Authors:
Joshua J. Levy
1
;
2
;
3
;
Christopher R. Jackson
2
;
Aravindhan Sriharan
2
;
Brock C. Christensen
1
and
Louis J. Vaickus
2
Affiliations:
1
Department of Epidemiology, Geisel School of Medicine, Dartmouth, Lebanon, U.S.A.
;
2
Department of Pathology, Dartmouth Hitchcock Medical Center, Dartmouth, Lebanon, U.S.A.
;
3
Program in Quantitative Biomedical Sciences, Geisel School of Medicine, Dartmouth, Lebanon, U.S.A.
Keyword(s):
Deep Learning, Histopathology, Image Translation.
Abstract:
Evaluation of a tissue biopsy is often required for the diagnosis and prognostic staging of a disease. Recent efforts have sought to accurately quantitate the distribution of tissue features and morphology in digitized images of histological tissue sections, Whole Slide Images (WSI). Generative modeling techniques present a unique opportunity to produce training data that can both augment these models and translate histologic data across different intra-and-inter-institutional processing procedures, provide cost-effective ways to perform computational chemical stains (synthetic stains) on tissue, and facilitate the creation of diagnostic aid algorithms. A critical evaluation and understanding of these technologies is vital for their incorporation into a clinical workflow. We illustrate several potential use cases of these techniques for the calculation of nuclear to cytoplasm ratio, synthetic SOX10 immunohistochemistry (IHC, sIHC) staining to delineate cell lineage, and the conversio
n of hematoxylin and eosin (H&E) stain to trichome stain for the staging of liver fibrosis.
(More)