Andi Xu
Pronouns: She/her/hers
Research Mentor(s): Arvind Rao
Co-Presenter: Sun, Loria
Research Mentor School/College/Department: Computational Medicine and Bioniformatics / Medicine
Presentation Date: April 20
Presentation Type: Oral5
Session: Session 3 – 1:40pm – 2:30 pm
Room: Breakout room 3
Authors: Andi Xu, Loria Sun, Asheley Chen, Anirudh Attaluri, Omkar Yadav, Avery Maddox, Arvind Rao
Presenter: 2
Abstract
Bladder cancer is a heterogeneous disease and understanding tumor heterogeneity is critical for effective cancer prognosis and treatment. Analyzing spatial maps or whole-slide images (WSI) of tumors can help learn tumor heterogeneity and thus enable better patient-treatment matching. Previous studies have utilized deep learning methods to support digital analysis of pathology WSI and characterize tumor heterogeneity. The use of deep learning has shown great results in lung cancer and breast cancer. However, due to the heterogeneous nature of cancer, more tests to other cancers are needed. In this study, we developed deep-learning classifiers for predicting key mutation outcomes and important biological pathway activities in bladder cancer based on WSI, with a self-attention mechanism.
Biomedical Sciences, Engineering
