Research Goals

Our areas of focus include the development and validation of digital pathologic and multi-modal deep learning models for:

Greater diagnostic accuracy and efficiency
 
 

Improved outcome prognostication and prediction of treatment response in cancer patient populations
 

Discovery of novel image-based biomarkers for precision medicine across various oncologic and non-oncologic diseases

Featured Publications

Inflamed immune phenotype predicts favorable clinical outcomes of immune checkpoint inhibitor therapy across multiple cancer types

J Immunother Cancer 2024

Computational pathology in 2030: a Delphi study forecasting the role of AI in pathology within the next decade

eBioMedicine 2023 

Deep learning model for the prediction of microsatellite instability in colorectal cancer: a diagnostic study

The Lancet Oncology 2021

Impact of a deep learning assistant on the histopathologic classification of liver cancer

NPJ Digit Med 2020

Deep learning assistance for the histopathologic diagnosis of Helicobacter pylori

Intelligence-Based Medicine 2020

Learning Domain-Agnostic Visual Representation for Computational Pathology Using Medically-Irrelevant Style Transfer Augmentation

IEEE Transactions on Medical Imaging 2021

Deep learning predicts postsurgical recurrence of hepatocellular carcinoma from digital histopathologic images

Scientific Reports 2021

Latest News

  • Weill Cancer Hub West
    – Shen Lab

    Weill Cancer Hub West

    Excited to be part of the Project IMPACT-AI team under the groundbreaking new Weill Cancer Hub West

  • Congratulations Mitch Peterson
    – Shen Lab

    Congratulations Mitch Peterson

    Congratulations to Mitch Peterson on receiving the 2025 Jack Kent Cooke Foundation graduate scholarship, as well as on his acceptance to the Electrical Engineering Master's program at Stanford!

  • Tucson Symposium
    – Shen Lab

    Tucson Symposium

    April 2, 2025 Thanks to the organizers of the 2025 Tucson Symposium for the opportunity to share our experiences with "Pathologists-in-the-loop: Case studies in AI-augmented Surgical Pathology" during the Digital Health session with esteemed co-presenters Faisal Mahmood ("Multimodal & generative AI for pathology") and Popi Siziopikou ("Artificial Intelligence (AI) in Breast Pathology: Promise and Challenges")

Supported By