Trending...
- Cyrus Webb and Conversations Media Group Providing New Opportunities for Authors and Creatives to Shine and Thrive
- 24 Hour Fitness Offers Full Club Access to Los Angeles Area Residents
- Crunch Fitness to Open Doors to those Affected by the Los Angeles Wildfires
LOS ANGELES - Californer -- The human epidermal growth factor receptor 2 (HER2) is a critical protein in the growth of cancer cells, and its expression level is a vital indicator of breast cancer aggressiveness. Traditionally, HER2 status is assessed manually by pathologists examining immunohistochemically (IHC) stained tissue slides. This manual process, however, is often subject to inter- and intra-observer variability and can be time-consuming, leading to potential delays in diagnosis and treatment planning.
The research team, led by Professor Aydogan Ozcan of UCLA, has developed an automated system using deep learning to analyze morphological features at various spatial scales. This system addresses the tissue heterogeneity of HER2 expression, providing a comprehensive view and achieving a high HER2 score classification accuracy of 84.70% on a dataset of 523 core images from tissue microarrays.
The deep learning model introduced by the researchers utilizes a pyramid sampling strategy, which captures and integrates patches of varying scales from high-resolution images into a Pyramid-Sampling Set (PSS). This multi-scale approach ensures a detailed examination of both cellular features and broader tissue architecture, enhancing the accuracy of HER2 status classification.
More on The Californer
During the training phase, the model was trained on 1462 core images from 823 patients, with an additional set of 162 cores from 149 patients used for validation. The efficacy of the model was blindly evaluated using a set of 523 core images from 300 patients that were not previously seen during the training or validation phases. The study involved five board-certified pathologists to independently score the cores, ensuring robust dataset labeling and minimizing the risk of relying on possibly inaccurate patient records due to tissue heterogeneity.
This automated system has the potential to revolutionize the assessment of HER2 status in clinical settings. By providing a reliable adjunct tool for pathologists, it can enhance diagnostic precision, reduce turnaround times, and ultimately improve patient outcomes. The automated approach standardizes HER2 assessment and streamlines the pathologists' workflow, making it especially valuable in resource-constrained areas where expert breast pathologists may be limited.
More on The Californer
The research team acknowledges that while the model demonstrated a high accuracy of 84.70%, further work is needed to enhance its robustness and generalizability to external datasets. Future studies will explore incorporating color normalization and other enhancement techniques to ensure consistent performance across diverse imaging and staining conditions.
This study marks a significant milestone in breast cancer diagnostics, paving the way for more nuanced, faster, and more accessible diagnostic tools. The integration of deep learning and pyramid sampling in HER2 scoring not only enhances the accuracy and reliability of breast cancer diagnostics but also contributes to the advancement of personalized medicine, ultimately improving patient care in oncology.
The authors acknowledge the funding of the NSF Biophotonics Program and the NIH National Center for Interventional Biophotonic Technologies.
Original paper: https://doi.org/10.34133/bmef.0048
The research team, led by Professor Aydogan Ozcan of UCLA, has developed an automated system using deep learning to analyze morphological features at various spatial scales. This system addresses the tissue heterogeneity of HER2 expression, providing a comprehensive view and achieving a high HER2 score classification accuracy of 84.70% on a dataset of 523 core images from tissue microarrays.
The deep learning model introduced by the researchers utilizes a pyramid sampling strategy, which captures and integrates patches of varying scales from high-resolution images into a Pyramid-Sampling Set (PSS). This multi-scale approach ensures a detailed examination of both cellular features and broader tissue architecture, enhancing the accuracy of HER2 status classification.
More on The Californer
- California: Governor Newsom Proclaims Dr. Martin Luther King, Jr. Day 2025
- Boys & Girls Clubs of Silicon Valley names Veronica Jowers Chief of Staff
- City of Long Beach Continues Activation of Inclement Weather Shelter for People Experiencing Homelessness
- AI Appointment Setters: The Benefits of AI Agents Over Expensive Receptionists
- California: Here's all the actions Governor Newsom has taken in response to the Los Angeles fires
During the training phase, the model was trained on 1462 core images from 823 patients, with an additional set of 162 cores from 149 patients used for validation. The efficacy of the model was blindly evaluated using a set of 523 core images from 300 patients that were not previously seen during the training or validation phases. The study involved five board-certified pathologists to independently score the cores, ensuring robust dataset labeling and minimizing the risk of relying on possibly inaccurate patient records due to tissue heterogeneity.
