1/2
25 files

Inference Dataset for Paper: Deep learning-based approach to the characterization and quantification of histopathology in mouse models of colitis, PLoS One

dataset
posted on 31.08.2022, 18:37 authored by Soma KobayashiSoma Kobayashi, Jason Shieh, Ainara Ruiz de Sabando, Julie Kim, Yang Liu, Sui Y. Zee, Prateek Prasanna, Agnieszka B. Bialkowska, Joel H. Saltz, Vincent W. Yang

Colitis mouse models have been heavily studied to elucidate the pathophysiology of human inflammatory bowel disease. As with patients, colitis mouse models exhibit the simultaneous presence of colonic regions that are histologically involved or uninvolved with disease. We have trained a ResNet-34 classifier to detect these regions from hematoxylin and eosin-stained whole murine colons. ‘Involved’ and ‘uninvolved’ image patches were gathered to cluster and identify histological patch classes. The per mouse proportions of these patch classes were then used to train machine learning classifiers to infer mouse model and clinical score bins.  This dataset contains the whole slide images (WSIs) from our prospective mouse cohort. This allows others to run our code from WSI scaling and patch extraction to 1) patch-level ‘Involved’ and ‘Uninvolved’ predictions, 2) ‘Involved’ versus ‘Uninvolved’ prediction WSI overlay generations, 3) histological patch class detection, and 4) mouse model and clinical score bin inference.

Funding

Regulation of Intestinal Epithelial Cell Proliferation

National Institute of Diabetes and Digestive and Kidney Diseases

Find out more...

TCIA Sustainment and Scalability - Platforms for Quantitative Imaging Informatics in Precision Medicine

National Cancer Institute

Find out more...

Methods and Tools for Integrating Pathomics Data into Cancer Registries

National Cancer Institute

Find out more...

History

Research Institution(s)

Renaissance School of Medicine at Stony Brook University

I confirm there is no human personally identifiable information in the files or description shared

Yes

I confirm the files and description shared may be publicly distributed under the license selected

Yes