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
Sign In
Advertise with Us
Siemens Healthineers - Laboratory Diagnostics

Download Mobile App

Machine Learning Solution Assists Pathologists in Detection of Precancerous Cervical Lesions

By LabMedica International staff writers
Posted on 15 Jun 2023
Print article
Image: A machine learning solution assists pathologists in detection of cervical dysplasia (Photo courtesy of Freepik)
Image: A machine learning solution assists pathologists in detection of cervical dysplasia (Photo courtesy of Freepik)

Cervical cancer ranks as the fourth most prevalent cancer in women, with a reported 604,000 new occurrences in 2020, as per the World Health Organization (WHO). Yet, it stands out as one of the most successfully preventable and treatable cancers, provided that it is detected early and managed appropriately. Therefore, early detection of pre-cancerous lesions is critical for disease prevention. Now, researchers have developed an innovative method using large, high-resolution images to detect crucial pre-cancerous lesions.

A team of researchers from INESC TEC (Porto, Portugal) and IMP Diagnostics (Porto, Portugal) has designed a machine learning solution to aid pathologists in detecting cervical dysplasia, making the diagnosis process of new samples fully automatic. This is among the first published works to utilize complete slides. The researchers set out to develop machine learning models to support the subjective classification of lesions in the squamous epithelium - the protective tissue layer against microorganisms - using whole-slide images (WSI) that contain information from the entire tissue.

The team developed a weakly-supervised methodology - a machine learning method that combines annotated and non-annotated data in the model training phase to classify cervical dysplasia. This technique proves particularly beneficial considering the difficulty of obtaining pathology data annotations: the large image sizes make the annotation process extremely time-consuming, tedious, and highly subjective. This methodology enables researchers to establish models with high performance, even when there's some missing information during the training phase. The resulting model can then grade cervical dysplasia, or abnormal cell growth on the surface, as low (LSIL) or high-grade intraepithelial squamous lesions (HSIL). Given the complexity and subjective nature of the classification process, these machine learning models can provide valuable assistance to pathologists. Furthermore, these systems could act as an early warning mechanism for suspicious cases, alerting pathologists to instances that warrant closer examination.

"In the detection of cervical dysplasia, this was one of the first published works that use the full slides, following an approach that includes the segmentation and subsequent classification of the areas of interest, making the diagnosis of new samples completely automatic," explained Sara Oliveira, a researcher at INESC TEC.

Related Links:
IMP Diagnostics 

Platinum Supplier
Xylazine Immunoassay Test
Xylazine ELISA
Gold Supplier
Automated, Random Access Chemistry Analyzer
LIDA 300
Concentrated Anionic Detergent
Semi Auto Biochemistry Analyzer

Print article


Clinical Chemistry

view channel
Image: The new assays are designed to run on the B•R•A•H•M•S KRYPTOR compact PLUS clinical chemistry analyzer (Photo courtesy of Thermo Fisher)

Breakthrough Immunoassays to Aid in Risk Assessment of Preeclampsia

Preeclampsia is a life-threatening blood pressure condition that can arise during pregnancy and the postpartum phase. This severe pregnancy complication is a primary cause of maternal and fetal mortality... Read more

Molecular Diagnostics

view channel
Image: A CRISPR technology-based diagnostic test detects MPXV in clinical samples with acute precision (Photo courtesy of 123RF)

Powerful Diagnostic Tool Accurately Detects Monkeypox Virus Faster Than Any Method

At present, testing for the monkeypox virus (MPXV) is done mainly in centralized labs, and it can take days to get results due to location and logistical issues. Now, researchers have leveraged cutting-edge... Read more


view channel
Image: The US FDA has cleared HemoScreen point of care CBC for direct capillary sampling (Photo courtesy of PixCell Medical)

Point of Care CBC Analyzer with Direct Capillary Sampling Enhances Ease-of-Use and Testing Throughput

The world’s only 5-part differential Complete Blood Count (CBC) analyzer that is FDA-cleared, CE-marked, and TGA-approved for point-of-care use has now been granted FDA 510(k) clearance for direct capillary... Read more


view channel
Image: Immune cells present long before infection predict flu symptoms (Photo courtesy of Shutterstock.com)

Single Blood Draw to Detect Immune Cells Present Months before Flu Infection Can Predict Symptoms

For decades, if not centuries, scientists have struggled to solve the mystery of why certain individuals fall ill to infections while others remain unaffected. In an impressive development, researchers... Read more


view channel
Image: The rapid diagnostic test could pinpoint the correct antibiotic for infection treatment in under an hour (Photo courtesy of Microplate Dx)

Point-of-Care Device to Reduce Antibiotic Susceptibility Testing Time from Days to Minutes

Antimicrobial resistance (AMR) is a significant global health issue, currently leading to over 1.27 million deaths worldwide each year. By 2050, AMR could be causing up to 10 million deaths annually, surpassing... Read more


view channel
Image: A new electrochemical device can quickly and inexpensively identify people at greatest risk for osteoporosis (Photo courtesy of ACS Central Science, 2023)

Electrochemical Device Identifies People at Higher Risk for Osteoporosis Using Single Blood Drop

With the global increase in life expectancy, the incidence of age-related conditions like osteoporosis is increasing. Osteoporosis, affecting around 200 million individuals worldwide, has a higher incidence... Read more


view channel
Image: The global fully automatic electrolyte analyzers market is projected to reach close to USD 0.77 billion by 2032 (Photo courtesy of 123RF)

Global Fully Automatic Electrolyte Analyzers Market Driven by Surge in Demand for Point-of-Care Testing

Fully automatic electrolyte analyzers can measure the levels of electrolytes in various bodily fluids like blood and plasma. Electrolytes are ions that have an electrical charge and are essential for multiple... Read more
Copyright © 2000-2023 Globetech Media. All rights reserved.