Connect with us

Technology

New Lunit Study Demonstrates Universal AI Model for Analysis of Immunohistochemistry Images

Published

2 years ago

on

Research in npj Precision Oncology highlights multi-cohort training approach and accurate analysis of unseen immunohistochemistry data

SEOUL, South Korea, Dec. 12, 2024 /PRNewswire/ — Lunit (KRX:328130.KQ), a leading provider of AI-powered solutions for cancer diagnostics and therapeutics, today announced the publication of a new study in npj Precision Oncology detailing the development of its Universal Immunohistochemistry (uIHC) AI model. The study demonstrates how the model excels at analyzing diverse cancer types and IHC stains, including datasets it had never encountered before, due to a novel training approach. Now commercialized as Lunit SCOPE uIHC, the model enables advanced biomarker formation from even singleplex IHC, with subcellular stain localization, continuous intensity scoring, and cell type identification..

Addressing Challenges in IHC Analysis

Immunohistochemistry (IHC) is an essential tool in oncology, enabling pathologists to detect and quantify protein expression which in turn guides decisions for systemic therapy. However, while several AI algorithms exist to assist in scoring IHC images and improving accuracy, current AI models face two major limitations:

Data Dependency: Current AI-IHC models require large numbers of immunostain-specific images for training, which are difficult to obtain, particularly for novel immunostain-target pairs.Lack of Generalization: Current  AI-IHC models struggle to analyze datasets that differ from their training set either in immunostain or cancer types, limiting their ability to be effective in diverse indications.

These challenges underscore the need for scalable solutions capable of accurate analysis across a wide range of cancer types and immunostains.

uIHC Model Outperforms in Generalization

Lunit’s study compared eight deep learning models, including four single-cohort (trained using data from a single stain or cancer type) and four multi-cohort (trained on combined datasets spanning multiple stains and cancer types) approaches, to evaluate their performance on both familiar and unseen datasets. The results validated the uIHC model’s ability to generalize across diverse datasets with high accuracy.

Key results include:

High Concordance on Known Datasets: The uIHC model achieved a Cohen’s kappa score of 0.792, surpassing the best single-cohort model, which scored 0.744 when analyzing known cancer types and immunostains.Superior Generalization to Unseen Data: On novel datasets involving previously unseen cancer types and immunostains, the uIHC model achieved a Cohen’s kappa score of 0.610, representing a relative improvement of 10.2% over the single-cohort model average of 0.508.Enhanced Tumor Proportion Score (TPS) Accuracy: Across multi-stain test sets, the uIHC model achieved an AUC of 0.921 for TPS evaluations and a TPS accuracy of 75.7%, demonstrating its reliability in quantifying IHC images.

These findings highlight the model’s robust performance across a wide variety of cancer types and immunostains, including those it had not been trained on.

The uIHC model’s ability to generalize across diverse IHC images marks a transformative step in digital pathology. By reducing the dependency on large stain-specific datasets, it enables scalable and efficient biomarker analysis for clinical diagnostics and drug development. This capability is particularly valuable for evaluating new biomarkers associated with novel therapies, addressing a critical bottleneck in precision oncology.

“Our Universal Immunohistochemistry AI model solves a practical bottleneck in development settings—handling unseen cancer types and stains without requiring additional data annotation,” said Brandon Suh, CEO of Lunit. “By proving the effectiveness of a multi-cohort training approach, this study shows how AI can be adapted to real-world complexities, delivering both precision and scalability. With the launch of Lunit SCOPE uIHC, we’re enabling researchers and clinicians to focus on what truly matters: advancing patient care and accelerating therapeutic innovation.”

About Lunit

Founded in 2013, Lunit (KRX:328130.KQ) is a medical AI company on a mission to conquer cancer. We harness AI-powered medical image analytics and AI biomarkers to ensure accurate diagnosis and optimal treatment for each cancer patient. The FDA-cleared Lunit INSIGHT suite for cancer screening serves over 4,500 hospitals and medical institutions across 55+ countries.

