本網站使用瀏覽器紀錄 (Cookies) 來提供您最好的使用體驗,我們使用的 Cookie 也包括了第三方 Cookie。相關資訊請訪問我們的隱私權與 Cookie 政策。如果您選擇繼續瀏覽或關閉這個提示,便表示您已接受我們的網站使用條款。 關閉
CHICAGO, Dec. 20, 2024 /PRNewswire/ -- As RSNA 2024 concluded, United Imaging Intelligence (UII), a subsidiary of United Imaging Group specializing in medical AI, made a significant impression with a visionary showcase that seamlessly aligned with the event's theme: "Building Intelligent Connections." Revolutionizing Healthcare with Groundbreaking Foundation Model Applications At the core of UII's showcase was the debut of the uAI PLUS (Pretrained Large Models for Unified Solutions), a foundational platform for advancing medical AI. By integrating Medical Imaging Foundation Models, Medical Large Language Models (LLMs), and Medical Multimodal Large Language Models (MLLMs), uAI PLUS redefines AI's capability to comprehend medical knowledge, imaging, and complex clinical scenarios with unprecedented depth and accuracy. This platform fosters innovation across clinical diagnosis, surgical treatment, biomedical research, hospital management, and patient services, unlocking unprecedented value and transforming workflows to improve efficiency, precision, and care outcomes. Building on the innovation of large models, UII highlighted the capabilities of hybrid models through two groundbreaking solutions: uAI AVATAR, a medical assistant powered by UII's Medical LLMs, and uAI MERITS PLUS, an advanced version of the company's surgical platform uAI MERITS with the integration of uAI AVATAR as an AI surgical assistant. These technologies showcased how voice interaction and deep understanding of medical scenarios can empower clinicians and enhance patient care. From preoperative planning and intraoperative navigation to personalized patient engagement, foundation models demonstrate their transformative potential in empowering clinicians and enhancing patient care. Creating Intelligent Connections in Global Communities This year's RSNA theme, "Building Intelligent Connections," set the stage for the uAI CONNECTS panel, which brought together eight distinguished experts from academia, clinical practice, and AI technology. They shared valuable insights on pressing topics, including AI's integration into clinical workflows and the creation of collaborative ecosystems. The discussions sparked engagement among attendees, who exchanged perspectives on AI's evolving role in healthcare and its impact on care delivery. The theme of intelligent connections is exemplified through UII's collaborations with leading global institutions. A standout example is a study conducted by Massachusetts General Hospital (MGH) on UII's pulmonary embolism detection algorithms, presented at this year's RSNA. This study evaluated the performance of UII's AI algorithms across diverse imaging centers, showcasing their robust generalizability and significant clinical relevance. These findings underscore UII's dedication to advancing healthcare through collaborative innovation and impactful partnerships. With a portfolio of 15 FDA-cleared applications (including 7 clinical applications, 3 algorithm-based solutions, and 5 uAI VISION applications) and 13 CE-marked applications, UII is strengthening its global connections across markets such as the United States, Europe, the Middle East, Southeast Asia, and beyond. At RSNA 2024, Dr. Terrence Chen, CEO of UII America, highlighted the excitement among attendees about the potential of uAI solutions to streamline workflows and improve patient outcomes. He noted that these interactions provided invaluable insights into regional needs, further strengthening collaborations and advancing the adoption of medical AI worldwide. At United Imaging, we develop and manufacture advanced medical products, digital healthcare solutions, and intelligent solutions that cover the entire process of imaging diagnosis and treatment. Founded in 2011, our company has subsidiaries and R&D centers across the world. Our North American headquarters in Houston includes our corporate offices, factory, product showroom, service training center, and service parts distribution center. With a cutting-edge digital portfolio and a mission of Equal Healthcare for All™, we help drive industry progress and bold change. To learn more, visit united-imaging.com or follow us on LinkedIn and Twitter @UnitedImagingHC. *Data on file.
