Alexander T. Pearson

FEATMAP corrects acquisition signatures in medical foundation model embeddings to improve cross-condition similarity and task generalization without retraining.

MoPaDi generates counterfactual explanations for histopathology images to reveal morphological features driving classifier predictions, improving interpretability in digital pathology.

The paper identifies SOX2 as a master regulator of immune modulatory circuits in tumor-initiating stem cells, enabling immunosuppressive myeloid cell development.

This study improves immunotherapy model predictions by integrating data and ensuring parameter identifiability using ODE models and bladder cancer data.

This study identifies tumor-initiating cells that modulate neutrophil plasticity to create a protective niche, preventing immunotherapy effectiveness.

This study identifies molecular traits distinguishing HPV+ oropharyngeal cancer recurrence, showing reduced genomic instability contributes to tumor progression and immune suppression.

This paper introduces HistoXGAN, a GAN that reconstructs cancer histology from latent features, showing it retains tumor grade, histologic subtype, and gene expression patterns across 29 cancer types.

This study compares ODE and ABM models to show how spatial components affect immunotherapy outcomes in tumors with different antigenicity and CTL killing mechanisms.

This study uses dual RNA-seq to analyze co-regulation of human and SARS-CoV-2 genes, identifying tissue-specific expression patterns and potential therapeutic targets.

This paper shows that digital histopathology batch effects in TCGA data affect DL model accuracy and bias, and proposes a method to address this issue.

This paper develops a deep learning method to predict genetic alterations from histological images across multiple cancer types.