About

Kimberly Cole is a Professor in the Department of Animal Sciences at The Ohio State University. She is based in the Animal Science Building, where her contact email is cole.436@osu.edu. Her research focuses on areas related to animal sciences, contributing to the academic and practical understanding of animal production and management. As a faculty member, she is involved in teaching, research, and extension activities that support the department's mission to advance knowledge in animal sciences and improve animal agriculture practices.

Research topics

• Artificial Intelligence
• Computer Science
• Medicine
• Political Science
• Pathology
• Internal medicine
• Business
• Finance
• Economics
• Economic growth
• Nursing
• Public relations

Selected publications

• 199 A Survey on Pathologic Evaluation of Extranodal Involvement in Axillary Metastases of Breast Cancer

  Laboratory Investigation · 2025-03-01 · 1 citations

  articleOpen access
  PublisherOA PDFDOI

• Generative adversarial networks accurately reconstruct pan-cancer histology from pathologic, genomic, and radiographic latent features

  Science Advances · 2024 · 21 citations

  • Artificial Intelligence
  • Computer Science
  • Artificial Intelligence

  Artificial intelligence models have been increasingly used in the analysis of tumor histology to perform tasks ranging from routine classification to identification of molecular features. These approaches distill cancer histologic images into high-level features, which are used in predictions, but understanding the biologic meaning of such features remains challenging. We present and validate a custom generative adversarial network-HistoXGAN-capable of reconstructing representative histology using feature vectors produced by common feature extractors. We evaluate HistoXGAN across 29 cancer subtypes and demonstrate that reconstructed images retain information regarding tumor grade, histologic subtype, and gene expression patterns. We leverage HistoXGAN to illustrate the underlying histologic features for deep learning models for actionable mutations, identify model reliance on histologic batch effect in predictions, and demonstrate accurate reconstruction of tumor histology from radiographic imaging for a "virtual biopsy."

  PublisherDOI

• Generative Adversarial Networks Accurately Reconstruct Pan-Cancer Histology from Pathologic, Genomic, and Radiographic Latent Features

  bioRxiv (Cold Spring Harbor Laboratory) · 2024-03-25 · 3 citations

  preprintOpen access

  Artificial intelligence models have been increasingly used in the analysis of tumor histology to perform tasks ranging from routine classification to identification of novel molecular features. These approaches distill cancer histologic images into high-level features which are used in predictions, but understanding the biologic meaning of such features remains challenging. We present and validate a custom generative adversarial network - HistoXGAN - capable of reconstructing representative histology using feature vectors produced by common feature extractors. We evaluate HistoXGAN across 29 cancer subtypes and demonstrate that reconstructed images retain information regarding tumor grade, histologic subtype, and gene expression patterns. We leverage HistoXGAN to illustrate the underlying histologic features for deep learning models for actionable mutations, identify model reliance on histologic batch effect in predictions, and demonstrate accurate reconstruction of tumor histology from radiographic imaging for a 'virtual biopsy'.

  PublisherOA PDFDOI

• Generative adversarial networks accurately reconstruct pan-cancer histology from pathologic, genomic, and radiographic latent features

  UNC Libraries · 2024-12-04

  articleOpen access

  Artificial intelligence models have been increasingly used in the analysis of tumor histology to perform tasks ranging from routine classification to identification of molecular features. These approaches distill cancer histologic images into high-level features, which are used in predictions, but understanding the biologic meaning of such features remains challenging. We present and validate a custom generative adversarial network-HistoXGAN-capable of reconstructing representative histology using feature vectors produced by common feature extractors. We evaluate HistoXGAN across 29 cancer subtypes and demonstrate that reconstructed images retain information regarding tumor grade, histologic subtype, and gene expression patterns. We leverage HistoXGAN to illustrate the underlying histologic features for deep learning models for actionable mutations, identify model reliance on histologic batch effect in predictions, and demonstrate accurate reconstruction of tumor histology from radiographic imaging for a "virtual biopsy."

  PublisherDOI

• Figure S6 from An Open-Source, Automated Tumor-Infiltrating Lymphocyte Algorithm for Prognosis in Triple-Negative Breast Cancer

  2023-03-31

  preprintOpen access

  <p>Correlation of QuPath machine read TIL scores of TMA cores to tissues in WTS format</p>

  PublisherDOI

• Table S2 from An Open-Source, Automated Tumor-Infiltrating Lymphocyte Algorithm for Prognosis in Triple-Negative Breast Cancer

  2023-03-31

  preprintOpen access

  <p>Areas of assessment</p>

  PublisherDOI

• 106 Use of biobehavioral responses during a novel object test to assess suitability of horses for equine assisted services

  Journal of Equine Veterinary Science · 2023-05-01

  articleOpen accessSenior author
  PublisherOA PDFDOI

• Figure S2 from An Open-Source, Automated Tumor-Infiltrating Lymphocyte Algorithm for Prognosis in Triple-Negative Breast Cancer

  2023-03-31

  preprintOpen access

  <p>Validation of QuPath TIL algorithms in TMA Yale1</p>

  PublisherDOI

• Table S4 from An Open-Source, Automated Tumor-Infiltrating Lymphocyte Algorithm for Prognosis in Triple-Negative Breast Cancer

  2023-03-31

  preprintOpen access

  <p>Correlation of TIL scores of overlapped cases between TMA Yale2 and WTS Yale sets</p>

  PublisherDOI

• Figure S1 from An Open-Source, Automated Tumor-Infiltrating Lymphocyte Algorithm for Prognosis in Triple-Negative Breast Cancer

  2023-03-31

  preprintOpen access

  <p>Schematic and H&E illustration of breast cancer annotated area and definition of QuPath TIL variables.</p>

  PublisherDOI

Frequent coauthors

• Jessica Bondy

  64 shared

• Kimberly Sidora

  64 shared

• Robert E. Cole

  64 shared

• David L. Olds

  Target (United States)

  64 shared

• Judith Glazner

  64 shared

• Carole Hanks

  64 shared

• Dennis W. Luckey

  University of Colorado Denver

  64 shared

• Yalai Bai

  Yale University

  18 shared

Education

• Ph.D., Animal Sciences

  The Ohio State University

  2005

• M.S., Animal Sciences

  The Ohio State University

  2001

• B.S., Animal Sciences

  The Ohio State University

  1999

Awards & honors

• Gamma Sigma Delta Extension Award of Merit (2013)
• CFAES Academic Mentor Award (2013)