CHICAGO, Dec. 12, 2024 /PRNewswire/ -- From December 1st to 5th, 2024, RSNA 2024—the largest and most future-oriented top medical event in the global radiology community, was held in Chicago. At this conference, Careverse officially made its debut, exhibiting in the AI Showcase area, sharing its innovative achievements in multimodal imaging AI and large language models with medical experts and scientists from around the world. Careverse booth at RSNA 2024 The theme of the 2024 RSNA Annual Meeting is "Building Intelligent Connections", denoting the important role of artificial intelligence in empowering radiologists to face the future. This is exactly what Careverse is committed to doing: to empower a new era of smart healthcare by creating an AI-powered Digital Doctor which assists human doctors to deliver much more efficient, accurate, consistent and accessible patient care. Careverse has an international product R & D and marketing team, cooperating with top hospitals and research institutions around the world. At present, it has launched more than 40 AI-powered clinical applications and holds numerous intellectual property rights globally. Careverse's products cover various modalities of medical imaging, such as CT, MRI, ultrasound, X-rays and mammography, etc., using a series of AI product combinations to reshape the entire workflow of disease management—from screening and diagnosis to treatment decision-making and follow-up care. This comprehensive approach significantly improve the efficiency and quality of the whole-cycle management of the most prevalent and life-threatening diseases in the world, including cardiovascular and neurovascular diseases, lung cancer, liver cancer, breast cancer, and numerous others. "Digital Heart" as a representative of multimodal AI changes traditional workflow The heart is one of the most complex organs in the human body, constantly beating, making imaging quite complex. Therefore, accurate diagnosis of heart diseases requires doctors to have rich clinical experience and profound professional knowledge accumulation. Careverse's "Digital Heart" product family takes the lead in applying AI to the automatic analysis of complex imaging data, aiming to accurately measure cardiac anatomy and various lesions, and present these key indicators in an intuitive and accurate manner preferred by doctors, assisting in generating diagnostic suggestions and pre-reports. This significantly reduces the manual workload of radiologists, enabling them to dedicate more time to accurate diagnoses and seamless collaboration with other clinical departments. In the screening process, Careverse enables fully automated calculation of non-gated coronary artery calcium scoring, quantifying the calcification of the four branches of the coronary artery (left main trunk, left circumflex, left anterior descending, right coronary artery) based on a single chest CT scan image data analysis, realizing the risk screening of coronary heart disease in asymptomatic populations. In the precise diagnosis process, Careverse's Coronary CTA product revolutionizes the traditional radiology workflow by enabling fully automated vessel segmentation and image reconstruction. This innovation eliminates the need for time-consuming post-processing and multi-step handoffs between post-processing doctors and diagnostic doctors, allowing for rapid, accurate assessments with the entire process completed in just 1 minute. As a result, doctor efficiency is significantly improved, and the patient experience is enhanced. Careverse's unique coronary AI model and algorithm also deliver superior image reconstruction, handling complex clinical scenarios like bypasses, stents, myocardial bridges, and ectopic origins with ease. While completing the morphological analysis of the coronary artery, doctors can also use Careverse's CT-FFR product to complete functional analysis, thereby further improving the accuracy of the diagnosis. Compared with the existing FFR analysis tools on the market, Careverse's fully automated CT-FFR product can generate the result directly within the hospital, with a calculation time three times shorter than semi-automatic products, and no manual intervention is required, which can be used as an objective and convenient tool for functional assessment of coronary artery stenosis. Careverse's CT-FFR product,which can complete functional analysis of