About
Lunit develops cutting-edge medical AI software designed to improve cancer detection rates and enable precision oncology at scale. Operating across 65+ countries and 10,000+ customer sites, the platform integrates seamlessly into existing radiology and pathology workflows to augment clinical decision-making. On the cancer screening side, Lunit INSIGHT MMG (2D) and INSIGHT DBT (3D) assist radiologists in detecting breast cancer earlier through AI analysis of mammography images, while Lunit INSIGHT CXR automates findings on chest X-rays. The ecosystem also includes tools for density assessment, risk stratification, quality management analytics, and patient engagement. For precision oncology, Lunit SCOPE IO performs tumor microenvironment (TME) analysis, while the SCOPE IHC Suite quantifies critical biomarkers such as HER2 and PD-L1 from whole-slide images, enabling faster and more reproducible companion diagnostic workflows. Biopharma partners leverage Lunit's AI for clinical trial acceleration and companion diagnostic strategy, reducing manual pathology workload and improving assay scalability. With over 700 peer-reviewed publications backing its technology, Lunit is a trusted partner for hospitals, radiology networks, and global pharmaceutical companies seeking to advance cancer outcomes through the power of AI.
Key Features
- AI Mammography Analysis: Lunit INSIGHT MMG (2D) and DBT (3D) analyze mammography images to flag suspicious lesions, improve detection sensitivity, and surface the smallest cancers often missed in routine reads.
- Chest X-ray AI (Lunit INSIGHT CXR): Automatically detects and localizes key findings on chest X-rays—such as nodules, consolidations, and cardiomegaly—helping radiologists triage and prioritize worklists efficiently.
- Tumor Microenvironment Analysis (Lunit SCOPE IO): Quantifies immune cell distribution within the tumor microenvironment from whole-slide pathology images, providing biomarker insights that inform immunotherapy treatment decisions.
- IHC Biomarker Quantification Suite: Automates scoring of HER2, PD-L1, and other IHC biomarkers with high reproducibility, replacing subjective manual pathology assessment and accelerating companion diagnostic workflows.
- Screening Ecosystem & Analytics: Integrates risk assessment, density scoring, quality management analytics, live mammography reporting, and patient engagement tools into a connected cancer screening platform.
Use Cases
- Radiology departments use Lunit INSIGHT MMG to improve mammography cancer detection rates and reduce false negatives in population screening programs.
- Hospitals deploy Lunit INSIGHT CXR to automate chest X-ray triage, prioritizing critical findings and reducing radiologist workload in high-volume settings.
- Pathology labs leverage Lunit SCOPE HER2 and PD-L1 to standardize and automate IHC biomarker scoring, replacing subjective manual assessment with reproducible AI quantification.
- Biopharma companies partner with Lunit to run AI-powered biomarker analysis across clinical trial cohorts, accelerating companion diagnostic strategy and patient selection.
- Cancer screening networks use Lunit's integrated ecosystem—including risk assessment, density scoring, and analytics dashboards—to manage program quality and improve early detection outcomes at scale.
Pros
- Clinically Validated at Scale: Backed by 700+ peer-reviewed publications and deployed across 10,000+ sites in 65+ countries, Lunit's AI has a deep evidence base supporting its clinical utility.
- End-to-End Cancer Care Coverage: Addresses the full oncology workflow—from population-level screening through to precision biomarker analysis—reducing the need for multiple disconnected tools.
- Seamless Workflow Integration: Designed to integrate with existing radiology PACS and pathology systems, minimizing disruption to clinical workflows while augmenting radiologist and pathologist output.
- Strong Biopharma Partnership Model: Offers dedicated AI solutions for clinical trial acceleration, CDx strategy, and global deployment, making it a valuable partner for pharmaceutical R&D organizations.
Cons
- Enterprise Pricing & Procurement: As a clinical-grade enterprise software solution, pricing is not publicly listed and typically requires direct engagement with the Lunit sales team, making evaluation slower for smaller institutions.
- Narrow Disease Focus: Lunit's AI is primarily focused on breast cancer and chest pathology screening, with oncology biomarkers centered on specific indications—not yet a general-purpose radiology AI covering all modalities.
- Requires IT & Regulatory Integration: Deploying clinical AI in hospital environments involves regulatory approvals, PACS integration, and IT infrastructure work that can extend implementation timelines.
Frequently Asked Questions
Lunit's AI is primarily focused on breast cancer (via mammography analysis with INSIGHT MMG and DBT) and lung/chest pathologies (via INSIGHT CXR). The precision oncology suite supports biomarker analysis relevant to multiple cancer types, including breast, lung, gastric, and others where HER2, PD-L1, and immune biomarkers are clinically actionable.
Lunit's solutions are designed to integrate with standard radiology PACS and digital pathology platforms via established interoperability protocols. Implementation is supported by Lunit's team and technology partners, though specific integration requirements vary by institution and existing infrastructure.
Lunit holds regulatory clearances in multiple markets. Specific clearance status varies by product and region—prospective customers should contact Lunit directly for the most up-to-date regulatory approvals relevant to their geography.
Lunit serves hospital radiology and pathology departments, cancer screening programs, and biopharma companies running oncology clinical trials or developing companion diagnostics. It operates across 65+ countries with 100+ partnerships.
Lunit's SCOPE platform automates IHC biomarker quantification and TME analysis at scale, enabling biopharma companies to accelerate patient stratification, companion diagnostic development, and retrospective study analysis across large multi-site trial datasets.
