Although genomics has heavily influenced the diagnosis and clinical management of hematologic malignancies, histology still plays an essential role in diagnostic criteria for leukemias, myelodysplastic syndromes, myeloproliferative neoplasms, and lymphomas. These diseases are remarkably heterogeneous, and new diagnostic categories have emerged as understanding of the biologic properties and response to therapy of these diseases has evolved. In lymphomas like Diffuse Large B-cell lymphoma (DLBCL), immunohistochemical scoring of CMYC and BCL2 expression can complement gene expression based subtyping to identify patients with poor prognosis.

Computational methods can play an important role in both subtype discovery and in reproducible diagnosis. Integrating genomics and quantitative histologic measurements can be a powerful tool for exploring new diagnostic criteria that better explain biology and clinical outcomes. As criteria grow more complex, the use of quantitative measurements can help pathologists apply these criteria correctly and consistently so that patients can realize the benefits. Significant opportunities also exist for precursor lesions like myelodysplastic syndrome, where better methods can help decide between watchful waiting and intervention.


Ramraj Chandradevan
Alumni - Student


Chandradevan R, Aljudi AA, Drumheller BR, Kunananthaseelan N, Amgad M, Gutman DA, Cooper LA, Jaye DL. Machine-based detection and classification for bone marrow aspirate differential counts: initial development focusing on nonneoplastic cells. Laboratory Investigation. 2020 Jan;100(1):98-109.

Jordan J, Goldstein JS, Jaye DL, Gurcan M, Flowers CR, Cooper LA. Informatics approaches to address new challenges in the classification of lymphoid malignancies. JCO clinical cancer informatics. 2018 Feb;2:1-9.


Informatics Tools for Quantitative Digital Pathology Profiling and Integrated Prognostic Modeling
NCI U01CA220401