Roh, Dana J.

The accurate diagnosis of chronic myelomonocytic leukemia (CMML) and acute myeloid leukemia (AML) subtypes with monocytic differentiation relies on the proper identification and quantitation of blast cells and blast-equivalent cells, including promonocytes. This distinction can be quite challenging given the cytomorphologic and immunophenotypic similarities among the monocytic cell precursors. The aim of this study was to assess the performance of convolutional neural networks (CNN) in separating monocytes from their precursors (i.e., promonocytes and monoblasts). We collected digital images of 935 monocytic cells that were blindly reviewed by five experienced morphologists and assigned into three subtypes: monocyte, promonocyte, and blast. The consensus between reviewers was considered as a ground truth reference label for each cell. In order to assess the performance of CNN models, we divided our data into training (70%), validation (10%), and test (20%) datasets, as well as applied fivefold cross validation. The CNN models did not perform well for predicting three monocytic subtypes, but their performance was significantly improved for two subtypes (monocyte vs. promonocytes + blasts). Our findings (1) support the concept that morphologic distinction between monocytic cells of various differentiation level is difficult; (2) suggest that combining blasts and promonocytes into a single category is desirable for improved accuracy; and (3) show that CNN models can reach accuracy comparable to human reviewers (0.78 ± 0.10 vs. 0.86 ± 0.05). As far as we know, this is the first study to separate monocytes from their precursors using CNN.

Abstract Objectives SF3B1 mutations are the most common mutations in myelodysplastic syndromes (MDS). The International Working Group for the Prognosis of MDS (IWG-PM) recently proposed SF3B1-mutant MDS (SF3B1-mut-MDS) as a distinct disease subtype. We evaluated the spectrum and molecular landscape of SF3B1-mutated myeloid disorders and assessed the prognostication in MDS harboring SF3B1 mutations (MDS-SF3B1). Methods Cases were selected by retrospective review. Clinical course and laboratory and clinical findings were collected by chart review. SF3B1-mut-MDS was classified following IWG-PM criteria. Results SF3B1 mutations were identified in 75 of 955 patients, encompassing a full spectrum of myeloid disorders. In MDS-SF3B1, Revised International Prognostic Scoring System (IPSS-R) score greater than 3 and transcription factor (TF) comutations were adverse prognostic markers by both univariate and multivariate analyses. We confirmed the favorable outcome of IWG-PM-defined SF3B1-mut-MDS. Interestingly, it did not show sharp prognostic differentiation within MDS-SF3B1. Conclusions SF3B1 mutations occur in the full spectrum of myeloid disorders. We independently validated the favorable prognostication of IWG-PM-defined SF3B1-mut-MDS. However it may not provide sharp prognostication within MDS-SF3B1 where IPSS-R and TF comutations were prognostic-informative. Larger cohort studies are warranted to verify these findings and refine MDS-SF3B1 prognostication.