Research
AI to Advance Pathology and Laboratory Medicine
Our Digital Pathology Research Center (DPRC) is driving pioneering research in digital pathology and AI-driven diagnostics.
The DPRC facilitates the testing and validation of multiple digital pathology instruments and platforms as well as artificial intelligence (AI) algorithms, aiding in standardization, technological advancements, regulatory approval and clinical deployment.
Part of what we do
We digitize glass pathology slides into high-resolution whole slide images (WSIs) using state-of-the-art scanners. These digital images allow us to:
- Store and share pathology data securely and efficiently
- Analyze slides using advanced machine learning and AI tools
- Build models that support diagnosis, prognosis, and personalized treatment decisions
Our Digital Pathology Research Focus
Our multidisciplinary teams are developing and validating AI algorithms that:
- Detect cancer and other diseases with high accuracy
- Quantify biomarkers and morphologic patterns
- Predict treatment response and patient outcomes
- Enhance consistency and productivity in pathology workflows
We collaborate closely with clinical departments, academic partners, and industry leaders to ensure our innovations are clinically relevant and ethically grounded.
Generative AI
We are dedicated to advancing the integration of generative AI technologies into pathology workflows to support and enhance pathologists’ diagnostic practice. We focus on developing novel generative models that can simulate, augment and interpret digital pathology data—enabling improved diagnostic accuracy, consistency and efficiency. Our research spans applications such as synthetic data generation for rare diseases, image-to-image translation for stain normalization and modality transformation, and automated report generation to streamline clinical documentation. Through interdisciplinary collaboration, we aim to build robust, clinically relevant AI tools that seamlessly integrate into existing pathology practices and accelerate the path from diagnosis to treatment.
Image-Based Research
Our focus is on advancing AI for medical imaging analysis, with applications spanning radiology, pathology and other image-intensive medical domains. We develop state-of-the-art AI algorithms to extract clinically meaningful insights from complex imaging data, aiming to improve diagnostic accuracy, prognostic assessment and treatment planning. Our research has a strong emphasis on clinical validation and real-world deployment. By bridging computational innovation with medical expertise, we strive to build trustworthy AI tools that empower clinicians and enhance patient care across diverse imaging modalities.
Multimodal AI
We are constantly working on advancing AI methodologies for multimodal health care data integration and analysis, aiming to unlock deeper, clinically actionable insights from the complex and heterogeneous data generated across the health care continuum. We develop AI models capable of learning from and reasoning across diverse data modalities—including medical imaging, molecular profiles, electronic health records, laboratory tests and clinical narratives. Our research emphasizes multimodal representation learning, data fusion techniques and predictive modeling to support tasks such as disease diagnosis, prognosis, treatment response prediction and personalized care. By leveraging the synergy between modalities, we strive to build intelligent systems that improve clinical decision-making, advance translational research and drive the next generation of precision medicine.
Lab Med and Molecular Pathology
We are dedicated to pioneering AI applications in laboratory medicine and molecular pathology, with the goal of transforming how complex diagnostic data is interpreted and used in clinical care. We focus on developing AI-driven methods to analyze high-dimensional molecular data, including genomics, transcriptomics, proteomics and laboratory test results, to support precision diagnostics, biomarker discovery and disease stratification. Our research also explores multi modal data integration, combining molecular profiles with imaging and clinical data to generate holistic, patient-specific insights. Through interdisciplinary collaboration, we aim to create scalable and interpretable AI solutions that enhance diagnostic accuracy, optimize laboratory workflows and enable data-driven decision-making in modern medicine.