{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"submitter":["Goldgof GM"],"funding":["NHLBI NIH HHS"],"pubmed_abstract":["Morphology-based classification of cells in the bone marrow aspirate (BMA) is a key step in the diagnosis and management of hematologic malignancies. However, it is time-intensive and must be performed by expert hematopathologists and laboratory professionals. We curated a large, high-quality dataset of 41,595 hematopathologist consensus-annotated single-cell images extracted from BMA whole slide images (WSIs) containing 23 morphologic classes from the clinical archives of the University of California, San Francisco. We trained a convolutional neural network, DeepHeme, to classify images in this dataset, achieving a mean area under the curve (AUC) of 0.99. DeepHeme was then externally validated on WSIs from Memorial Sloan Kettering Cancer Center, with a similar AUC of 0.98, demonstrating r"],"journal":["bioRxiv : the preprint server for biology"],"pagination":["2023.02.20.528987"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9979993"],"repository":["biostudies-literature"],"pubmed_title":["DeepHeme: A generalizable, bone marrow classifier with hematopathologist-level performance."],"pmcid":["PMC9979993"],"funding_grant_id":["K38 HL159128","R38 HL143581"],"pubmed_authors":["Dogan A","Baik J","Lu CM","Goldgof DB","Goldgof GM","Wang L","Zhu M","Van Cleave J","Lucas F","Ardon O","Brown L","Prakash S","Sun S","Spector JD","Carmichael I","Boiocchi L","Butte AJ"],"additional_accession":[]},"is_claimable":false,"name":"DeepHeme: A generalizable, bone marrow classifier with hematopathologist-level performance.","description":"Morphology-based classification of cells in the bone marrow aspirate (BMA) is a key step in the diagnosis and management of hematologic malignancies. However, it is time-intensive and must be performed by expert hematopathologists and laboratory professionals. We curated a large, high-quality dataset of 41,595 hematopathologist consensus-annotated single-cell images extracted from BMA whole slide images (WSIs) containing 23 morphologic classes from the clinical archives of the University of California, San Francisco. We trained a convolutional neural network, DeepHeme, to classify images in this dataset, achieving a mean area under the curve (AUC) of 0.99. DeepHeme was then externally validated on WSIs from Memorial Sloan Kettering Cancer Center, with a similar AUC of 0.98, demonstrating r","dates":{"release":"2023-01-01T00:00:00Z","publication":"2023 Feb","modification":"2025-04-05T11:27:36.005Z","creation":"2025-04-05T11:27:36.005Z"},"accession":"S-EPMC9979993","cross_references":{"pubmed":["36865216"],"doi":["10.1101/2023.02.20.528987"]}}