Peter Bankhead

This paper uses machine learning to predict genomic alterations from H&E images of liver tumors, revealing genotype-phenotype links and highlighting genetic background limitations.

GelGenie is an AI framework that automatically identifies gel bands in electrophoresis images, outperforming existing software and matching manual analysis.

The paper introduces ChannelNet, a deep learning architecture for segmenting cells and nuclei in multiplexed images, and demonstrates its effectiveness when combined with InstanSeg.

CLEAR-IT improves cell phenotyping in tumor microenvironments by using contrastive learning, outperforming existing methods across imaging modalities and requiring fewer labels.

OPTIMAL benchmarks segmentation and analysis methods for Imaging Mass Cytometry data, identifying optimal parameters for cell type identification and spatial analysis.

AimSeg is a machine learning tool for segmenting axons, inner tongue, and myelin in EM images, improving efficiency and accuracy over manual methods.

The BioImage Model Zoo provides a community standard, infrastructure, and open repository for sharing, testing, and deploying pre-trained deep learning microscopy models across multiple bioimage analysis tools.

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

Open-source QuPath combines tile-based whole slide viewing, object hierarchies and trainable classifiers; it automated CD3, CD8, p53, PD-L1 and stromal scoring that stratified colon cancer survival.