Lunit clinical studies have been published in top journals, including the Journal of Clinical Oncology and the Lancet Digital Health, and presented at global conferences such as ASCO and RSNA. In 2024, Lunit acquired Volpara Health Technologies, setting the stage for unparalleled synergy and accuracy, particularly in breast health and screening technologies. Headquartered in Seoul, South Korea, with a network of offices worldwide, Lunit leads the global fight against cancer. Discover more at lunit.io.

View original content to download multimedia:https://www.prnewswire.com/news-releases/new-lunit-study-demonstrates-universal-ai-model-for-analysis-of-immunohistochemistry-images-302330295.html

SOURCE Lunit

Related Topics:
Continue Reading

Technology

Pavlov Media Employees Give Back Through Nationwide Day of Service, Contributing More Than 500 Volunteer Hours

Published

35 minutes ago

on

November 6, 2026

By

More than 100 team members supported local nonprofits, community organizations, and environmental initiatives across the United States.

CHAMPAIGN, Ill., Nov. 6, 2026 /PRNewswire/ — Pavlov Media, a leading provider of fiber-optic Internet and managed Wi-Fi solutions, recently brought employees together for a company-wide Day of Service, contributing more than 500 hours of volunteer work to communities across the United States. The event builds on the company’s ongoing commitment to giving back through Pavlov Cares, its community outreach and philanthropic program.

More than 100 Pavlov Media employees participated in the initiative, dedicating their time to supporting local nonprofits, environmental conservation efforts, food assistance programs, and other community-focused organizations.

The Day of Service brought employees together around a shared commitment to making a meaningful difference in the communities where they live and work. From supporting food banks and animal rescue organizations to maintaining public spaces and assisting local nonprofits, team members stepped away from their daily responsibilities to give back.

“At Pavlov Media, our commitment to the communities we serve extends beyond providing Internet,” says Cory Douglas, CEO of Pavlov Media. “Through our Pavlov Cares program, we support organizations that strengthen the places where we live and work. Seeing more than 100 employees come together for this initiative is a reflection of the people who make up our organization.”

Making an Impact Across Communities

Employees volunteered with a variety of organizations and community initiatives, including:

Salt & Light (Champaign/Urbana, IL): Supporting community assistance programs in Central Illinois.Eastern Illinois Foodbank (Urbana, IL): Contributing to efforts addressing food insecurity.Champaign Public Library (Champaign, IL): Supporting a valuable community resource.Champaign County Forest Preserve District (Champaign County, IL): Assisting with invasive plant removal and botanical garden maintenance.Moore’s Rescue Ranch/Kitty Crib (Urbana, IL): Supporting local animal rescue and care efforts.Aikman Wildlife Adventure (Arcola, IL): Enhancing visitor spaces through grounds maintenance and revitalizing the indoor play area.Atlanta Food Bank (Atlanta, GA): Supporting efforts to address food insecurity in Georgia.GRACE Marketplace (Gainesville, FL): Supporting programs assisting individuals experiencing homelessness.Corinth Park District (Corinth, TX): Helping maintain community parks and recreational spaces. 

Connecting Through Community Service

Pavlov Media’s Day of Service provided employees with an opportunity to collaborate outside the workplace while supporting organizations that make a difference in their communities.

With more than 500 hours of service contributed nationwide, the initiative reflects the collective impact employees can make when they come together for a shared purpose.

Through our Pavlov Cares program, Pavlov Media continues to support local and national organizations dedicated to strengthening communities and improving lives. The company’s Day of Service reflects this ongoing commitment, bringing employees together to make a meaningful difference beyond their everyday work.

Learn more about Pavlov Cares at www.pavlovmedia.com/pavlov-cares/.

About Pavlov Media

Pavlov Media is a provider of fiber-optic Internet and managed Wi-Fi solutions serving residential communities, multifamily properties, student housing, and businesses across the United States. With a focus on connectivity, innovation, and customer experience, Pavlov Media delivers Internet solutions designed to meet the evolving needs of the communities it serves.

