UCSF ohgami lab pdf nlp project corinn.small@ucsf.edu
Natural language processing (NLP) pipeline for the blastic plasmacytoid dendritic cell neoplasm (bpdcn) project. We want to streamline pdf analysis by using the aws sdk 'textract' and pull out relevant disease data including patient history, tissue/cell morphology, cell markers (disease cell origin/type), genetics, treatments and outcome. WE also want to eventually include images.