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.

LabMedica

Download Mobile App
Recent News Expo Clinical Chem. Molecular Diagnostics Hematology Immunology Microbiology Pathology Technology Industry Focus

AI-Based Digital Pathology Platform Improves Lung Cancer Diagnosis

By LabMedica International staff writers
Posted on 26 Aug 2024

Lung cancer ranks among the most prevalent and fatal cancers worldwide. Current treatment strategies for lung cancer patients rely on pathological examinations, which can reveal genetic mutations specific to the patient's cancer, facilitating personalized treatment approaches. Over the last few years, pathology has evolved dramatically due to digital advancements, making traditional microscopes obsolete. Tissue samples are now digitized and analyzed via computer screens, which is essential for employing sophisticated artificial intelligence (AI)-based analytical methods. These AI technologies can extract additional insights from pathological tissue sections that were previously unattainable.

A team of researchers at the University of Cologne (Cologne, Germany) has developed an AI-driven digital pathology platform that can revolutionize the analysis of lung cancer tissues. This platform utilizes newly developed algorithms to perform fully automated examination of digitized lung cancer tissue sections, offering faster and more precise analyses than traditional methods. Detailed in their publication in the journal Cell Reports Medicine, the platform is founded on the most extensive and high-quality dataset available, enabling it to process H&E-stained whole-slide images (WSIs) of both resection and biopsy specimens from non-small cell lung cancer (NSCLC) patients. It can accurately segment all relevant tumor and benign tissue classes at the pixel level.


Image: The new AI-based digital platform enables extremely fast and accurate analysis of tissue sections from lung cancer patients (Photo courtesy of Dr. Yuri Tolkach)
Image: The new AI-based digital platform enables extremely fast and accurate analysis of tissue sections from lung cancer patients (Photo courtesy of Dr. Yuri Tolkach)

The core of this platform is a cutting-edge multi-class tissue segmentation algorithm, marking a significant leap in the accuracy and precision of lung cancer pathology. This development is among a handful of published studies that focus on tissue detection and classification in WSIs from lung cancer patients. Furthermore, the research team has identified four prognostic parameters that have proven effective in stratifying NSCLC patients prognostically, which could be crucial for determining patient eligibility for adjuvant therapy following surgery. To support ongoing academic research and enhance algorithm development and benchmarking, the team has made four of their annotated test datasets publicly available. This innovative platform is poised to transform various diagnostic, prognostic, and predictive applications within the field.

“We also show how the platform could be used to develop new clinical tools,” said physician Dr. Yuri Tolkach from the Institute of General Pathology and Pathological Anatomy at University Hospital Cologne, who led the study. “The new tools can not only improve the quality of diagnosis, but also provide new types of information about the patient’s disease, such as how the patient is responding to treatment.”

Related Links:
University of Cologne


New
Gold Member
Thyroid Stimulating Hormone Assay
TSH EIA 96 Test
Antipsychotic TDM Assays
Saladax Antipsychotic Assays
New
Dengue Test
Lab Rapid Dengue NS1
New
C-Reactive Protein Test
mLabs CRP

Latest Pathology News

AI Model Identifies Sex-Specific Risks Associated with Brain Tumors

Breakthrough Virus Detection Technology Combines Confocal Fluorescence Microscopy with Microfluidic Laminar Flow

AI Technology Accurately Predicts Breast Cancer Risk Via ‘Zombie Cells’