Learn more at https://mdu.pavlovmedia.com/

View original content to download multimedia:https://www.prnewswire.com/news-releases/pavlov-media-employees-give-back-through-nationwide-day-of-service-contributing-more-than-500-volunteer-hours-302930898.html

SOURCE Pavlov Media

Continue Reading

Technology

Urban Outfitters Invites Everyone to the Party with “All Together Now: More the Merrier” Holiday Campaign

Published

35 minutes ago

on

November 6, 2026

By

Rooted in Gen Z insights, UO celebrates the season with the most coveted gifts, festive fashion, and community experiences, kicking off with a holiday celebration in partnership with DoorDash.

PHILADELPHIA, Nov. 6, 2026 /PRNewswire/ — Urban Outfitters is inviting everyone to the party this holiday season with the launch of “All Together Now: More the Merrier,” an omnichannel campaign that taps into the personal style and shared experiences that make the season special. Building on the brand’s All Together Now platform, the campaign celebrates the joy of coming together and captures the excitement of the season, from getting ready and finding the perfect outfit to showing up and celebrating with friends.

At the heart of the campaign is UO’s understanding of how Gen Z lives, shops, and celebrates. Insights from UO Insiders, the brand’s community of more than 10,000 Gen Z shoppers, students, and influencers, reveal that 85% of Gen Z shoppers self-gift during the holidays—purchasing an average of seven to eight items for themselves. Alongside self-gifting, 78% of Gen Z prefer to shop with someone else, underscoring this generation’s focus on community and togetherness.

“At Urban Outfitters, everything starts with understanding our customer,” said Shea Jensen, President of Urban Outfitters. “More the Merrier brings together the products, brands, and experiences they love, with new ways to discover and make the holiday season even more memorable.”

The campaign kicked off with an exclusive launch party in Los Angeles on November 5, reuniting members of UO’s always-on community, including Meet Me@UO Joshua Tree attendees, All Together Now commercial cast members, and Game Day student ambassadors. Designed for connection, creativity, and community, the evening featured seasonal activations, including white elephant, customization stations, and a surprise UO Live performance by Grammy-nominated artist DESTIN CONRAD. The party was brought to life in partnership with DoorDash, building on the UO’s strategy to make last-minute gifting and getting-ready essentials more accessible through on-demand delivery.

Extending the celebration beyond Los Angeles, UO brings the ultimate holiday house party to life across its digital channels and stores through doorbell-inspired creative, festive editorial imagery and specialized gift shops. Content from the campaign’s editorial shoot extends the house party atmosphere across social and digital channels, with select video content featured on connected TV (CTV) platforms, including Hulu, Disney+, ESPN+ and Peacock.

The in-store and online UO Holiday Gift Shop features a curated assortment of exclusive collections and seasonal must-haves across apparel, footwear, beauty, and home. New Analog Gifting, Scent Shop, and Cozy Shop destinations bring the season’s most coveted gifts to life, curated around Gen Z’s evolving shopping habits and interests.

With giving at the heart of the season, UO is continuing to put community first through its three-month Giving Season initiative, running November to January. Alongside ongoing brand donations, customers can make contributions at checkout to support six of UO’s longstanding nonprofit partners: Altadena Girls, Active Minds, Creatives Want Change, Glisten, Rock to the Future, and Asian Arts Initiative.

For more information, visit urbanoutfitters.com.

About Urban Outfitters
Urban Outfitters is a global lifestyle brand dedicated to fueling the next generation’s individuality through a unique blend of product, creativity, music, and youth culture. Founded in 1970 in a small space across from the University of Pennsylvania, Urban Outfitters now operates over 200 stores across the United States, Canada, and Europe, alongside a dynamic digital presence. Empowering bold self-expression, Urban Outfitters leads with its distinctive designs and curated selection of women’s, men’s, accessories, and home products, and best-in-class brand partnerships. For more information, visit Urban Outfitters at www.urbanoutfitters.com.