the coronary artery Careverse's "Digital Heart" product family also includes intelligent analysis of coronary vulnerable plaques, peri-coronary fat, and CT heart function in CT modality, and coronary MRA AI and CMR AI products in MR modality. It can provide AI support for the diagnosis and treatment of cardiovascular disease patients at different stages. In addition to "Digital Heart," Careverse has also launched a series of AI products such as "Digital Brain", "Digital Chest", "Digital Abdomen", and "Digital Breast", covering imaging examinations of whole-body blood vessels, bones, and other important organs related to tumors in CT/MR and other scenarios. Integrated into a seamless Scan-to-Report process, they support disease-centered screening, diagnosis, treatment, and research. Clinically validated across multiple centers, these products deliver accuracy on par with expert human doctors. Careverse has also integrated the AI system with ultrasound equipment, introducing the world's first "Turing Brain" and "Turing AR" hardware technologies. These innovations enable real-time analysis of ultrasound video streams, displaying AI-enhanced lesion details directly on the original ultrasound screen. This advancement assists doctors during scanning and diagnosis, significantly improving the detection and diagnostic processes for conditions in areas such as breast, thyroid, carotid artery, and obstetrics. Dr. Josep Munuera, Director of the Diagnostic Imaging Service at Hospital Sant Pau in Spain, is at the forefront of AI research in advanced medical imaging. Reflecting on his decade-long experience attending the RSNA, Dr. Munuera noted a significant surge in the number of AI companies and the diversity of AI-driven applications in the field. "The medical imaging industry is undergoing a transformation — from machines that generate imaging data to software that analyzes it, driven by the rapid development of artificial intelligence," says Dr. Munuera. Dr. Munuera highlighted his appreciation for the comprehensive, full-body coverage offered by Careverse AI's solution. Unlike the need to rely on multiple vendors to target different anatomical areas, Careverse provides a single, unified platform. This approach is not only more convenient and easier to apply but also enables the accumulation of invaluable resources for physicians seeking a holistic view of patient health. "One of the key areas where AI is making a significant impact is in emergency care, such as acute chest pain" emphasized Dr. Munuera. He noted that Sant Pau is currently facing a shortage of radiologists to handle chest pain cases. Careverse's AI solution, which supports coronary CTA, CT-FFR, pulmonary embolism, and aortic dissection diagnosis, serves as a "Co-pilot" for radiologists. This solution enhances efficiency, optimizes capacity, and enables faster, more accurate diagnoses in high-pressure emergency scenarios.  Dr. Munuera, director of the Diagnostic Imaging Service at Hospital Sant Pau in Spain, highlighted his appreciation for the comprehensive, full-body coverage offered by Careverse AI's solution. Multimodal large language models lead future healthcare to a higher level Due to its deep accumulation in the medical imaging industry, Careverse naturally has a first-mover advantage in the era of medical large models, launching industry-leading AIGC solutions that can not only better assist radiologists but also bring great help to doctors in all departments of the hospital, which has been used in hundreds of hospitals. For example, when a liver disease patient comes to the imaging department for examination, Careverse's AIGC solution can act as a full-process digital assistant for doctors— Post-processing assistant: The liver's own anatomical structure is complex, and surgical history, tumor compression, or cirrhosis can cause variations in the liver substance and pipeline system, making precise segmentation of the liver and lesions difficult. Now, no matter which imaging examination the patient undergoes, such as X-ray, CT, MR, US, pathology, etc., doctors can use Careverse's leading medical imaging large language model to automatically segment, detect, and classify image data, greatly shortening image post-processing time. Diagnosis assistant: Due to the complexity and multifunctionality of the liver, liver diseases also show a wide variety of complex and diverse