This automated system has the potential to revolutionize the assessment of HER2 status in clinical settings. By providing a reliable adjunct tool for pathologists, it can enhance diagnostic precision, reduce turnaround times, and ultimately improve patient outcomes. The automated approach standardizes HER2 assessment and streamlines the pathologists' workflow, making it especially valuable in resource-constrained areas where expert breast pathologists may be limited.
More on The Californer
- California: Governor Newsom issues order to protect fire victims from predatory real estate speculators
- Wildfire-Ravaged Communities in California Receive Support from Local Lions Through $100K+ Lions Clubs International Foundation Grant Funds
- IntellaTriage Launches New Patient Engagement Service
- Cascadia Global Security Launches Cascadia Off-Duty
- Anti-Racism Song from Neal Fox Drops in Time for Martin Luther King Day
The research team acknowledges that while the model demonstrated a high accuracy of 84.70%, further work is needed to enhance its robustness and generalizability to external datasets. Future studies will explore incorporating color normalization and other enhancement techniques to ensure consistent performance across diverse imaging and staining conditions.
This study marks a significant milestone in breast cancer diagnostics, paving the way for more nuanced, faster, and more accessible diagnostic tools. The integration of deep learning and pyramid sampling in HER2 scoring not only enhances the accuracy and reliability of breast cancer diagnostics but also contributes to the advancement of personalized medicine, ultimately improving patient care in oncology.
The authors acknowledge the funding of the NSF Biophotonics Program and the NIH National Center for Interventional Biophotonic Technologies.
Original paper: https://doi.org/10.34133/bmef.0048
Source: ucla ita
Filed Under: Health
0 Comments
Latest on The Californer
- Orcas Island Property Owner Returns Two Prime Waterfront Properties to the Market
- Maine Coon Maniacs Launches Guide on Maine Coon Cats for Sale in California
- YEYIAN GAMING Shines at CES 2025 with Groundbreaking Gaming PCs and Hardware Launches
- California: Governor Newsom mobilizes L.A. debris removal teams to begin work immediately once cleared for safety
- Muench Workshops Welcomes New Partners Luke Dray and Sara Linssen, Announces Retirement of Andy Williams
- California: Governor Newsom signs executive order to quickly help L.A. schools, children and families affected by firestorms
- Long Beach: City Health Officer Advises Residents to Avoid Leaf Blowers While LA Region is Impacted by Wildfires
- Long Beach Shares Event Details for 2025 Martin Luther King, Jr. Parade and Celebration
- Revitalized Resource for Photography Workshops in North America Now Live on Muench Workshops' Site
- High-Performance AC Sources Built For Standards Based Testing
- NuNorm Announces Stop Soldier Suicide as This Year's EQUAL Grant Recipient
- What Is Your Impact? New Book Discovering Your Legacy Will Reshape Your Views on Your Life, Your Legacy & Your Purpose
- Southeast Ventura County YMCA and California Strong Will Provide Essential Supplies To Fire Victims
- A Legendary Unreleased Game Arrives - 35 Years After Its Cancellation
- Savvas Learning Company is Named to the GSV 150 For the Third Year in a Row
- BKM Capital Partners Releases White Paper Examining E-Commerce's Profound Impact on Industrial Real Estate
- RevArt and CoBiz Richmond Partner to Empower Local Artists and Foster Community Creativity
- Darrin Jones: The Creative Force Behind the Trends—Raising Questions About Influence in The Weeknd's Music
- Foresight Practitioner Conference 2025 – Dates, Venue, Speakers, And Competition Finalists Announced
- Car Insurance Myths That Put a Dent in Your Wallet