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
RANDOX LABORATORIES

Download Mobile App




Neural Network Recognizes Breast Cancer on Histological Samples With 100% Accuracy

By LabMedica International staff writers
Posted on 02 Feb 2024
Print article
Image: The “attentive” neural network recognizes breast cancer with 99.6% accuracy (Photo courtesy of RUDN University)
Image: The “attentive” neural network recognizes breast cancer with 99.6% accuracy (Photo courtesy of RUDN University)

The likelihood of a favorable outcome for a breast cancer patient is greatly influenced by the stage at which the cancer is diagnosed. Histological examination is the benchmark for diagnosis, but its reliability can be affected by subjective interpretations and the quality of the tissue sample. Inaccuracies in these examinations can lead to incorrect diagnoses. Now, a team of mathematicians has developed a machine learning model that significantly enhances the accuracy of identifying cancer in histological images. The highlight of this model is the incorporation of an additional module that boosts the neural network's "attention" capability, enabling it to achieve near-perfect accuracy.

The mathematicians at RUDN University (Moscow, Russia) conducted tests on several convolutional neural networks and supplemented them with two convolutional attention modules. These modules are crucial for detecting objects within images. The model underwent training and testing using the BreakHis dataset, which comprises nearly 10,000 histological images at various scales, sourced from 82 patients. The most impressive performance came from a model that combined the DenseNet211 convolutional network with the attention modules, achieving a remarkable accuracy rate of 99.6%. The research team noted that the detection of cancerous formations is affected by image scale. This is because images differ in quality at various zoom levels, and cancerous formations appear differently. Therefore, during practical application, selecting the appropriate scale for image analysis must be a critical consideration.

“Computer classification of histological images will reduce the burden on doctors and increase the accuracy of tests. Such technologies will improve the treatment and diagnosis of breast cancer. Deep learning methods have shown promising results in medical image analysis problems in recent years,” said Ammar Muthanna, Ph.D., Director of the Scientific Center for Modeling Wireless 5G Networks at RUDN University. “The attention modules in the model improved feature extraction and the overall performance of the model. With their help, the model focused on significant areas of the image and highlighted the necessary information. It shows the importance of attention mechanisms in the analysis of medical images.”

Related Links:
RUDN University

New
Platinum Member
Flu SARS-CoV-2 Combo Test
OSOM® Flu SARS-CoV-2 Combo Test
Magnetic Bead Separation Modules
MAG and HEATMAG
Anti-Cyclic Citrullinated Peptide Test
GPP-100 Anti-CCP Kit
New
Gold Member
Rickettsia Conorii Assay
RICKETTSIA CONORII ELISA

Print article
77 ELEKTRONIKA

Channels

Clinical Chemistry

view channel
Image: PhD student and first author Tarek Eissa has analyzed thousands of molecular fingerprints (Photo courtesy of Thorsten Naeser / MPQ / Attoworld)

Screening Tool Detects Multiple Health Conditions from Single Blood Drop

Infrared spectroscopy, a method using infrared light to study the molecular composition of substances, has been a foundational tool in chemistry for decades, functioning similarly to a molecular fingerprinting... Read more

Molecular Diagnostics

view channel
Image: Protein ‘signatures’ obtained via a blood sample can be used to predict the onset of 67 diseases (Photo courtesy of Queen Mary University of London)

Protein Signatures in Blood Can Predict Risk of Developing More Than 60 Diseases

Measuring specific proteins to diagnose conditions like heart attacks, where troponin is tested, is a well-established clinical practice. Now, new research highlights the broader potential of protein measurements... Read more

Hematology

view channel
Image: The Truvian diagnostic platform combines clinical chemistry, immunoassay and hematology testing in a single run (Photo courtesy of Truvian Health)

Automated Benchtop System to Bring Blood Testing To Anyone, Anywhere

Almost all medical decisions are dependent upon laboratory test results, which are essential for disease prevention and the management of chronic illnesses. However, routine blood testing remains limited worldwide.... Read more

Microbiology

view channel
Image: The Simplexa C. auris direct kit is a real-time polymerase chain reaction assay run on the LIAISON MDX instrument (Photo courtesy of Diasorin)

Novel Molecular Test to Help Prevent and Control Multi Drug-Resistant Fungal Pathogen in Healthcare Settings

Candida auris (C. auris) is a rapidly emerging multi drug-resistant fungal pathogen that is commonly found in healthcare environments, where it presents a challenge due to its ability to asymptomatically... Read more

Industry

view channel
Image: Beckman Coulter will utilize the ALZpath pTau217 antibody to detect key biomarker for Alzheimer\'s disease on its DxI 9000 immunoassay analyzer (Photo courtesy of Beckman Coulter)

Beckman Coulter Licenses Alzpath's Proprietary P-tau 217 Antibody to Develop Alzheimer's Blood Test

Cognitive assessments have traditionally been the primary method for diagnosing Alzheimer’s disease, but this approach has its limitations as symptoms become apparent only after significant brain changes... Read more
Copyright © 2000-2024 Globetech Media. All rights reserved.