manifestations, posing challenges to accurate diagnosis. Careverse's large language model can integrate and compare different modalities of image data from the same patient, forming an unprecedented basis for image diagnosis. In addition, it has learned a large amount of medical literature and clinical guidelines, can output clinical reasoning analysis, thereby assisting doctors in differential diagnosis, can improve the diagnostic accuracy rate of difficult multiple diseases, and help doctors diagnose efficiency by 1 time. Modeling assistant: In assisting the treatment decision of liver disease, Careverse's large language model has excellent 3D image generation capabilities. It can produce movie-quality renderings of human organ structures, allowing for a detailed exploration of the course and interrelationships between interlobular vessels and bile ducts, and provide accurate basis for doctors to view organ lesions more intuitively and plan surgeries more effectively. Careverse's large language model has excellent 3D image generation capabilities. It can produce movie-quality renderings of human organ structures. Reporting assistant: During the examination and consultation process, Careverse's large language model can interpret existing reports, extract key information, and automatically generate reports in real-time according to the examination and diagnosis results, while checking the doctor's typos, assisting doctors in standardizing medical record writing. Q&A assistant: The AI Agent derived from Careverse's large language model also brings a new way of interaction for doctors and patients, which can conduct pre-consultation and give rehabilitation advice through dialogue. This helps to form a comprehensive patient health record, providing strong support for better prevention, accurate diagnosis, treatment decision-making, rehabilitation, and daily health monitoring. The combination of healthcare and AI is becoming increasingly close. The well-known consulting institution Fortune Business Insights predicts that the global healthcare AI market size will grow from $27.69 billion in 2024 to $490.96 billion in 2032, with a compound annual growth rate of 43.2%. As of now, Careverse has obtained 4 MDR CE markings, 2 FDA 510(K) approvals and 1 PMDA Certificate. With field-tested reliability and performance, the company's products have been embedded into the radiology workflow. Careverse has collaborated with top researching institutions in Japan, South East Asia, US and Europe, and their products are deployed in the hospitals in Asia, Europe, Middle East and US. Facing the vast market, Careverse will continue to innovate with multimodal medical large language model technology, build an open cooperative ecosystem, promote the deep integration and application of AI technology in the healthcare industry, and lead the new trend of intelligent healthcare services.
Lunit SCOPE® IO now available to SITC members for AI-powered TME profiling, in a collaborative effort to advance cancer immunotherapy SEOUL, South Korea, Feb. 3, 2025 /PRNewswire/ -- Lunit (KRX:328130.KQ), a leading provider of AI-powered solutions for cancer diagnostics and therapeutics, has entered into a partnership with the Society for Immunotherapy of Cancer (SITC). This collaboration will launch the "Lunit Research Program" for SITC members, granting access to Lunit SCOPE® IO for quantitative immune phenotyping and tumor microenvironment (TME) analysis from H&E whole slide images (WSIs). Lunit and SITC collaborate to offer SITC members exclusive access to Lunit SCOPE IO for AI-driven tumor microenvironment analysis. SITC is the world's leading member-driven organization specifically dedicated to improving cancer patient outcomes by advancing the science and application of cancer immunotherapy. Through this program, Lunit and SITC will support academic and non-profit researchers who are SITC members by offering use of Lunit's AI model, Lunit SCOPE IO, at no cost. The program will enable participants to conduct advanced analyses of histologic features from H&E whole slides images, including cell identification such as Tumor-Infiltrating Lymphocytes (TILs), macrophages, endothelial cells, and more; tissue segmentation; and quantitative immune phenotyping (e.g. inflamed, excluded, and desert), providing valuable insights for biomarker discovery and immunotherapy research. Lunit SCOPE IO is an AI