View original content to download multimedia:https://www.prnewswire.com/news-releases/urban-outfitters-invites-everyone-to-the-party-with-all-together-now-more-the-merrier-holiday-campaign-302931715.html

SOURCE Urban Outfitters

Continue Reading

Technology

ExpertCrowd and HUD Collaborate to Advance AI Training and Evaluation, Release SWE Benchmark

Published

35 minutes ago

on

November 6, 2026

By

SAN FRANCISCO, Nov. 6, 2026 /PRNewswire/ — ExpertCrowd, Toptal‘s platform for training and improving AI models and systems, today announced a collaboration with HUD, a Y Combinator-backed startup that provides tools for building AI training data through its DataVendor™ marketplace. Together, the teams released ExpertCrowd-SWE, a software engineering benchmark that evaluates the performance of frontier-grade LLMs and coding agents.

As AI systems take on increasingly complex work, measuring their capabilities requires tasks that reflect professional practice and grading criteria that capture what successful execution actually means. This collaboration brings together ExpertCrowd’s expert-led task development and HUD’s infrastructure for running complex RL environments.

ExpertCrowd and HUD co-developed ExpertCrowd-SWE, bringing together engineers from Toptal’s global network of highly skilled domain experts with HUD’s experience collaborating with frontier research teams. After Toptal’s experts authored tasks and grading rubrics, HUD’s infrastructure hosted task-run environments and verified the benchmarks against internal quality assurance pipelines. HUD and Toptal’s AI research teams, composed of more than a dozen PhDs and researchers with educational or professional experience at Harvard, EPFL, the University of Liège, DeepMind, Qwen, and ByteDance, reviewed and assessed the methodology and results to build one of the most robust software engineering benchmarks in the industry.

“ExpertCrowd puts practitioners at the center of defining the work AI systems should perform and judging how well they perform it. By combining that specialized expertise with HUD’s testing infrastructure, we’re advancing what AI systems can achieve and setting a higher standard for real-world performance,” said Taso Du Val, founder and CEO of Toptal.

ExpertCrowd-SWE is the first release of an ongoing Toptal-HUD collaboration, with additional initiatives in development and further announcements coming soon. Building on this foundation, ExpertCrowd and HUD will bring more specialized human expertise into the tasks, environments, and evaluations that support the next generation of AI.

“We built HUD’s infrastructure to give research teams the tools to create realistic RL training environments, run evaluations across AI models, and inspect model performance. ExpertCrowd put that infrastructure to work, bringing the professional expertise to translate complex, real-world workflows into rigorous tasks, reference outputs, and evaluation frameworks that test the limits of today’s leading AI models,” said Jay Ram, founder and CEO of HUD.

About ExpertCrowd

ExpertCrowd is Toptal’s platform for training and improving AI models and systems through RLHF, RL data generation, data labeling, and model evaluation. It is powered by Toptal’s global talent network, with more than 30,000 specialized domain experts across 140+ countries, including more than 2,000 AI and big data specialists, 12,000 professionals with advanced degrees, and 1,000 PhD-level AI specialists, available on demand. For more information, please visit ExpertCrowd.com.

About HUD

HUD is a platform for building reinforcement learning environments, used by startups, Fortune 500 companies, and frontier labs. It provides infrastructure for training models, evaluating AI agents, and creating the post-training data that aligns AI to organizations’ work. HUD’s mission is to build reliable, fair, and open infrastructure for AI data with the goal of making data valuable for the people who create it and trustworthy for the labs that train on it. DataVendor™ is HUD’s marketplace, which allows AI labs to license training and evaluation data directly from the companies that created it. For more information, please visit HUD.ai.

Contact

Luiz Baia
SVP of Marketing Strategy
luiz.baia@toptal.com

SOURCE Toptal

Continue Reading

Trending