Year: 2024
Type: conference-paper
Abstract: Understanding the way cells communicate, co-locate, and interrelate is essential to understanding human physiology. Hematoxylin and eosin (H&E) staining is ubiquitously available both for clinical studies and research. The Colon Nucleus Identification and Classification (CoNIC) Challenge has recently innovated on robust artificial intelligence labeling of six cell types on H&E stains of the colon. However, this is a very small fraction of the number of potential cell classification types. Specifically, the CoNIC Challenge is unable to classify epithelial subtypes (progenitor, endocrine, goblet), lymphocyte subtypes (B, helper T, cytotoxic T), or connective subtypes (fibroblasts, stromal). In this paper, we propose to use inter-modality learning to label previously un-labelable cell types on virtual H&E. We leveraged multiplexed immunofluorescence (MxIF) histology imaging to identify 14 subclasses of cell types. We performed style transfer to synthesize virtual H&E from MxIF and transferred the higher density labels from MxIF to these virtual H&E images. We then evaluated the efficacy of learning in this approach. We identified helper T and progenitor nuclei with positive predictive values of 0.34 ± 0.15 (prevalence 0.03 ± 0.01) and 0.47 ± 0.1 (prevalence 0.07 ± 0.02) respectively on virtual H&E. This approach represents a promising step towards automating annotation in digital pathology.
DOI: 10.1117/12.3006237
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funders: National Science Foundation, U.S. Department of Veterans Affairs, Vanderbilt University, Leona M. and Harry B. Helmsley Charitable Trust, Nvidia, Vanderbilt Institute for Clinical and Translational Research, Vanderbilt University Medical Center, Georgia Clinical and Translational Science Alliance, National Institutes of Health, National Institute of General Medical Sciences, National Institute of Diabetes and Digestive and Kidney Diseases, National Center for Research Resources, National Center for Advancing Translational Sciences
Awards: G1016015727, G1173929046, G1182793083, Vanderbilt Institute for Clinical and Translational Research (VICTR), G1331061530, G1390942713, G1473319671, G1486488711, G1531600799, CAREER: Modeling Personalized Brain Development with Big Data, G1853596577, G1942042315, G1951620746, G2043477120, G2109392540, G2209161966, G2284173953, G2308744219, G2537422520, G2591101265, G2759730755, Tuft cell heterogeneity in function, lineage, and structure in ileal inflammatory disease, G3002259123, NSF Convergence Accelerator Track D: Scalable, TRaceable Ai for Imaging Translation: Innovation to Implementation for Accelerated Impact (STRAIT I3), G326042038, G3606619490, G3619590958, G3724712001, Medical Scientist Training Program, G3958555850, G4107354744, G4195101910, G4290769314, G4425699080, Overall: Eunice Kennedy Shriver Intellectual and Developmental Disabilities Research Center at Vanderbilt, G4969333640, Graduate Research Fellowship Program (GRFP), G560889077, G5614773401, G563474107, G5679716143, G5868276417, G5993123900, The Vanderbilt Institute for Clinical and Translational Research (VICTR) UL1, G6246474086, G6263508347, G64116031, Spermidine as a New Therapy for Colitis and Chemopreventive for Colitis-associated Carcinogenesis, G6671297155, G6704072150, G6988210397, G7307553525, G7358180766, G7412434281, G7653134492, The Vanderbilt Institute for Clinical and Translational Research (VICTR), G8159288582, G8214155716, G8287001021, G872640053, G9000001553, G9000026873, G9000033427, G9000041293, G9000043901, G9000117310, G9000128600, G9000141600, G9000300101, Molecular and Cellular Basis for Digestive Diseases, G949362299, G95160140, G959610197
OpenAlex ID: W4393404049