solution developed to quantify histology from H&E WSIs, bridging the gap between pathology and precision oncology. Its advanced capabilities provide researchers with insights into the immune landscape of tumors, enabling the identification of biomarkers predictive of immunotherapy response. This innovative approach supports the discovery of novel treatment strategies and enhances cancer immunotherapy research. Lunit SCOPE IO leverages advanced deep learning algorithms to provide: Quantitative Immune Phenotyping: Classifying the tumor microenvironment into inflamed, excluded, and desert phenotypes provides actionable insights for immunotherapy strategies. TIL Analysis: Identifying and quantifying Tumor-Infiltrating Lymphocytes, a key biomarker for immune response. Comprehensive TME Profiling: Analyzing histologic features including stromal and immune components such as fibroblasts, macrophages, and endothelial cells. Support for Biomarker Discovery: Enabling researchers to identify novel biomarkers and assess correlations with therapeutic outcomes in cancer immunotherapy. This initiative aligns with Lunit's mission to bring AI-powered image analysis into routine cancer diagnostic research and clinical practice. By collaborating with SITC, the global authority in immunotherapy, Lunit aims to enhance immunotherapy research conducted by leading experts in oncology, pathology, and immunology. Program Highlights Eligibility: The program is open to SITC members affiliated with academic or non-profit research institutions, holding positions such as faculty member, research scientist, or postdoctoral fellow. Applicants must demonstrate expertise in oncology, pathology, or immunology. Application Process: Eligible members can submit a brief study outline (1-2 pages) and the principal investigator's CV. The application period runs from February 1 to April 30, with a review process taking 2-3 months. Resources Provided: Participants will receive complimentary access to Lunit SCOPE IO for analysis of H&E slides, as well as optional slide scanning services at cost. Desired Outcomes: The program encourages peer-reviewed publications and conference presentations detailing findings from studies using Lunit SCOPE IO. Timeline and Key Dates Application Period: February 1 – April 30, 2025 Review and Notifications: May – July 2025 Project Start Date: Summer 2025 "Through our partnership with SITC, we are enabling researchers to harness Lunit SCOPE IO's advanced AI capabilities for a deeper understanding of the tumor microenvironment," said Brandon Suh, CEO of Lunit. "We eagerly look forward to the discoveries and advancements this collaboration will bring, shaping the future of cancer immunotherapy and delivering more precise treatments to patients." "For forty years, SITC has been at the forefront of driving the immuno-oncology field in an effort to positively affect patient outcomes," said Mary Dean, Executive Director of SITC. "SITC is excited to make this benefit available to its members, enabling advancement to their impactful research." Contact Information For inquiries about the program, please contact: Dr. Siraj Ali, MD, PhD Email: SITCproject@lunit.io About Lunit Founded in 2013, Lunit (KRX:328130.KQ) is a medical AI company on a mission to conquer cancer. Lunit harnesses AI-powered medical image analytics and biomarker analysis to ensure accurate diagnosis and optimal treatment for each cancer patient. The FDA-cleared Lunit INSIGHT suite for cancer screening serves over 4,500 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 the 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. About SITC Established in 1984, the Society for Immunotherapy of Cancer (SITC) is a nonprofit organization of medical professionals dedicated to improving cancer patient outcomes by advancing the development, science and application of cancer immunotherapy and tumor immunology. SITC is comprised of influential basic and translational scientists, practitioners, health care professionals, government leaders and industry professionals around the globe. Through educational initiatives that foster scientific exchange and collaboration among leaders in the field, SITC aims to one day make the word "cure" a reality for cancer patients everywhere. Learn more about SITC, our educational offerings and other resources at sitcancer.org and follow us on X, LinkedIn, Facebook and YouTube.
