Skip to Videos
  • biodataxai video image (clin-comp).png
    • 7/10/24

    Bridging the Clinical-computational Divide

    Pathologists may be slow to adopt computer aided diagnostic (CAD) tools due to limited comprehension of their design and purpose. Similarly, computer scientists may develop algorithms that, while technically proficient, lack clinical relevance. Better pathologist understanding of computational terminology and processes can foster building better CADs that are optimized for clinical purpose.

    Our proposed framework offers a standardized approach for aligning clinical goals with their computational execution.

    We hope to facilitate a shared language between computational scientists and pathologists, bridging the existing gap to ensure more synergistic, healthcare-forwarding collaborations in digital pathology.

  • Untitled design (5).png
    • 7/10/24

    Embracing the Multimodal Nature of Clinical AI Deployment: A Comprehensive TRL-Based Approach to Avoid Wastefulness and Ensure Responsible Innovation

    The integration of AI within clinical environments transcends simple data analysis, encompassing a complex interplay of multidimensional data, technological frameworks, procedural nuances, and interdisciplinary collaboration.

    The Clinical AI Readiness Evaluator (CARE) framework is a rigorous methodology to navigate and optimize this intricate landscape. Through its adoption, we can enhance the efficacy, responsibility, and sustainability of healthcare innovations.

  • Anatomic site group breakdown.jpg
    • 7/10/24

    The Role of Biobanking in Personalized Medicine and AI-enabled Translational Pathology Research

    Biobanks play an integral role in the nexus of personalized medicine, big data, and AI.

    Biobanks like the Cooperative Human Tissue Network (CHTN) are uniquely positioned to facilitate advanced medical research by providing high-quality, well-characterized biospecimens used to train and validate AI models for clinical use.

    Key challenges covered include data management, interoperability, and ethics in the collection and use of human tissue samples.

  • Figure 5.jpg
    • 7/10/24

    Feasibility of AI for Pathology Practice

    AI has the potential to transform the field of pathology by addressing unmet needs and enhancing the efficiency and accuracy of diagnostic processes.

    In exploring the feasibility of implementing AI in clinical pathology practices, we navigate:

    • Specific unmet needs within pathology that AI technology can potentially fulfill

    • The synergy of digital pathology with deep learning technologies, and -

    • Various generative and non-generative AI applications in pathology.

  • High-resolution section of WSI (PCNB adenocarcinoma in pt. w. elevated PSA).jpg
    • 7/10/24

    Histologic Features: Everything Old is New Again

    An extensive history follows the modern concept of feature extraction from histology images: the images that pathologists use to make gold standard diagnoses for many diseases.

    In 2024, there are now various options available to extract these features via computational methods.

  • Screenshot 2024-06-27 at 9.49.10 AM.png
    • 7/10/24

    AI to survive AI: A discussion about laboratory management systems role in preparing for an AI future

    As AI advances, laboratory archival information emerges as a crucial tool. With historical data serving as the bedrock of diagnostic truth, AI integrates this repository for modeling and testing. As novel laboratory tests reshape disease classification, AI adapts, accommodating evolving diagnostic paradigms. Archival data safeguards against AI-driven errors while pioneering dynamic diagnostic frameworks for the future.

  • Shields 2 copy (3).jpg
    • 7/10/24

    Transforming Pathology through Digital Innovation: The Mayo Clinic Experience

    The convergence of laboratory medicine, novel whole-slide imaging technologies, and the availability of cloud storage has created a unique opportunity for advancing patient care. At Mayo Clinic, state-of-the-art scanning facilities support the extensive digitization of pathology slides. The clinic has developed a robust infrastructure, including a dedicated team and advanced scanners, to handle the high volume of slides produced. Pramana scanners integrate AI for real-time quality control, ensuring high accuracy in digitizing archived tissue slides.

    By empowering pathologists with user-friendly AI tools to develop their own algorithms, Mayo Clinic fosters innovation and upskilling. Some of many successful AI projects are those resulting in automated scoring for eosinophilic esophagitis and integrating genomics with histopathology.

    Mayo Clinic's BioPharma initiative leverages a vast multimodal dataset, in partnership with biopharmaceutical companies, for biomarker discovery and validation. The initiative aims to provide end-to-end solutions for digital and molecular biomarker identification, enhancing the integration of clinical data with innovative technologies.

    the future of digital pathology, including the potential of 3D imaging, augmented reality (AR), and virtual reality (VR) to revolutionize diagnostic workflows. Examples include AI-driven mutation prediction algorithms and immersive VR environments for pathologists. All is poised to significantly enhance diagnostic precision, efficiency, and collaboration within the medical community.

    The Mayo Clinic approach underscores the importance of integrating cutting-edge technology with clinical expertise for better patient care.