studies are needed before this AI tool can be used in clinical practice, but the results so far are promising and suggest that it could be a very useful tool in clinical pathology.”


Gold Member
Antipsychotic TDM Assays
Saladax Antipsychotic Assays
POC Helicobacter Pylori Test Kit
Hepy Urease Test
New
Silver Member
Rapid Test Reader
DIA5000
New
Sperm Quality Analyis Kit
QwikCheck Beads Precision and Linearity Kit
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

Hematology

view channel
Image: New research points to protecting blood during radiation therapy (Photo courtesy of 123RF)

Pioneering Model Measures Radiation Exposure in Blood for Precise Cancer Treatments

Scientists have long focused on protecting organs near tumors during radiotherapy, but blood — a vital, circulating tissue — has largely been excluded from dose calculations. Each blood cell passing through... Read more

Immunology

view channel
Image: The test could streamline clinical decision-making by identifying ideal candidates for immunotherapy upfront (Xiao, Y. et al. Cancer Biology & Medicine July 2025, 20250038)

Blood Test Predicts Immunotherapy Efficacy in Triple-Negative Breast Cancer

Triple-negative breast cancer (TNBC) is an aggressive subtype lacking targeted therapies, making immunotherapy a promising yet unpredictable option. Current biomarkers such as PD-L1 expression or tumor... Read more

Microbiology

view channel
Image: New diagnostics could predict a woman’s risk of a common sexually transmitted infection (Photo courtesy of 123RF)

New Markers Could Predict Risk of Severe Chlamydia Infection

Chlamydia trachomatis is a common sexually transmitted infection that can cause pelvic inflammatory disease, infertility, and other reproductive complications when it spreads to the upper genital tract.... Read more

Technology

view channel
Image: The sensor can help diagnose diabetes and prediabetes on-site in a few minutes using just a breath sample (Photo courtesy of Larry Cheng/Penn State)

Graphene-Based Sensor Uses Breath Sample to Identify Diabetes and Prediabetes in Minutes

About 37 million U.S. adults live with diabetes, and one in five is unaware of their condition. Diagnosing diabetes often requires blood draws or lab visits, which are costly and inconvenient.... Read more
Copyright © 2000-2025 Globetech Media. All rights reserved.