DUBAI, UAE, Feb. 1, 2025 /PRNewswire/ -- United Imaging, a global leader in manufacturing advanced medical imaging and radiotherapy equipment, has showcased a series of game-changing innovations at Arab Health 2025, solidifying pivotal partnerships with healthcare and technology leaders. With an ever-expanding footprint in the global healthcare ecosystem, the company highlighted its advanced solutions, including the uMR ultra, uMI Panvivo, uRT 506c, uAngio AVIVA and the uSense platform for CT. The uRT 506c, the next-generation personalized precision radiotherapy platform, is a highlight, marking a new benchmark in radiotherapy innovation. The uAngio AVIVA, pioneering the paradigm in angiography, redefines interventional X-ray. Another key attraction at the event was the uSense platform, paving the way for an era of intelligent, instinct-driven CT imaging. These innovations underline United Imaging's commitment to empowering healthcare worldwide through cutting-edge imaging technologies and AI-driven diagnostic tools. This year, United Imaging Intelligence (UII), United Imaging Microelectronics, and United Imaging MetaHealthcare—subsidiaries of United Imaging Group—showcased their latest innovations, highlighting cutting-edge medical AI advancements, groundbreaking progress in medical large models, the uOrigin hearing aid product series and HearOn - hearing aids product turnkey solutions, as well as uMetaGenesis, refined medical device management solution. These highlights underscore the company's holistic approach to innovation. Notably, it marks the first time that the uOrigin hearing aid product series and uMetaGenesis have been officially introduced to the international market. During the event, United Imaging strengthened strategic partnerships with key healthcare and technology leaders across the Middle East and beyond. Collaborations with institutions. Among some of the key partnerships are collaborations with: Sezin Medical Imaging in Turkey, which will integrate the uMR Jupiter 5T, the world's first whole-body ultra-high field 5T MRI, into its operations, setting a new benchmark for MRI technology in the region. Al Mana Group in Saudi Arabia, one of the largest medical groups in the country, establishing a multi-disciplinary collaboration across CT, radiotherapy, molecular imaging, and AI to enhance diagnostic and treatment capabilities. KPJ Healthcare in Malaysia, which will feature the installation of uMI Vista, United Imaging's first digital PET/CT system in southern Malaysia, further advancing the nation's nuclear medicine offerings. Jaber Al-Ahmad Center for Nuclear Medicine and Molecular Imaging in Kuwait, where United Imaging's uMI Panorama 35 will be installed as part of the region's growing focus on advanced molecular imaging. Al-Khalidi Medical Center in Jordan, which will enhance its diagnostic and theranostic services with United Imaging's cutting-edge digital PET/CT and high-end MRI technology, particularly benefiting cancer patients. The Nairobi West Hospital in Kenya, using UIH Digital PET/CT will collaborate with United Imaging for uAngio, MRI, CT, MRI, DR systems and uAI solutions. These collaborations are a testament to United Imaging's role as a driving force in transforming healthcare, and they underscore the company's mission to deliver accessible, high-quality healthcare globally. Dr. Jusong Xia, President of International Business at United Imaging Healthcare, emphasized the company's commitment to medical technology innovation, particularly in artificial intelligence (AI). He stated, "Since its inception, United Imaging has made innovation a cornerstone of its strategy. We are honored that our advanced technologies, including AI, are trusted by global healthcare leaders. By integrating AI into our medical imaging solutions, we enhance diagnostic accuracy, improve patient outcomes, and expand access to high-quality healthcare. These partnerships demonstrate the transformative impact of innovation and collaboration, setting the stage for further advancements. Moving forward, we will strengthen our collaborations with key medical stakeholders, deliver greater value to our customers, and uphold our mission to bring equal healthcare to all." United Imaging's impact extends far beyond the Middle East. Up to now, with over 14,000 hospitals and institutions in more than 75 countries and regions utilizing more than 32000 United Imaging products, the company's innovations are making a significant difference in clinical settings worldwide. From the U.S. and Europe to Japan, Southeast Asia, and Africa, United Imaging is driving progress in medical imaging, AI diagnostics, and treatment capabilities across the globe. About United Imaging Healthcare United Imaging Healthcare was founded in 2011 with a commitment to providing high-performance medical imaging products, radiotherapy equipment, life science instruments, and intelligent digital solutions to global customers. With a mission " To Bring Equal Healthcare for All" and a vision to "lead healthcare innovation", United Imaging is continuously devoted to creating more value for its customers and improving the accessibility of high-end medical equipment and services worldwide through close collaborations with hospitals, universities, research institutions, and industry partners.
