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
PURITAN MEDICAL

Download Mobile App




Events

ATTENTION: Due to the COVID-19 PANDEMIC, many events are being rescheduled for a later date, converted into virtual venues, or altogether cancelled. Please check with the event organizer or website prior to planning for any forthcoming event.

AI Pathological Analysis System More Accurate than Humans in Reading Digital Biopsy Images

By LabMedica International staff writers
Posted on 05 Dec 2022
Print article
Image: A deep-learning system looks at breast cancer scans better than a human ever could (Photo courtesy of Pexels)
Image: A deep-learning system looks at breast cancer scans better than a human ever could (Photo courtesy of Pexels)

One in nine women in the developed world will be diagnosed with breast cancer at some point in her life. The prevalence of breast cancer is increasing, an effect caused in part by the modern lifestyle and increased life spans. Thankfully, treatments are becoming more efficient and more personalized. However, what isn’t increasing – and is in fact decreasing – is the number of pathologists, or the doctors whose specialization is examining body tissues to provide the specific diagnosis necessary for personalized medicine. Now, a team of researchers have made it their quest to turn computers into effective pathologists’ assistants, simplifying and improving the human doctor’s work.

The specific task that researchers at the Technion – Israel Institute of Technology (Haifa, Israel) have set out to achieve lies within the realm of immunotherapy. Immunotherapy has been gaining prominence in recent years as an effective, sometimes even game-changing, treatment for several types of cancer. The basis of this form of therapy is encouraging the body’s own immune system to attack the tumor. However, such therapy needs to be personalized as the correct medication must be administered to the patients who stand to benefit from it based on the specific characteristics of the tumor.

Multiple natural mechanisms prevent our immune systems from attacking our own bodies. These mechanisms are often exploited by cancer tumors to evade the immune system. One such mechanism is related to the PD-L1 protein – some tumors display it, and it acts as a sort of password by erroneously convincing the immune system that the cancer should not be attacked. Specific immunotherapy for PD-L1 can persuade the immune system to ignore this particular password, but of course would only be effective when the tumor expresses the PD-L1. It is a pathologist’s task to determine whether a patient’s tumor expresses PD-L1. Expensive chemical markers are used to stain a biopsy taken from the tumor in order to obtain the answer. The process is non-trivial, time-consuming, and at times inconsistent.

The Technion researchers took a different approach. In recent years, it has become an FDA-approved practice for biopsies to be scanned so they can be used for digital pathological analysis. The researchers decided to see if a neural network could use these scans to make the diagnosis without requiring additional processes. Neural networks are trained in a manner similar to how children learn: they are presented with multiple tagged examples. A child is shown many dogs and various other things, and from these examples forms an idea of what “dog” is.

The neural network developed by the Technion researchers was presented with digital biopsy images from 3,376 patients that were tagged as either expressing or not expressing PD-L1. After preliminary validation, it was asked to determine whether additional clinical trial biopsy images from 275 patients were positive or negative for PD-L1. It performed better than expected: for 70% of the patients, it was able to confidently and correctly determine the answer. For the remaining 30% of the patients, the program could not find the visual patterns that would enable it to decide one way or the other. Interestingly, in the cases where the artificial intelligence (AI) disagreed with the human pathologist’s determination, a second test proved the AI to be right.

“This is a momentous achievement,” explained Professor Ron Kimmel from the Henry and Marilyn Taub Faculty of Computer Science at the Technion. “The variations that the computer found – they are not distinguishable to the human eye. Cells arrange themselves differently if they present PD-L1 or not, but the differences are so small that even a trained pathologist can’t confidently identify them. Now our neural network can.”

“We expect AI to become a powerful tool in doctors’ hands,” added Prof. Kimmel. “AI can assist in making or verifying a diagnosis, it can help match the treatment to the individual patient, it can offer a prognosis. I do not think it can, or should, replace the human doctor. But it can make some elements of doctors’ work simpler, faster, and more precise.”

Related Links:
Technion

HLX
Gold Supplier
Blood Glucose Reference Analyzer
Nova Primary
New
IFA Automation Solution
dIFine 30 System
New
Diagnostic Salivary DHEA ELISA Kit
Salimetrics Salivary DHEA Enzyme Immunoassay Kit

Print article

Channels

Clinical Chem.

view channel
Image: Electrochemical cells etched by laser on wooden tongue depressor measure glucose and nitrite in saliva (Photo courtesy of Analytical Chemistry)

Biosensor-Fabricated Wooden Tongue Depressor Measures Glucose and Nitrite in Saliva

Physicians often use tongue depressors to examine a patient's mouth and throat. However, it is hard to imagine that this simple wooden tool could actively assess a patient's health. This idea has led to... Read more

Hematology

view channel
Image: The Atellica HEMA 570 and 580 hematology analyzers remove workflow barriers (Photo courtesy of Siemens)

Next-Gen Hematology Analyzers Eliminate Workflow Roadblocks and Achieve Fast Throughput

Hematology testing is a critical aspect of patient care, utilized to establish a patient's health baseline, track treatment progress, or guide timely modifications to care. However, increasing constraints... Read more

Immunology

view channel
Image: Newly observed anti-FSP antibodies have also been found to predict immune-related adverse events (Photo courtesy of Calviri)

First Blood-Based Biomarkers Test to Predict Treatment Response in Cancer Patients

Every year worldwide, lung cancer afflicts over two million individuals and almost the same number of people succumb to the disease. This malignancy leads the charts in cancer-related mortalities, with... Read more

Microbiology

view channel
Image: The rapid MTB strip test for tuberculosis can identify TB patients within two hours (Photo courtesy of Chulalongkorn University)

Rapid MTB Strip Test Detects Tuberculosis in Less Than an Hour without Special Tools

Tuberculosis (TB), a highly infectious disease, continues to pose significant challenges to public health worldwide. TB is caused by a bacterium known as "Mycobacterium tuberculosis," spreading through... Read more

Technology

view channel
Electronic biosensor uses DNA aptamers for detecting biomarkers in whole blood samples (Photo courtesy of Freepik)

Electronic Biosensor Detects Biomarkers in Whole Blood Samples without Addition of Reagents

The absence of robust, reliable, and user-friendly bioanalytical tools for early and timely diagnosis of cardiovascular diseases, particularly sudden cardiac arrest, leads to preventable deaths and imposes... Read more

Industry

view channel
Image: The global HbA1c testing devices market is expected to reach USD 2.56 billion in 2027 (Photo courtesy of Freepik)

Global Hemoglobin A1c Testing Devices Market Driven by Rising Prevalence of Diabetes

Hemoglobin A1c (HbA1c), or glycated hemoglobin, refers to hemoglobin with glucose attached. HbA1c testing devices are used for blood tests that determine average blood glucose, or blood sugar levels.... Read more
Copyright © 2000-2023 Globetech Media. All rights reserved.