Newly published study in collaboration with Japan's NCCHE reveals how AI-powered HER2 and tumor microenvironment analysis improves patient stratification and clinical outcome predictions SEOUL, South Korea, Jan. 23, 2025 /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 the Journal of Clinical Oncology Precision Oncology. Conducted in collaboration with Japan's National Cancer Center Hospital East (NCCHE), the study reveals how Lunit's cutting-edge AI-powered pathology solutions, Lunit SCOPE® HER2 and Lunit SCOPE IO, significantly improve HER2 biomarker evaluation and the prediction of clinical outcomes in metastatic colorectal cancer (mCRC) patients undergoing HER2-targeted therapy. "Lunit SCOPE HER2", Lunit's AI-powered solution designed to detect HER2 expression profile This study presents findings from the TRIUMPH phase II clinical trial, which evaluated 30 patients with HER2-positive metastatic colorectal cancer treated with dual HER2-targeted therapy using Trastuzumab and Pertuzumab. Lunit's AI solutions were applied to assess HER2 status and tumor microenvironment (TME) variables, with significant findings: Enhanced HER2 Assessment Accuracy Lunit SCOPE HER2 demonstrated 86.7% accuracy compared to pathologist assessments for HER2 immunohistochemistry (IHC), achieving 100% accuracy in identifying HER2 IHC 3+ cases. Improved Prediction of Treatment Response and Outcomes Patients identified by the AI model as having a high proportion of HER2 IHC 3+ staining tumor cells (AI-H3-high, >50%) exhibited better clinical outcomes than those identified through traditional HER2 evaluation methods: Objective Response Rate (ORR): 42.1% (AI-H3-high) vs. 26.7% (overall TRIUMPH trial) Progression-Free Survival (PFS): 4.4 months (AI-H3-high) vs. 1.4 months (AI-H3-low) Overall Survival (OS): 16.5 months (AI-H3-high) vs. 4.1 months (AI-H3-low) Deeper Insights into the Tumor Microenvironment (TME) Using Lunit SCOPE IO, the study performed detailed TME profiling, including lymphocyte, macrophage, and fibroblast densities. Among AI-H3-high patients, those with low stromal TME density (TME-low) achieved the most favorable outcomes: ORR: 57.1% PFS: 5.6 months OS: 26.0 months The findings underscore the transformative potential of AI-powered pathology tools in precision oncology. By providing a more accurate and detailed evaluation of HER2 status and TME characteristics, Lunit's solutions can better stratify patients and predict responses to HER2-targeted therapies currently available or in development. This capability may inform more tailored treatment strategies, ultimately improving patient outcomes in mCRC and potentially other HER2-amplified cancers. "This study underscores the potential of AI technology to redefine how we evaluate biomarkers and predict treatment responses," said Dr. Takayuki Yoshino of the National Cancer Center Hospital East, principal investigator of the research. "The ability to more precisely stratify patients will lead to more personalized treatment options, improving outcomes for patients with HER2-positive metastatic colorectal cancer." "The findings from this study demonstrate how Lunit's AI-powered solutions, Lunit SCOPE HER2 and Lunit SCOPE IO, can provide clinicians with actionable insights to refine treatment strategies," said Brandon Suh, CEO of Lunit. "Our continued collaboration with NCCHE showcases the transformative potential of AI in precision oncology." About Lunit Founded in 2013, Lunit (KRX:328130.KQ) is a medical AI company on a mission to conquer cancer. Lunit harnesses AI-powered medical image analytics and biomarker analysis to ensure accurate diagnosis and optimal treatment for each cancer patient. The FDA-cleared Lunit INSIGHT suite for cancer screening serves over 4,500 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 the 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.
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.. Lunit's Universal Immunohistochemistry (uIHC) AI model, "Lunit SCOPE uIHC" 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.
A12 藝術空間
medical AI
請先登入後才能發佈新聞。
還不是會員嗎?立即 加入台灣產經新聞網會員 ,使用免費新聞發佈服務。 (服務項目) (投稿規範)